diff --git a/categories/ai-ml/llm-token-cost-reduction/SKILL.md b/categories/ai-ml/llm-token-cost-reduction/SKILL.md index 8045ef812..b20430386 100644 --- a/categories/ai-ml/llm-token-cost-reduction/SKILL.md +++ b/categories/ai-ml/llm-token-cost-reduction/SKILL.md @@ -49,7 +49,7 @@ Before proposing a fix, you may run: caveman learn simulate . Show it o as scale over scanned history: it sums over scanned history and never projects forward. -REDUCIBLE (a heavy CLAUDE.md, a never-invoked skill): +REDUCIBLE (a heavy AGENTS.md, a never-invoked skill): - Run: caveman learn apply --dry-run (this materializes a candidate; it does not edit anything). - Propose a concrete diff and show before -> after tokens/turn. @@ -77,7 +77,7 @@ re-pasted every turn. The candidate carries only a LOCATOR โ€” never the block b running caveman mem recall "" and reading tokens_added on the hit. If after is not below before, run caveman mem forget , leave the source untouched, and stop. -- Trim the source and write the pointer. Remove the block from its CLAUDE.md or +- Trim the source and write the pointer. Remove the block from its AGENTS.md or AGENTS.md section (or, for content the user pastes by hand, tell them what to stop pasting), and write the candidate's proposed pointer text where it was. The pointer names the recall path: caveman mem recall "" for the compact form, and diff --git a/categories/ai-ml/prompt-optimization/SKILL.md b/categories/ai-ml/prompt-optimization/SKILL.md index 641b32042..88aabf8d3 100644 --- a/categories/ai-ml/prompt-optimization/SKILL.md +++ b/categories/ai-ml/prompt-optimization/SKILL.md @@ -47,7 +47,7 @@ For repo or agent prompts, list stable context by exact path: | Context type | Examples | |--------------|----------| -| Agent rules | `AGENTS.md`, `CLAUDE.md` | +| Agent rules | `AGENTS.md` | | Specs | `specs/*.md`, `docs/api.md` | | Policies | `SECURITY.md`, `docs/releasing.md` | | Examples | `examples/`, `tests/fixtures/` | diff --git a/categories/caveman/caveman-compress/SKILL.md b/categories/caveman/caveman-compress/SKILL.md index 6b4039814..e5ba2b03a 100644 --- a/categories/caveman/caveman-compress/SKILL.md +++ b/categories/caveman/caveman-compress/SKILL.md @@ -10,7 +10,7 @@ tags: [caveman, prompt-compression] ## Purpose -Compress natural language files (CLAUDE.md, todos, preferences) into caveman-speak to reduce input tokens. Compressed version overwrites original. Human-readable backup saved as `.original.md`. +Compress natural language files (AGENTS.md, todos, preferences) into caveman-speak to reduce input tokens. Compressed version overwrites original. Human-readable backup saved as `.original.md`. ## Trigger diff --git a/categories/cursor-rules/agent-rule-management/SKILL.md b/categories/cursor-rules/agent-rule-management/SKILL.md index e68e9bc95..7618e9755 100644 --- a/categories/cursor-rules/agent-rule-management/SKILL.md +++ b/categories/cursor-rules/agent-rule-management/SKILL.md @@ -20,7 +20,7 @@ Creates rules at project or user level and manages the rule set at both. | "create / add / new rule", "convention", "standard", or a declarative description with no verb | create.md | | "list / show rules", "what rules exist" | list.md | | "edit / update / change rule X" | edit.md | -| "extract / split / move from AGENTS.md / CLAUDE.md", "AGENTS.md / CLAUDE.md is too big" | extract.md | +| "extract / split / move from AGENTS.md", "AGENTS.md is too big" | extract.md | | "delete / remove rule X" | delete.md | ## Workflow diff --git a/categories/cursor-rules/extra-context-prime/SKILL.md b/categories/cursor-rules/extra-context-prime/SKILL.md index 2dde68b8d..4d0075ee1 100644 --- a/categories/cursor-rules/extra-context-prime/SKILL.md +++ b/categories/cursor-rules/extra-context-prime/SKILL.md @@ -11,7 +11,7 @@ Prime Claude with comprehensive project understanding. ## Standard Context Loading: 1. Read README.md for project overview -2. Read CLAUDE.md for AI-specific instructions +2. Read AGENTS.md for AI-specific instructions 3. List project files excluding ignored paths 4. Review key configuration files 5. Understand project structure and conventions @@ -23,7 +23,7 @@ Prime Claude with comprehensive project understanding. - Note key technologies and dependencies 2. **AI Guidelines**: - - Read CLAUDE.md if present + - Read AGENTS.md if present - Load project-specific AI instructions - Note coding standards and preferences diff --git a/categories/documentation/agent-context-file-generation/SKILL.md b/categories/documentation/agent-context-file-generation/SKILL.md index 5da253c4f..3cfa19293 100644 --- a/categories/documentation/agent-context-file-generation/SKILL.md +++ b/categories/documentation/agent-context-file-generation/SKILL.md @@ -336,23 +336,9 @@ Fill in the real section names, technologies, and project-specific conventions. Agents read the nearest AGENTS.md in the directory tree. Nested files take precedence, so they should contain folder-specific details, not global ones. -## CLAUDE.md Companion File +## No Companion Files -Whenever you generate an `AGENTS.md` in a folder, also generate a `CLAUDE.md` in the same folder โ€” **only if `CLAUDE.md` does not already exist**. - -The `CLAUDE.md` content is always exactly: - -```markdown -# CLAUDE.md - - - -Before beginning work in this repository, read `AGENTS.md` and follow all scoped AGENTS guidance. -``` - -This ensures Claude Code (and similar tools that look for `CLAUDE.md`) are redirected to the authoritative `AGENTS.md` instructions. - -**Same guard applies:** check if `CLAUDE.md` exists before writing. If it exists, skip it. +`AGENTS.md` is the single source of truth. Do not generate a `CLAUDE.md`, `GEMINI.md`, or any other per-tool companion or pointer file alongside it โ€” agents that support `AGENTS.md` read it directly, and a second file only drifts from the first. ## Quality Principles diff --git a/categories/documentation/agent-facing-documentation/SKILL.md b/categories/documentation/agent-facing-documentation/SKILL.md index a4d0cad05..b2fbcd98a 100644 --- a/categories/documentation/agent-facing-documentation/SKILL.md +++ b/categories/documentation/agent-facing-documentation/SKILL.md @@ -9,7 +9,7 @@ tags: - context-management --- -Reference for writing any document an agent consumes: a skill, an `AGENTS.md` / `CLAUDE.md`, a doc reached by a pointer. The packaging differs; the writing does not: the same levers make each one predictable, since the agent takes the same _process_ every run rather than producing the same output. +Reference for writing any document an agent consumes: a skill, an `AGENTS.md`, a doc reached by a pointer. The packaging differs; the writing does not: the same levers make each one predictable, since the agent takes the same _process_ every run rather than producing the same output. When the document you're writing is a skill, read `SKILL-MECHANICS.md` for frontmatter, invocation choice, and router skills. diff --git a/categories/documentation/agent-instructions-file/SKILL.md b/categories/documentation/agent-instructions-file/SKILL.md index 1300d53c1..f8c318292 100644 --- a/categories/documentation/agent-instructions-file/SKILL.md +++ b/categories/documentation/agent-instructions-file/SKILL.md @@ -29,8 +29,7 @@ Goal: concise, actionable agent instructions. Target under 60 lines; never excee ## File Setup - Create `AGENTS.md` at the repository root. -- If a Claude-compatible entrypoint is required, symlink `CLAUDE.md` to `AGENTS.md`. -- Do not maintain divergent `AGENTS.md` and `CLAUDE.md` copies. +- Do not create per-tool companion files or symlinks alongside it; `AGENTS.md` is the single source of truth. ## Default Sections diff --git a/categories/documentation/readme-authoring/SKILL.md b/categories/documentation/readme-authoring/SKILL.md index 452e9ffc1..e5f561ec8 100644 --- a/categories/documentation/readme-authoring/SKILL.md +++ b/categories/documentation/readme-authoring/SKILL.md @@ -13,7 +13,7 @@ tags: Write a README that reads as a shop window, not a wiki. - **IS:** writing or rewriting `README.md` for the person deciding whether to use the project, with the project type driving which capability sections earn a place and where the file will render (GitHub only, or also a registry page) driving image and badge choices. -- **IS NOT:** polishing the prose of a README that already covers the project, or a multi-page docs site (use `docs-writing`); AGENTS.md or CLAUDE.md agent-instruction files (use `agents-md`); fixing the install or first-run experience the README describes (use `dx-audit`); marketing copy for a landing page (use `copywriting`). +- **IS NOT:** polishing the prose of a README that already covers the project, or a multi-page docs site (use `docs-writing`); AGENTS.md agent-instruction files (use `agents-md`); fixing the install or first-run experience the README describes (use `dx-audit`); marketing copy for a landing page (use `copywriting`). ## The reader @@ -150,7 +150,7 @@ Rewriting a published package's README, say in the summary that npmjs.com and Py | When | Run | |------|-----| | README exists and needs a prose audit, or a full docs site | `docs-writing` | -| Project needs agent instructions (AGENTS.md, CLAUDE.md), including the content the audience gate moved out | `agents-md` | +| Project needs agent instructions (AGENTS.md), including the content the audience gate moved out | `agents-md` | | The install or first-run path the README documents is itself the problem | `dx-audit` | | Landing-page or marketing copy beyond the tagline | `copywriting` | | Drafting in the user's own voice | external `ghostwriter` skill where installed, platform `readme` | diff --git a/categories/documentation/technical-docs-writing-audit/SKILL.md b/categories/documentation/technical-docs-writing-audit/SKILL.md index 830bdc77e..e58baf49b 100644 --- a/categories/documentation/technical-docs-writing-audit/SKILL.md +++ b/categories/documentation/technical-docs-writing-audit/SKILL.md @@ -126,7 +126,7 @@ For the full rule list per category, read `rules/_sections.md`. The `*-defaults. ## Related skills - `readme-creator`: a README from scratch or a full rewrite; this skill audits and fixes existing ones in place. -- `agents-md`: AGENTS.md/CLAUDE.md instruction files (execution-first, not reader-facing docs). +- `agents-md`: AGENTS.md instruction files (execution-first, not reader-facing docs). - `copywriting`: marketing, landing-page, and product copy. - `dx-audit`: the product's own error messages, CLI output, and API ergonomics; this skill covers how the docs describe them. - `optimise-seo`: implementing `llms.txt`, AI-crawler policy, and Markdown routes in a Next.js App Router site; `nav-agent-readable` says what the docs should expose, that skill builds it. diff --git a/categories/general/ag-agents-md/SKILL.md b/categories/general/ag-agents-md/SKILL.md index 3bb60da06..524a9ca01 100644 --- a/categories/general/ag-agents-md/SKILL.md +++ b/categories/general/ag-agents-md/SKILL.md @@ -1,6 +1,6 @@ --- name: ag-agents-md -description: "This skill should be used when the user asks to \"create AGENTS.md\", \"update AGENTS.md\", \"maintain agent docs\", \"set up CLAUDE.md\", or needs to keep agent instructions concise. Enforces research-bac..." +description: "This skill should be used when the user asks to \"create AGENTS.md\", \"update AGENTS.md\", \"maintain agent docs\", or needs to keep agent instructions concise. Enforces research-bac..." license: MIT tags: [general] risk: unknown @@ -12,14 +12,13 @@ source: community AGENTS.md is the canonical agent-facing documentation. Keep it minimalโ€”agents are capable and don't need hand-holding. Target under 60 lines; never exceed 100. Instruction-following quality degrades as document length increases. ## When to Use -- The user asks to create, update, or audit `AGENTS.md` or `CLAUDE.md`. +- The user asks to create, update, or audit `AGENTS.md`. - The project needs concise, high-signal agent instructions derived from the actual toolchain and repo layout. - Existing agent documentation is too long, duplicated, or drifting away from real project conventions. ## File Setup 1. Create `AGENTS.md` at project root -2. Create symlink: `ln -s AGENTS.md CLAUDE.md` ## Before Writing diff --git a/categories/general/ag-ai-md/SKILL.md b/categories/general/ag-ai-md/SKILL.md index d443a5f97..98c008e52 100644 --- a/categories/general/ag-ai-md/SKILL.md +++ b/categories/general/ag-ai-md/SKILL.md @@ -1,6 +1,6 @@ --- name: ag-ai-md -description: Convert human-written CLAUDE.md into AI-native structured-label format. +description: Convert human-written AGENTS.md into AI-native structured-label format. Battle-tested across 4 models. Same rules, fewer tokens, higher compliance. license: MIT tags: @@ -12,7 +12,7 @@ date_added: 2026-03-11 ## Real-World Results -Tested 2026-03, washinmura.jp CLAUDE.md, 5 rounds, 4 models: +Tested 2026-03, washinmura.jp AGENTS.md, 5 rounds, 4 models: | Round | Change | Codex (GPT-5.3) | Gemini 2.5 Pro | Claude Opus 4.6 | |-------|--------|-----------------|----------------|-----------------| @@ -27,7 +27,7 @@ Key findings: 3. **Cross-model consistency**: Format that works for one model works for all (except Grok) 4. **Semantic anchoring**: The `new-api:` label fix was the single most impactful change -**The uncomfortable truth: Your beautiful, carefully-written CLAUDE.md +**The uncomfortable truth: Your beautiful, carefully-written AGENTS.md might be HURTING your AI's performance. Structure > Prose. Always.** ## Limitations diff --git a/categories/general/ag-code-simplifier/SKILL.md b/categories/general/ag-code-simplifier/SKILL.md index c687e5525..621a60e08 100644 --- a/categories/general/ag-code-simplifier/SKILL.md +++ b/categories/general/ag-code-simplifier/SKILL.md @@ -29,7 +29,7 @@ Never change what the code does - only how it does it. All original features, ou ### 2. Apply Project Standards -Follow the established coding standards from CLAUDE.md including: +Follow the established coding standards from AGENTS.md including: - Use ES modules with proper import sorting and extensions - Prefer `function` keyword over arrow functions diff --git a/categories/general/ag-context-fundamentals/SKILL.md b/categories/general/ag-context-fundamentals/SKILL.md index 961cc26d6..31456ed61 100644 --- a/categories/general/ag-context-fundamentals/SKILL.md +++ b/categories/general/ag-context-fundamentals/SKILL.md @@ -95,7 +95,7 @@ The file system itself provides structure that agents can navigate. File sizes s ### Hybrid Strategies -The most effective agents employ hybrid strategies. Pre-load some context for speed (like CLAUDE.md files or project rules), but enable autonomous exploration for additional context as needed. The decision boundary depends on task characteristics and context dynamics. +The most effective agents employ hybrid strategies. Pre-load some context for speed (like AGENTS.md files or project rules), but enable autonomous exploration for additional context as needed. The decision boundary depends on task characteristics and context dynamics. For contexts with less dynamic content, pre-loading more upfront makes sense. For rapidly changing or highly specific information, just-in-time loading avoids stale context. diff --git a/categories/general/ag-faf-expert/SKILL.md b/categories/general/ag-faf-expert/SKILL.md index 0e5d94c9b..b615e1571 100644 --- a/categories/general/ag-faf-expert/SKILL.md +++ b/categories/general/ag-faf-expert/SKILL.md @@ -91,7 +91,7 @@ Expert setup of claude-faf-mcp with 33 tools: ### ๐Ÿ”„ Bi-Directional Sync Keep context synchronized across platforms: -- `.faf` โ†” `CLAUDE.md` +- `.faf` โ†” `AGENTS.md` - `.faf` โ†” `.cursorrules` - `.faf` โ†” `GEMINI.md` - `.faf` โ†” `AGENTS.md` diff --git a/categories/general/ag-faf-wizard/SKILL.md b/categories/general/ag-faf-wizard/SKILL.md index fd2176ad7..349ea24be 100644 --- a/categories/general/ag-faf-wizard/SKILL.md +++ b/categories/general/ag-faf-wizard/SKILL.md @@ -138,7 +138,7 @@ Already have AI context files? ```bash # Migrates existing context faf migrate --from .cursorrules -faf migrate --from CLAUDE.md +faf migrate --from AGENTS.md faf migrate --from README.md # One format, works everywhere diff --git a/categories/general/ag-gha-security-review/SKILL.md b/categories/general/ag-gha-security-review/SKILL.md index 03733b065..b0e0ea837 100644 --- a/categories/general/ag-gha-security-review/SKILL.md +++ b/categories/general/ag-gha-security-review/SKILL.md @@ -33,7 +33,7 @@ Review the workflows provided (file, diff, or repo). Research the codebase as ne - `.github/workflows/*.yml` โ€” all workflow definitions - `action.yml` / `action.yaml` โ€” composite actions in the repo - `.github/actions/*/action.yml` โ€” local reusable actions -- Config files loaded by workflows: `CLAUDE.md`, `AGENTS.md`, `Makefile`, shell scripts under `.github/` +- Config files loaded by workflows: `AGENTS.md`, `Makefile`, shell scripts under `.github/` ### Out of Scope @@ -122,7 +122,7 @@ Are elevated credentials (PATs, deploy keys) accessible to untrusted code? ### Check 5: Config File Poisoning Does the workflow load configuration from PR-supplied files? -- AI agent instructions: `CLAUDE.md`, `AGENTS.md`, `.cursorrules` +- AI agent instructions: `AGENTS.md`, `.cursorrules` - Build configuration: `Makefile`, shell scripts ### Check 6: Supply Chain diff --git a/categories/general/ag-hierarchical-agent-memory/SKILL.md b/categories/general/ag-hierarchical-agent-memory/SKILL.md index addb85c97..3b815b5f0 100644 --- a/categories/general/ag-hierarchical-agent-memory/SKILL.md +++ b/categories/general/ag-hierarchical-agent-memory/SKILL.md @@ -1,6 +1,6 @@ --- name: ag-hierarchical-agent-memory -description: "Scoped CLAUDE.md memory system that reduces context token spend. Creates directory-level context files, tracks savings via dashboard, and routes agents to the right sub-context." +description: "Scoped AGENTS.md memory system that reduces context token spend. Creates directory-level context files, tracks savings via dashboard, and routes agents to the right sub-context." license: MIT tags: [general] risk: safe @@ -10,13 +10,13 @@ date_added: 2026-02-27 # Hierarchical Agent Memory (HAM) -Scoped memory system that gives AI coding agents a cheat sheet for each directory instead of re-reading your entire project every prompt. Root CLAUDE.md holds global context (~200 tokens), subdirectory CLAUDE.md files hold scoped context (~250 tokens each), and a `.memory/` layer stores decisions, patterns, and an inbox for unconfirmed inferences. +Scoped memory system that gives AI coding agents a cheat sheet for each directory instead of re-reading your entire project every prompt. Root AGENTS.md holds global context (~200 tokens), subdirectory AGENTS.md files hold scoped context (~250 tokens each), and a `.memory/` layer stores decisions, patterns, and an inbox for unconfirmed inferences. ## When to Use This Skill - Use when you want to reduce input token costs across Claude Code sessions - Use when your project has 3+ directories and the agent keeps re-reading the same files -- Use when you want directory-scoped context instead of one monolithic CLAUDE.md +- Use when you want directory-scoped context instead of one monolithic AGENTS.md - Use when you want a dashboard to visualize token savings, session history, and context health - Use when setting up a new project and want structured agent memory from day one @@ -28,28 +28,28 @@ Auto-detects your project platform and maturity, then generates the memory struc ``` project/ -โ”œโ”€โ”€ CLAUDE.md # Root context (~200 tokens) +โ”œโ”€โ”€ AGENTS.md # Root context (~200 tokens) โ”œโ”€โ”€ .memory/ โ”‚ โ”œโ”€โ”€ decisions.md # Architecture Decision Records โ”‚ โ”œโ”€โ”€ patterns.md # Reusable patterns โ”‚ โ”œโ”€โ”€ inbox.md # Inferred items awaiting confirmation โ”‚ โ””โ”€โ”€ audit-log.md # Audit history โ””โ”€โ”€ src/ - โ”œโ”€โ”€ api/CLAUDE.md # Scoped context for api/ - โ”œโ”€โ”€ components/CLAUDE.md - โ””โ”€โ”€ lib/CLAUDE.md + โ”œโ”€โ”€ api/AGENTS.md # Scoped context for api/ + โ”œโ”€โ”€ components/AGENTS.md + โ””โ”€โ”€ lib/AGENTS.md ``` ### Step 2: Context Routing -The root CLAUDE.md includes a routing section that tells the agent exactly which sub-context to load: +The root AGENTS.md includes a routing section that tells the agent exactly which sub-context to load: ```markdown ## Context Routing -โ†’ api: src/api/CLAUDE.md -โ†’ components: src/components/CLAUDE.md -โ†’ lib: src/lib/CLAUDE.md +โ†’ api: src/api/AGENTS.md +โ†’ components: src/components/AGENTS.md +โ†’ lib: src/lib/AGENTS.md ``` The agent reads root, then immediately loads the relevant subdirectory context โ€” no guessing. @@ -60,7 +60,7 @@ Launches a web dashboard at localhost:7777 that visualizes: - Token savings (HAM-on vs HAM-off sessions) - Daily token and cost trends - Per-directory session breakdown -- Context file health (missing/stale/inherited CLAUDE.md coverage) +- Context file health (missing/stale/inherited AGENTS.md coverage) - Routing compliance (how often the agent follows the routing map) - Carbon/energy estimates @@ -68,12 +68,12 @@ Launches a web dashboard at localhost:7777 that visualizes: | Trigger | What it does | |---|---| -| `go ham` | Set up HAM โ€” auto-detect platform, generate CLAUDE.md files | +| `go ham` | Set up HAM โ€” auto-detect platform, generate AGENTS.md files | | `ham savings` | Show token and cost savings report | | `ham dashboard` | Launch the interactive web dashboard | | `ham audit` | Health check on memory files | | `ham insights` | Generate actionable insights from session data | -| `ham route` | Add/update Context Routing section in root CLAUDE.md | +| `ham route` | Add/update Context Routing section in root AGENTS.md | | `ham carbon` | Show energy and carbon efficiency data | ## Examples @@ -84,14 +84,14 @@ Launches a web dashboard at localhost:7777 that visualizes: User: go ham Agent: HAM setup complete. Created 8 files. - - CLAUDE.md (root) + - AGENTS.md (root) - .memory/decisions.md - .memory/patterns.md - .memory/inbox.md - - src/api/CLAUDE.md - - src/components/CLAUDE.md - - src/lib/CLAUDE.md - - src/utils/CLAUDE.md + - src/api/AGENTS.md + - src/components/AGENTS.md + - src/lib/AGENTS.md + - src/utils/AGENTS.md Baseline captured in .memory/baseline.json Run "HAM savings" to see your token and cost savings. @@ -114,8 +114,8 @@ Agent: ## Best Practices -- Keep root CLAUDE.md under 60 lines / 250 tokens -- Keep subdirectory CLAUDE.md files under 75 lines each +- Keep root AGENTS.md under 60 lines / 250 tokens +- Keep subdirectory AGENTS.md files under 75 lines each - Run `ham audit` every 2 weeks to catch stale or missing context files - Use `ham route` after adding new directories to keep routing current - Review `.memory/inbox.md` periodically โ€” confirm or reject inferred items @@ -125,8 +125,8 @@ Agent: - Token estimates use ~4 chars = 1 token approximation, not a real tokenizer - Baseline savings comparisons are estimates based on typical agent behavior - Dashboard requires Node.js 18+ and reads session data from `~/.claude/projects/` -- Context routing detection relies on CLAUDE.md read order in session JSONL files -- Does not auto-update subdirectory CLAUDE.md content โ€” you maintain those manually or via `ham audit` +- Context routing detection relies on AGENTS.md read order in session JSONL files +- Does not auto-update subdirectory AGENTS.md content โ€” you maintain those manually or via `ham audit` - Carbon estimates use regional grid averages, not real-time energy data ## Related Skills diff --git a/categories/general/ag-kaizen/SKILL.md b/categories/general/ag-kaizen/SKILL.md index a706d0a12..780f2e356 100644 --- a/categories/general/ag-kaizen/SKILL.md +++ b/categories/general/ag-kaizen/SKILL.md @@ -356,7 +356,7 @@ Follow established patterns. Document what works. Make good practices easy to fo **Documentation lives with code:** - README for setup and architecture -- CLAUDE.md for AI coding conventions +- AGENTS.md for AI coding conventions - Comments for "why", not "what" - Examples for complex patterns @@ -466,7 +466,7 @@ Documents why, when, and how **Before adding new patterns:** - Search codebase for similar problems solved -- Check CLAUDE.md for project conventions +- Check AGENTS.md for project conventions - Discuss with team if breaking from pattern - Update docs when introducing new pattern @@ -482,7 +482,7 @@ Documents why, when, and how - Check consistency with existing code - Point to examples in codebase - Suggest aligning with standards -- Update CLAUDE.md if new standard emerges +- Update AGENTS.md if new standard emerges ### 4. Just-In-Time (JIT) diff --git a/categories/general/ag-kubestellar-console/SKILL.md b/categories/general/ag-kubestellar-console/SKILL.md index bf2cd782d..fffd956ab 100644 --- a/categories/general/ag-kubestellar-console/SKILL.md +++ b/categories/general/ag-kubestellar-console/SKILL.md @@ -46,7 +46,7 @@ This bridges the active kubeconfig context to any MCP-compatible coding agent. D ### Step 3: Use built-in agent skills -The project ships with agent skills accessible via `CLAUDE.md` and `AGENTS.md`: +The project ships with agent skills accessible via `AGENTS.md`: - **@perf-test** โ€” Dashboard performance testing and TTFI analysis - **@cache-test** โ€” Card cache compliance testing (IndexedDB warm return) @@ -97,5 +97,4 @@ The project ships with agent skills accessible via `CLAUDE.md` and `AGENTS.md`: - [GitHub](https://github.com/kubestellar/console) - [Website](https://console.kubestellar.io) -- [CLAUDE.md](https://github.com/kubestellar/console/blob/main/CLAUDE.md) - [AGENTS.md](https://github.com/kubestellar/console/blob/main/AGENTS.md) \ No newline at end of file diff --git a/categories/general/ag-receiving-code-review/SKILL.md b/categories/general/ag-receiving-code-review/SKILL.md index 6fd6a6de3..07cbca7e3 100644 --- a/categories/general/ag-receiving-code-review/SKILL.md +++ b/categories/general/ag-receiving-code-review/SKILL.md @@ -32,7 +32,7 @@ WHEN receiving code review feedback: ## Forbidden Responses **NEVER:** -- "You're absolutely right!" (explicit CLAUDE.md violation) +- "You're absolutely right!" (explicit AGENTS.md violation) - "Great point!" / "Excellent feedback!" (performative) - "Let me implement that now" (before verification) diff --git a/categories/general/ag-skill-installer/SKILL.md b/categories/general/ag-skill-installer/SKILL.md index 294dbeef6..7f8f157ea 100644 --- a/categories/general/ag-skill-installer/SKILL.md +++ b/categories/general/ag-skill-installer/SKILL.md @@ -17,7 +17,7 @@ tools: None Esta skill e auto-detectada pelo `scan_registry.py` e matchada pelo `match_skills.py` quando o usuario menciona keywords de instalacao. Nenhuma configuracao manual necessaria. -Alem disso, o CLAUDE.md global contem instrucao para rodar o instalador automaticamente +Alem disso, o AGENTS.md global contem instrucao para rodar o instalador automaticamente apos o skill-creator finalizar uma skill. ## Best Practices diff --git a/categories/general/ag-skill-scanner/SKILL.md b/categories/general/ag-skill-scanner/SKILL.md index 80f1fb44d..449f6e716 100644 --- a/categories/general/ag-skill-scanner/SKILL.md +++ b/categories/general/ag-skill-scanner/SKILL.md @@ -91,7 +91,7 @@ This phase is agent-only โ€” no pattern matching. Read the full SKILL.md instruc - A skill described as "code formatter" that instructs the agent to read ~/.ssh is misaligned **Config/memory poisoning**: -- Instructions to modify `CLAUDE.md`, `MEMORY.md`, `settings.json`, `.mcp.json`, or hook configurations +- Instructions to modify `AGENTS.md`, `MEMORY.md`, `settings.json`, `.mcp.json`, or hook configurations - Instructions to add itself to allowlists or auto-approve permissions - Writing to `~/.claude/` or any agent configuration directory diff --git a/categories/general/ag-test-fixing/SKILL.md b/categories/general/ag-test-fixing/SKILL.md index 1cd82435d..85e849a92 100644 --- a/categories/general/ag-test-fixing/SKILL.md +++ b/categories/general/ag-test-fixing/SKILL.md @@ -53,7 +53,7 @@ For each group (starting with highest impact): 2. **Implement fix** - Use Edit tool for code changes - - Follow project conventions (see CLAUDE.md) + - Follow project conventions (see AGENTS.md) - Make minimal, focused changes 3. **Verify fix** diff --git a/categories/general/ag-ui-component/SKILL.md b/categories/general/ag-ui-component/SKILL.md index c7a11057e..98a85958c 100644 --- a/categories/general/ag-ui-component/SKILL.md +++ b/categories/general/ag-ui-component/SKILL.md @@ -30,7 +30,7 @@ Part of [StyleSeed](https://github.com/bitjaru/styleseed), this skill generates ### Step 1: Read the Local Design Context Before generating code, inspect the seed's source of truth: -- `CLAUDE.md` for conventions +- `AGENTS.md` for conventions - `css/theme.css` for semantic tokens - at least one representative component from `components/ui/` diff --git a/categories/general/ag-using-git-worktrees/SKILL.md b/categories/general/ag-using-git-worktrees/SKILL.md index c1c7ab5c7..b2d2c8135 100644 --- a/categories/general/ag-using-git-worktrees/SKILL.md +++ b/categories/general/ag-using-git-worktrees/SKILL.md @@ -32,17 +32,17 @@ ls -d worktrees 2>/dev/null # Alternative **If found:** Use that directory. If both exist, `.worktrees` wins. -### 2. Check CLAUDE.md +### 2. Check AGENTS.md ```bash -grep -i "worktree.*director" CLAUDE.md 2>/dev/null +grep -i "worktree.*director" AGENTS.md 2>/dev/null ``` **If preference specified:** Use it without asking. ### 3. Ask User -If no directory exists and no CLAUDE.md preference: +If no directory exists and no AGENTS.md preference: ``` No worktree directory found. Where should I create worktrees? @@ -153,7 +153,7 @@ Ready to implement | `.worktrees/` exists | Use it (verify ignored) | | `worktrees/` exists | Use it (verify ignored) | | Both exist | Use `.worktrees/` | -| Neither exists | Check CLAUDE.md โ†’ Ask user | +| Neither exists | Check AGENTS.md โ†’ Ask user | | Directory not ignored | Add to .gitignore + commit | | Tests fail during baseline | Report failures + ask | | No package.json/Cargo.toml | Skip dependency install | @@ -168,7 +168,7 @@ Ready to implement ### Assuming directory location - **Problem:** Creates inconsistency, violates project conventions -- **Fix:** Follow priority: existing > CLAUDE.md > ask +- **Fix:** Follow priority: existing > AGENTS.md > ask ### Proceeding with failing tests @@ -203,10 +203,10 @@ Ready to implement auth feature - Skip baseline test verification - Proceed with failing tests without asking - Assume directory location when ambiguous -- Skip CLAUDE.md check +- Skip AGENTS.md check **Always:** -- Follow directory priority: existing > CLAUDE.md > ask +- Follow directory priority: existing > AGENTS.md > ask - Verify directory is ignored for project-local - Auto-detect and run project setup - Verify clean test baseline diff --git a/categories/general/ag-vibers-code-review/SKILL.md b/categories/general/ag-vibers-code-review/SKILL.md index f0404fc52..d1e836a1c 100644 --- a/categories/general/ag-vibers-code-review/SKILL.md +++ b/categories/general/ag-vibers-code-review/SKILL.md @@ -57,7 +57,7 @@ jobs: ### Step 3. Add commit rules to your AI agent -Add this block to your project's `CLAUDE.md`, `.cursorrules`, or `AGENTS.md`: +Add this block to your project's `AGENTS.md` or `.cursorrules`: ```markdown ## Commit messages diff --git a/categories/general/agc-calver/SKILL.md b/categories/general/agc-calver/SKILL.md index b8a9ac092..4bb690c5a 100644 --- a/categories/general/agc-calver/SKILL.md +++ b/categories/general/agc-calver/SKILL.md @@ -64,7 +64,7 @@ version ver="": } ``` -## CLAUDE.md snippet +## AGENTS.md snippet ```markdown Update CHANGELOG.md under the [Unreleased] section with concise bullet points grouped under Added/Changed/Fixed/Removed. Combine or update items refined within the same session. Don't add version numbers; the build process computes the CalVer at release time via `make stamp-version`. Truncate when the file exceeds 2000 lines. diff --git a/categories/general/agc-compact-prep/SKILL.md b/categories/general/agc-compact-prep/SKILL.md index 7744d9d47..06d47c01c 100644 --- a/categories/general/agc-compact-prep/SKILL.md +++ b/categories/general/agc-compact-prep/SKILL.md @@ -10,11 +10,11 @@ argument-hint: [optional additional instructions] As such, could you please: -1. (Only if applicable) Update any state that tracks the work currently in progress / the state of the tasks being worked on, e.g. A development plan if operating from one, the CLAUDE.md ( Only if that is where the user has asked you to track in flight work and it does not only contain rules), etc... to ensure it's up to date without any now outdated or invalid information, if it has next steps that they are correct, and if you're mid troubleshooting a complex problem - where you've got to and what you've tried so far (but keep it concise). +1. (Only if applicable) Update any state that tracks the work currently in progress / the state of the tasks being worked on, e.g. A development plan if operating from one, the AGENTS.md ( Only if that is where the user has asked you to track in flight work and it does not only contain rules), etc... to ensure it's up to date without any now outdated or invalid information, if it has next steps that they are correct, and if you're mid troubleshooting a complex problem - where you've got to and what you've tried so far (but keep it concise). 2. Give me a concise prompt that I can provide to the compaction agent that will be compacting our conversation to ensure the signal to noise ratio is kept high and focused. The agent will already be aware of it's task to compact the conversation so only needs additional guidance on specific things that may not be obvious but are important to keep (e.g. the WHY not just the WHAT). -3. Give me a concise prompt that I can provide to continue our work after compaction is complete. Keep in mind that the new agent / session will have access to the same files and will have the same CLAUDE.md agent rules in context. +3. Give me a concise prompt that I can provide to continue our work after compaction is complete. Keep in mind that the new agent / session will have access to the same files and will have the same AGENTS.md agent rules in context. Note: You must not quote, indent or format the prompts in any way that might impact me copying and pasting them without cleaning them up. diff --git a/categories/general/agc-semver/SKILL.md b/categories/general/agc-semver/SKILL.md index ecde4faa8..6ceca31d5 100644 --- a/categories/general/agc-semver/SKILL.md +++ b/categories/general/agc-semver/SKILL.md @@ -110,7 +110,7 @@ version ver: Use `npm run version:bump 0.2.0`. -## CLAUDE.md snippet +## AGENTS.md snippet ```markdown Update CHANGELOG.md under the [Unreleased] section with concise bullet points grouped under Added/Changed/Fixed/Removed. Combine or update items refined within the same session. Don't add version numbers; at release time use `make version V=X.Y.Z` to bump the canonical version source and freeze the changelog (or `make stamp-version` to freeze using the existing version). Truncate when the file exceeds 2000 lines. diff --git a/categories/general/agc-step-back/SKILL.md b/categories/general/agc-step-back/SKILL.md index 4893ddc05..6c049853f 100644 --- a/categories/general/agc-step-back/SKILL.md +++ b/categories/general/agc-step-back/SKILL.md @@ -30,7 +30,7 @@ The caller should have told you: If any of this is missing or vague, ask for it before proceeding. Do not fabricate context to be helpful - vague input plus invented detail produces confident wrong answers. You have Read, Grep and Glob so you can verify claims about the code (e.g. "is this abstract type really only used once?"), but use them to check specifics, not to spelunk the whole repo. -Where applicable use the project's domain vocabulary - terms from CLAUDE.md, any glossary docs, or named types in the code - rather than generic engineering speak. "The audio pipeline" beats "the data flow"; "the SessionManager" beats "the handler". Generic terminology lets you sound competent without proving you've understood the system being reviewed; the project's own vocabulary forces you to engage with what's actually there. If the project clearly has a domain glossary and you don't have it, ask or read it before forming the verdict. +Where applicable use the project's domain vocabulary - terms from AGENTS.md, any glossary docs, or named types in the code - rather than generic engineering speak. "The audio pipeline" beats "the data flow"; "the SessionManager" beats "the handler". Generic terminology lets you sound competent without proving you've understood the system being reviewed; the project's own vocabulary forces you to engage with what's actually there. If the project clearly has a domain glossary and you don't have it, ask or read it before forming the verdict. ## The review diff --git a/categories/general/agent-configuration/SKILL.md b/categories/general/agent-configuration/SKILL.md index b30bbcf27..daf2d8ead 100644 --- a/categories/general/agent-configuration/SKILL.md +++ b/categories/general/agent-configuration/SKILL.md @@ -26,7 +26,7 @@ source: Claude Code Complete Guide 70 Tips (ykdojo + Ado Kukic) .claude/settings.json # Project settings .claude/skills/ # Project skills .agent-skills/ # Universal skills -CLAUDE.md # Project AI manual +AGENTS.md # Project AI manual ``` ### Security Priority diff --git a/categories/general/agent-context-setup/SKILL.md b/categories/general/agent-context-setup/SKILL.md index eed04b4b8..34dd619f1 100644 --- a/categories/general/agent-context-setup/SKILL.md +++ b/categories/general/agent-context-setup/SKILL.md @@ -30,7 +30,7 @@ Structure context from most persistent to most transient: ``` โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ” -โ”‚ 1. Rules Files (CLAUDE.md, etc.) โ”‚ โ† Always loaded, project-wide +โ”‚ 1. Rules Files (AGENTS.md, etc.) โ”‚ โ† Always loaded, project-wide โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค โ”‚ 2. Spec / Architecture Docs โ”‚ โ† Loaded per feature/session โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค @@ -46,7 +46,7 @@ Structure context from most persistent to most transient: Create a rules file that persists across sessions. This is the highest-leverage context you can provide. -**CLAUDE.md** (for Claude Code): +**AGENTS.md** (for Claude Code): ```markdown # Project: [Name] diff --git a/categories/general/agent-instruction-files/SKILL.md b/categories/general/agent-instruction-files/SKILL.md index 1b462f157..3d8579bef 100644 --- a/categories/general/agent-instruction-files/SKILL.md +++ b/categories/general/agent-instruction-files/SKILL.md @@ -63,7 +63,7 @@ Audit Progress: ```bash find . \( -name "AGENTS.md" -o -name "AGENTS.override.md" -o -name "CLAUDE.md" -o -name "CLAUDE.local.md" \) -not -path "*/node_modules/*" 2>/dev/null | sort -ls -la CLAUDE.md .claude/rules .cursor/rules 2>/dev/null +ls -la AGENTS.md .claude/rules .cursor/rules 2>/dev/null ``` Also check `~/.claude/CLAUDE.md` and `~/.codex/AGENTS.md`; both load in every repo. `ls -la CLAUDE.md` tells you whether it is a symlink, an `@AGENTS.md` pointer, or a second copy, and a copy is a finding on its own. For monorepos, include workspace-level files. Audit each level independently: root holds universal rules, child files hold directory-specific rules (see the placement hierarchy in `references/root-content-guidance.md`). @@ -117,7 +117,7 @@ Apply approved edits, re-score with the same checklist, report before/after scor ## Gotchas - Claude Code reads `CLAUDE.md`, not `AGENTS.md`. A repo with only `AGENTS.md` gives Claude Code no instructions and nothing warns; `/context` shows an empty Memory files list. Add a `CLAUDE.md` containing `@AGENTS.md`. -- `@import` moves text, not cost. Imported files are expanded into context at launch, so splitting a 400-line `CLAUDE.md` into five imports still loads 400 lines every session. Only nested files, path-scoped `.claude/rules/`, and skills load on demand. +- `@import` moves text, not cost. Imported files are expanded into context at launch, so splitting a 400-line `AGENTS.md` into five imports still loads 400 lines every session. Only nested files, path-scoped `.claude/rules/`, and skills load on demand. - `@import` reaches Claude Code only. Codex and Cursor pass the line through as text without warning, so an imported safety or format rule is absent from most sessions while the file still looks correct. - `@import` lines inside backticks or fenced blocks are literal text: a real import wrapped in a code span silently never loads. The same rule makes example imports inside fences safe to show. - Import chains stop at four hops; deeper content disappears with no error. @@ -135,9 +135,9 @@ Apply approved edits, re-score with the same checklist, report before/after scor ## Related Skills - `agent-skills-creator`: authoring and improving SKILL.md files (different format and rules). -- External `cadence-advise` skill where installed: proposes AGENTS.md/CLAUDE.md edits from observed session history; complements this skill's file-first audit. +- External `cadence-advise` skill where installed: proposes AGENTS.md edits from observed session history; complements this skill's file-first audit. - `readme-creator` / `docs-writing`: human-facing documentation; AGENTS.md content that belongs in docs should move there. - `codebase-architecture` (Harden mode): the rest of the repo an agent works in. A rule a linter can enforce belongs there as an exit code, not here as prose, and it owns the docs tree this file indexes. -- Claude Code's `/doctor` checkup: proposes trims for a checked-in `CLAUDE.md`, cutting what Claude can derive from the codebase and migrating always-loaded procedures into skills and nested files. Complementary automated triage; it doesn't run the commands, so it never replaces Step 6. +- Claude Code's `/doctor` checkup: proposes trims for a checked-in `AGENTS.md`, cutting what Claude can derive from the codebase and migrating always-loaded procedures into skills and nested files. Complementary automated triage; it doesn't run the commands, so it never replaces Step 6. Maintenance only: `evals/evals.json` contains regression scenarios for changes to this skill; it does not load during a user task. diff --git a/categories/general/agent-skill-authoring-agent-skills-creator/SKILL.md b/categories/general/agent-skill-authoring-agent-skills-creator/SKILL.md index 26ee58a40..7750f64d1 100644 --- a/categories/general/agent-skill-authoring-agent-skills-creator/SKILL.md +++ b/categories/general/agent-skill-authoring-agent-skills-creator/SKILL.md @@ -14,7 +14,7 @@ tags: Create and improve skills in the Agent Skills open format: full lifecycle from pattern selection through validation and README update. - **IS:** creating new agent skills and auditing or rewriting existing ones: SKILL.md, references, rules folders, scripts, evaluations. -- **IS NOT:** AGENTS.md/CLAUDE.md instruction files (use `agents-md`) or general documentation quality (use `docs-writing`). +- **IS NOT:** AGENTS.md instruction files (use `agents-md`) or general documentation quality (use `docs-writing`). ## Choose a Mode @@ -143,7 +143,7 @@ When installation behavior changed, install the edited local source into a dispo ## Related Skills -- `agents-md` for auditing AGENTS.md/CLAUDE.md instruction files +- `agents-md` for auditing AGENTS.md instruction files - `docs-writing` for documentation quality rules Maintenance only: `evals/evals.json` holds the behavioural scenarios and routing prompts for anyone changing this skill. It never loads during a user task, which is the baseline Phase A of `references/improving-existing-skills.md` asks for. diff --git a/categories/general/agentic-surface-audit/SKILL.md b/categories/general/agentic-surface-audit/SKILL.md index 00ecb9139..64e4ff21d 100644 --- a/categories/general/agentic-surface-audit/SKILL.md +++ b/categories/general/agentic-surface-audit/SKILL.md @@ -129,6 +129,6 @@ Flag the audit `INCOMPLETE` if any of these hold, and include the counts as evid - `ui-design` Audit mode: traditional frontend UX around agentic surfaces; run both on agentic feature PRs - `dx-audit`: same files, different reader. This skill asks whether an agent can operate and recover; `dx-audit` asks whether a human adopting the API, CLI, or types finds it ergonomic - `product-design`: what the agentic feature should do, before this audit -- `agents-md`: CLAUDE.md / AGENTS.md instruction files +- `agents-md`: AGENTS.md instruction files Maintenance only: `evals/evals.json` contains regression scenarios for changes to this skill; it does not load during a user task. diff --git a/categories/general/arb-usage/SKILL.md b/categories/general/arb-usage/SKILL.md index bb013678c..1dea0dd68 100644 --- a/categories/general/arb-usage/SKILL.md +++ b/categories/general/arb-usage/SKILL.md @@ -92,7 +92,7 @@ If your team uses more than one editor, use a portable baseline: - Keep one canonical `AGENTS.md` with a single `mini` rule set when the supported tools can handle it. - Use `nano` as the portable fallback only when `mini` is too large for one of the tools. - Let Codex read that file directly. -- Let Claude Code import it from `CLAUDE.md`. +- Let Claude Code import it from `AGENTS.md`. - Let Cursor either read `AGENTS.md` directly for simple projects or translate the same content into `.cursor/rules` for better scoping. - Add editor-specific on-demand mechanisms next to that baseline instead of duplicating a large global rule file. @@ -164,7 +164,7 @@ project/ - `CLAUDE.md` or `.claude/CLAUDE.md` - `CLAUDE.local.md` for private local additions -- `@path` imports inside `CLAUDE.md` +- `@path` imports inside `AGENTS.md` - `.claude/rules/` for scoped project rules - `.claude/skills//SKILL.md` - subagents @@ -178,13 +178,13 @@ Claude Code works best with a small root memory file plus scoped additions. Preferred order: -1. Keep root `CLAUDE.md` short. +1. Keep root `AGENTS.md` short. 2. If you want one shared cross-tool base file, put the chosen repo file at `AGENTS.md` and import it from `CLAUDE.md`. 3. Use Claude Code skills for book-specific workflows. 4. Use one `mini` rule set for always-on project context when the file stays short enough for the team. 5. Use `.claude/rules/` or path-scoped skills for `mini`. 6. Use `nano` only when the shared root file has to be much smaller. -7. Put procedures, large checklists, and long references into skills instead of the root `CLAUDE.md`. +7. Put procedures, large checklists, and long references into skills instead of the root `AGENTS.md`. 8. Use `disable-model-invocation: true` for side-effectful manual workflows such as deploy or release flows. 9. Use subagents or `context: fork` skills when a side task would otherwise flood the main context. @@ -199,13 +199,13 @@ Preferred order: ```text project/ AGENTS.md - CLAUDE.md + AGENTS.md .claude/ rules/ skills/ ``` -Example `CLAUDE.md`: +Example `AGENTS.md`: Import the shared root `AGENTS.md` baseline by adding this line to `CLAUDE.md` in order to reuse the same project-wide rules in Claude Code. @@ -226,7 +226,7 @@ Import the shared root `AGENTS.md` baseline by adding this line to `CLAUDE.md` i ### Avoid -- pasting a long `full` rule file into root `CLAUDE.md` +- pasting a long `full` rule file into root `AGENTS.md` - mixing many conflicting imports - relying on auto memory instead of reviewed project instructions diff --git a/categories/general/arezv-c-level-agents/SKILL.md b/categories/general/arezv-c-level-agents/SKILL.md index feaac3769..f3a6220b9 100644 --- a/categories/general/arezv-c-level-agents/SKILL.md +++ b/categories/general/arezv-c-level-agents/SKILL.md @@ -106,7 +106,7 @@ User question - persona-voices.md - llm-wiki-bridge.md -- Parent c-level CLAUDE.md +- Parent c-level AGENTS.md - [Existing executive-mentor sibling]() --- diff --git a/categories/general/arezv-c-level-skills/SKILL.md b/categories/general/arezv-c-level-skills/SKILL.md index 1b3cd319f..3608cf6e5 100644 --- a/categories/general/arezv-c-level-skills/SKILL.md +++ b/categories/general/arezv-c-level-skills/SKILL.md @@ -149,6 +149,6 @@ Culture Architect, Company OS, Founder Coach, Strategic Alignment, Change Manage ## See Also -- `CLAUDE.md` โ€” full architecture diagram and integration guide +- `AGENTS.md` โ€” full architecture diagram and integration guide - `agent-protocol/SKILL.md` โ€” communication standard and quality loop details - `chief-of-staff/SKILL.md` โ€” routing matrix for all 28 skills \ No newline at end of file diff --git a/categories/general/arezv-cs-agile-product-owner/SKILL.md b/categories/general/arezv-cs-agile-product-owner/SKILL.md index d4519f593..144c9ac18 100644 --- a/categories/general/arezv-cs-agile-product-owner/SKILL.md +++ b/categories/general/arezv-cs-agile-product-owner/SKILL.md @@ -407,8 +407,8 @@ echo "Location: product-team/agile-product-owner/references/user-story-templates - **Primary Skill:** [product-team/agile-product-owner/SKILL.md](SKILL.md) - **RICE Framework:** [product-team/product-manager-toolkit/SKILL.md](SKILL.md) -- **Product Domain Guide:** product-team/CLAUDE.md -- **Agent Development Guide:** CLAUDE.md +- **Product Domain Guide:** product-team/AGENTS.md +- **Agent Development Guide:** AGENTS.md - **Scrum Master Skill:** [project-management/scrum-master/SKILL.md](SKILL.md) --- diff --git a/categories/general/arezv-cs-ceo-advisor/SKILL.md b/categories/general/arezv-cs-ceo-advisor/SKILL.md index 7122e9a33..8feacfcd7 100644 --- a/categories/general/arezv-cs-ceo-advisor/SKILL.md +++ b/categories/general/arezv-cs-ceo-advisor/SKILL.md @@ -351,8 +351,8 @@ esac ## References - **Skill Documentation:** [c-level-advisor/skills/ceo-advisor/SKILL.md](SKILL.md) -- **C-Level Domain Guide:** c-level-advisor/CLAUDE.md -- **Agent Development Guide:** CLAUDE.md +- **C-Level Domain Guide:** c-level-advisor/AGENTS.md +- **Agent Development Guide:** AGENTS.md --- diff --git a/categories/general/arezv-cs-content-creator/SKILL.md b/categories/general/arezv-cs-content-creator/SKILL.md index cd3ad4bd0..f9a613f0a 100644 --- a/categories/general/arezv-cs-content-creator/SKILL.md +++ b/categories/general/arezv-cs-content-creator/SKILL.md @@ -237,8 +237,8 @@ cat marketing-skill/content-creator/references/analytics_guide.md ## References - **Skill Documentation:** [marketing-skill/content-creator/SKILL.md](SKILL.md) -- **Marketing Domain Guide:** marketing-skill/CLAUDE.md -- **Agent Development Guide:** CLAUDE.md +- **Marketing Domain Guide:** marketing-skill/AGENTS.md +- **Agent Development Guide:** AGENTS.md - **Marketing Roadmap:** marketing-skill/marketing_skills_roadmap.md --- diff --git a/categories/general/arezv-cs-cto-advisor/SKILL.md b/categories/general/arezv-cs-cto-advisor/SKILL.md index a6fa1f4a7..2ac8f6369 100644 --- a/categories/general/arezv-cs-cto-advisor/SKILL.md +++ b/categories/general/arezv-cs-cto-advisor/SKILL.md @@ -403,8 +403,8 @@ echo "- Process improvements identified" ## References - **Skill Documentation:** [c-level-advisor/skills/cto-advisor/SKILL.md](SKILL.md) -- **C-Level Domain Guide:** c-level-advisor/CLAUDE.md -- **Agent Development Guide:** CLAUDE.md +- **C-Level Domain Guide:** c-level-advisor/AGENTS.md +- **Agent Development Guide:** AGENTS.md --- diff --git a/categories/general/arezv-cs-demand-gen-specialist/SKILL.md b/categories/general/arezv-cs-demand-gen-specialist/SKILL.md index 572cfa473..47d8c88a5 100644 --- a/categories/general/arezv-cs-demand-gen-specialist/SKILL.md +++ b/categories/general/arezv-cs-demand-gen-specialist/SKILL.md @@ -280,8 +280,8 @@ fi ## References - **Skill Documentation:** [marketing-skill/marketing-demand-acquisition/SKILL.md](SKILL.md) -- **Marketing Domain Guide:** marketing-skill/CLAUDE.md -- **Agent Development Guide:** CLAUDE.md +- **Marketing Domain Guide:** marketing-skill/AGENTS.md +- **Agent Development Guide:** AGENTS.md - **Marketing Roadmap:** marketing-skill/marketing_skills_roadmap.md --- diff --git a/categories/general/arezv-cs-product-manager/SKILL.md b/categories/general/arezv-cs-product-manager/SKILL.md index b48a0c1cc..a224bd5a6 100644 --- a/categories/general/arezv-cs-product-manager/SKILL.md +++ b/categories/general/arezv-cs-product-manager/SKILL.md @@ -676,8 +676,8 @@ echo "Report: $QUARTER-roadmap.txt" ## References - **Skill Documentation:** [product-team/product-manager-toolkit/SKILL.md](SKILL.md) -- **Product Domain Guide:** product-team/CLAUDE.md -- **Agent Development Guide:** CLAUDE.md +- **Product Domain Guide:** product-team/AGENTS.md +- **Agent Development Guide:** AGENTS.md --- diff --git a/categories/general/arezv-cs-product-strategist/SKILL.md b/categories/general/arezv-cs-product-strategist/SKILL.md index d96c4c91e..d6f9fd6ad 100644 --- a/categories/general/arezv-cs-product-strategist/SKILL.md +++ b/categories/general/arezv-cs-product-strategist/SKILL.md @@ -479,8 +479,8 @@ python product-team/product-strategist/scripts/okr_cascade_generator.py growth - **Competitive Teardown Skill:** [product-team/competitive-teardown/SKILL.md](SKILL.md) - **OKR Framework:** product-team/product-strategist/references/okr_framework.md - **Strategy Types:** product-team/product-strategist/references/strategy_types.md -- **Product Domain Guide:** product-team/CLAUDE.md -- **Agent Development Guide:** CLAUDE.md +- **Product Domain Guide:** product-team/AGENTS.md +- **Agent Development Guide:** AGENTS.md --- diff --git a/categories/general/arezv-cs-project-manager/SKILL.md b/categories/general/arezv-cs-project-manager/SKILL.md index 908234224..0062bf413 100644 --- a/categories/general/arezv-cs-project-manager/SKILL.md +++ b/categories/general/arezv-cs-project-manager/SKILL.md @@ -507,8 +507,8 @@ echo "Template: project-management/senior-pm/assets/executive_report_template.md - **Jira Expert Skill:** [project-management/jira-expert/SKILL.md](SKILL.md) - **Confluence Expert Skill:** [project-management/confluence-expert/SKILL.md](SKILL.md) - **Atlassian Admin Skill:** [project-management/atlassian-admin/SKILL.md](SKILL.md) -- **PM Domain Guide:** project-management/CLAUDE.md -- **Agent Development Guide:** CLAUDE.md +- **PM Domain Guide:** project-management/AGENTS.md +- **Agent Development Guide:** AGENTS.md --- diff --git a/categories/general/arezv-cs-ux-researcher/SKILL.md b/categories/general/arezv-cs-ux-researcher/SKILL.md index 6cd4e6477..b26435b89 100644 --- a/categories/general/arezv-cs-ux-researcher/SKILL.md +++ b/categories/general/arezv-cs-ux-researcher/SKILL.md @@ -523,8 +523,8 @@ echo "See: product-team/ui-design-system/references/developer-handoff.md" - **Journey Mapping Guide:** product-team/ux-researcher-designer/references/journey-mapping-guide.md - **Usability Testing:** product-team/ux-researcher-designer/references/usability-testing-frameworks.md - **Design System:** [product-team/ui-design-system/SKILL.md](SKILL.md) -- **Product Domain Guide:** product-team/CLAUDE.md -- **Agent Development Guide:** CLAUDE.md +- **Product Domain Guide:** product-team/AGENTS.md +- **Agent Development Guide:** AGENTS.md --- diff --git a/categories/general/arezv-cs-wiki-ingestor/SKILL.md b/categories/general/arezv-cs-wiki-ingestor/SKILL.md index ec2436751..258fee346 100644 --- a/categories/general/arezv-cs-wiki-ingestor/SKILL.md +++ b/categories/general/arezv-cs-wiki-ingestor/SKILL.md @@ -22,7 +22,7 @@ You are spawned **per-ingest**, not as a long-running agent. You do one source a - Path to a source file (must be inside the vault's `raw/` layer) - The current state of `wiki/` (especially `index.md`) -- The vault's `CLAUDE.md` or `AGENTS.md` schema +- The vault's `AGENTS.md` schema ## Workflow diff --git a/categories/general/arezv-engineering-skills/SKILL.md b/categories/general/arezv-engineering-skills/SKILL.md index cafb0d695..d89f21043 100644 --- a/categories/general/arezv-engineering-skills/SKILL.md +++ b/categories/general/arezv-engineering-skills/SKILL.md @@ -78,4 +78,4 @@ No pip install needed. Scripts include embedded samples for demo mode. - Load only the specific skill SKILL.md you need โ€” don't bulk-load all 23 - Use Python tools for analysis and scaffolding, not manual judgment -- Check CLAUDE.md for tool usage examples and workflows \ No newline at end of file +- Check AGENTS.md for tool usage examples and workflows \ No newline at end of file diff --git a/categories/general/arezv-karpathy-coder/SKILL.md b/categories/general/arezv-karpathy-coder/SKILL.md index a9373f28b..4951d479e 100644 --- a/categories/general/arezv-karpathy-coder/SKILL.md +++ b/categories/general/arezv-karpathy-coder/SKILL.md @@ -119,7 +119,7 @@ Installs via plugin for Claude Code. For other tools, copy the principles into y | Tool | Schema file | |---|---| -| Claude Code | `CLAUDE.md` (auto-loaded by plugin) | +| Claude Code | `AGENTS.md` (auto-loaded by plugin) | | Codex CLI | `AGENTS.md` | | Cursor | `AGENTS.md` or `.cursorrules` | | Antigravity / OpenCode / Gemini CLI | `AGENTS.md` | diff --git a/categories/general/arezv-llm-wiki/SKILL.md b/categories/general/arezv-llm-wiki/SKILL.md index a9544e3cd..750e96709 100644 --- a/categories/general/arezv-llm-wiki/SKILL.md +++ b/categories/general/arezv-llm-wiki/SKILL.md @@ -44,7 +44,7 @@ vault/ โ”‚ โ”œโ”€โ”€ sources/ # One summary page per ingested source โ”‚ โ”œโ”€โ”€ comparisons/ # Cross-source analysis pages โ”‚ โ””โ”€โ”€ synthesis/ # High-level syntheses, theses, overviews -โ”œโ”€โ”€ CLAUDE.md # Schema + conventions (Claude Code) +โ”œโ”€โ”€ AGENTS.md # Schema + conventions (Claude Code) โ””โ”€โ”€ AGENTS.md # Same content, for Codex/Cursor/Antigravity ``` diff --git a/categories/general/arezv-monorepo-navigator/SKILL.md b/categories/general/arezv-monorepo-navigator/SKILL.md index 6ff96e91f..7465edf57 100644 --- a/categories/general/arezv-monorepo-navigator/SKILL.md +++ b/categories/general/arezv-monorepo-navigator/SKILL.md @@ -8,8 +8,8 @@ tags: ## Best Practices -1. **Root CLAUDE.md defines the map** โ€” document every package, its purpose, and dependency rules -2. **Per-package CLAUDE.md defines the rules** โ€” what's allowed, what's forbidden, testing commands +1. **Root AGENTS.md defines the map** โ€” document every package, its purpose, and dependency rules +2. **Per-package AGENTS.md defines the rules** โ€” what's allowed, what's forbidden, testing commands 3. **Always scope commands with --filter** โ€” running everything on every change defeats the purpose 4. **Remote cache is not optional** โ€” without it, monorepo CI is slower than multi-repo CI 5. **Changesets over manual versioning** โ€” never hand-edit package.json versions in a monorepo diff --git a/categories/general/arezv-promote/SKILL.md b/categories/general/arezv-promote/SKILL.md index 0fc32b527..d839e6aad 100644 --- a/categories/general/arezv-promote/SKILL.md +++ b/categories/general/arezv-promote/SKILL.md @@ -1,6 +1,6 @@ --- name: arezv-promote -description: Graduate a proven pattern from auto-memory (MEMORY.md) to CLAUDE.md or +description: Graduate a proven pattern from auto-memory (MEMORY.md) to AGENTS.md or .claude/rules/ for permanent enforcement. license: MIT tags: @@ -51,9 +51,9 @@ The pattern is now an enforced instruction. Claude will follow it in all future - It might change soon (e.g., during a migration) - It's already covered by existing rules -### CLAUDE.md vs .claude/rules/ +### AGENTS.md vs .claude/rules/ -| Use CLAUDE.md for | Use .claude/rules/ for | +| Use AGENTS.md for | Use .claude/rules/ for | |---|---| | Global project rules | File-type-specific patterns | | Build commands | Testing conventions | @@ -62,7 +62,7 @@ The pattern is now an enforced instruction. Claude will follow it in all future ## Tips -- Keep CLAUDE.md under 200 lines โ€” use rules/ for overflow +- Keep AGENTS.md under 200 lines โ€” use rules/ for overflow - One rule per line is easier to maintain than paragraphs - Include the concrete command, not just the concept - Review promoted rules quarterly โ€” remove what's no longer relevant diff --git a/categories/general/arezv-remember/SKILL.md b/categories/general/arezv-remember/SKILL.md index 25bdc26f4..88e724721 100644 --- a/categories/general/arezv-remember/SKILL.md +++ b/categories/general/arezv-remember/SKILL.md @@ -23,7 +23,7 @@ Writes an explicit entry to auto-memory when something is important enough that | Situation | Example | |-----------|---------| | Hard-won debugging insight | "CORS errors on /api/upload are caused by the CDN, not the backend" | -| Project convention not in CLAUDE.md | "We use barrel exports in src/components/" | +| Project convention not in AGENTS.md | "We use barrel exports in src/components/" | | Tool-specific gotcha | "Jest needs `--forceExit` flag or it hangs on DB tests" | | Architecture decision | "We chose Drizzle over Prisma for type-safe SQL" | | Preference you want Claude to learn | "Don't add comments explaining obvious code" | @@ -69,7 +69,7 @@ If MEMORY.md is over 180 lines, warn the user: If the knowledge sounds like a rule (imperative, always/never, convention): ``` -๐Ÿ’ก This sounds like it could be a CLAUDE.md rule rather than a memory entry. +๐Ÿ’ก This sounds like it could be a AGENTS.md rule rather than a memory entry. Rules are enforced with higher priority. Want to /si:promote it instead? ``` @@ -87,7 +87,7 @@ If the knowledge sounds like a rule (imperative, always/never, convention): ## What NOT to use /si:remember for - **Temporary context**: Use session memory or just tell Claude in conversation -- **Enforced rules**: Use `/si:promote` to write directly to CLAUDE.md +- **Enforced rules**: Use `/si:promote` to write directly to AGENTS.md - **Cross-project knowledge**: Use `~/.claude/CLAUDE.md` for global rules - **Sensitive data**: Never store credentials, tokens, or secrets in memory files @@ -97,4 +97,4 @@ If the knowledge sounds like a rule (imperative, always/never, convention): - Include the concrete command or value, not just the concept - โœ… "Build with `pnpm build`, tests with `pnpm test:e2e`" - โŒ "The project uses pnpm for building and testing" -- If you're remembering the same thing twice, promote it to CLAUDE.md \ No newline at end of file +- If you're remembering the same thing twice, promote it to AGENTS.md \ No newline at end of file diff --git a/categories/general/arezv-review/SKILL.md b/categories/general/arezv-review/SKILL.md index 12323d6c8..9427f6581 100644 --- a/categories/general/arezv-review/SKILL.md +++ b/categories/general/arezv-review/SKILL.md @@ -50,7 +50,7 @@ Analyze each entry for: 2. **Staleness indicators** - References files that no longer exist (`find` to verify) - Mentions outdated tools, versions, or commands - - Contradicts current CLAUDE.md rules + - Contradicts current AGENTS.md rules 3. **Consolidation opportunities** - Multiple entries about the same topic (e.g., three lines about testing) @@ -60,7 +60,7 @@ Analyze each entry for: - Appeared in 2+ sessions (check wording patterns) - Not project-specific trivia (broadly useful) - Actionable (can be written as a concrete rule) - - Not already in CLAUDE.md or `.claude/rules/` + - Not already in AGENTS.md or `.claude/rules/` ### Step 3: Read topic files @@ -69,12 +69,12 @@ If `MEMORY.md` references or the directory contains additional files (`debugging - Cross-reference with MEMORY.md for duplicates - Check for entries that belong in the main file (high value) vs. topic files (details) -### Step 4: Cross-reference with CLAUDE.md +### Step 4: Cross-reference with AGENTS.md -Read the project's `CLAUDE.md` (if it exists) and compare: -- Are there MEMORY.md entries that duplicate CLAUDE.md rules? (โ†’ remove from memory) -- Are there MEMORY.md entries that contradict CLAUDE.md? (โ†’ flag conflict) -- Are there MEMORY.md patterns not yet in CLAUDE.md that should be? (โ†’ promotion candidate) +Read the project's `AGENTS.md` (if it exists) and compare: +- Are there MEMORY.md entries that duplicate AGENTS.md rules? (โ†’ remove from memory) +- Are there MEMORY.md entries that contradict AGENTS.md? (โ†’ flag conflict) +- Are there MEMORY.md patterns not yet in AGENTS.md that should be? (โ†’ promotion candidate) Also check `.claude/rules/` directory for existing scoped rules. @@ -88,12 +88,12 @@ Output format: Memory Health: MEMORY.md: {{lines}}/200 lines ({{percent}}%) Topic files: {{count}} ({{names}}) - CLAUDE.md: {{lines}} lines + AGENTS.md: {{lines}} lines Rules: {{count}} files in .claude/rules/ ๐ŸŽฏ Promotion Candidates ({{count}}): 1. "{{pattern}}" โ€” seen {{n}}x, applies broadly - โ†’ Suggest: {{target}} (CLAUDE.md / .claude/rules/{{name}}.md) + โ†’ Suggest: {{target}} (AGENTS.md / .claude/rules/{{name}}.md) 2. ... ๐Ÿ—‘๏ธ Stale Entries ({{count}}): @@ -105,7 +105,7 @@ Memory Health: 2. ... โš ๏ธ Conflicts ({{count}}): - 1. MEMORY.md line {{n}} contradicts CLAUDE.md: {{detail}} + 1. MEMORY.md line {{n}} contradicts AGENTS.md: {{detail}} ๐Ÿ’ก Recommendations: - {{actionable suggestion}} diff --git a/categories/general/arezv-self-improving-agent/SKILL.md b/categories/general/arezv-self-improving-agent/SKILL.md index cea8e5ca8..7f5d993fe 100644 --- a/categories/general/arezv-self-improving-agent/SKILL.md +++ b/categories/general/arezv-self-improving-agent/SKILL.md @@ -1,7 +1,7 @@ --- name: arezv-self-improving-agent description: Curate Claude Code's auto-memory into durable project knowledge. Analyze - MEMORY.md for patterns, promote proven learnings to CLAUDE.md and .claude/rules/, + MEMORY.md for patterns, promote proven learnings to AGENTS.md and .claude/rules/, extract recurring solutions into reusable ... license: MIT tags: @@ -22,7 +22,7 @@ Analyzes MEMORY.md and topic files to identify: - Entries that recur across sessions (promotion candidates) - Stale entries referencing deleted files or old patterns - Related entries that should be consolidated -- Gaps between what MEMORY.md knows and what CLAUDE.md enforces +- Gaps between what MEMORY.md knows and what AGENTS.md enforces ### skill-extractor Takes a proven pattern and generates a complete skill: diff --git a/categories/general/arezv-wiki-init/SKILL.md b/categories/general/arezv-wiki-init/SKILL.md index 64f7b4020..e298942a2 100644 --- a/categories/general/arezv-wiki-init/SKILL.md +++ b/categories/general/arezv-wiki-init/SKILL.md @@ -40,7 +40,7 @@ Bootstrap a new LLM Wiki vault. Creates `raw/`, `wiki/{entities,concepts,sources โ”‚ โ”œโ”€โ”€ comparisons/ โ”‚ โ”œโ”€โ”€ synthesis/ โ”‚ โ””โ”€โ”€ .templates/ # page templates for reference -โ”œโ”€โ”€ CLAUDE.md # if --tool claude-code or all +โ”œโ”€โ”€ AGENTS.md # if --tool claude-code or all โ”œโ”€โ”€ AGENTS.md # if --tool codex|cursor|antigravity|opencode|gemini-cli|all โ”œโ”€โ”€ .cursorrules # if --tool cursor or all โ””โ”€โ”€ .gitignore diff --git a/categories/general/code-knowledge-graph/SKILL.md b/categories/general/code-knowledge-graph/SKILL.md index 5075e3b1a..5452db400 100644 --- a/categories/general/code-knowledge-graph/SKILL.md +++ b/categories/general/code-knowledge-graph/SKILL.md @@ -139,7 +139,7 @@ codegraph install 2. **`codegraph init -i` ๆ˜ฏๅฟ…้œ€็š„** โ€” ๆฏไธช้กน็›ฎ้ฆ–ๆฌกไฝฟ็”จๅ‰ๅฟ…้กปๅˆๅง‹ๅŒ–็ดขๅผ•๏ผŒๅฆๅˆ™ๆ‰€ๆœ‰ MCP ๅทฅๅ…ทๅคฑ่ดฅ 3. **้˜ฒๆŠ–็ช—ๅฃ๏ผˆ2s๏ผ‰ๅ†…็š„ๆ•ฐๆฎๅฏ่ƒฝ่ฟ‡ๆ—ถ** โ€” ็ผ–่พ‘ๅŽ็ซ‹ๅณๆŸฅ่ฏขๅฏ่ƒฝ่ฟ”ๅ›žๆ—งๆ•ฐๆฎ๏ผŒๆฃ€ๆŸฅ `โš ๏ธ` banner 4. **WSL/Windows ๅ…ฑไบซๆฃ€ๅ‡บ** โ€” ไธ่ฆๅ…ฑไบซๅŒไธ€ `.codegraph/`๏ผŒไฝฟ็”จ `CODEGRAPH_DIR` ๅŒบๅˆ† -5. **MCP ๆœๅŠกๅ™จ่‡ช่กŒไบคไป˜ไฝฟ็”จๆŒ‡ๅ—** โ€” ๆ— ้œ€ๆ‰‹ๅŠจ็ผ–่พ‘ CLAUDE.md๏ผŒๆŒ‡ๅ—้€š่ฟ‡ MCP initialize ่‡ชๅŠจไบคไป˜ +5. **MCP ๆœๅŠกๅ™จ่‡ช่กŒไบคไป˜ไฝฟ็”จๆŒ‡ๅ—** โ€” ๆ— ้œ€ๆ‰‹ๅŠจ็ผ–่พ‘ AGENTS.md๏ผŒๆŒ‡ๅ—้€š่ฟ‡ MCP initialize ่‡ชๅŠจไบคไป˜ 6. **ๆŽ’้™ค็›ฎๅฝ•** โ€” `node_modules`ใ€`dist`ใ€`build` ็ญ‰้ป˜่ฎคๆŽ’้™ค๏ผŒ้€š่ฟ‡ `.gitignore` ็ฎก็† 7. **ไฟกๆฏไธ่ถณๆ—ถไธ่ฆ็ฌผ็ปŸๆ้—ฎ** โ€” ๅ…ˆ่พ“ๅ‡บๅ‡่ฎพ็‰ˆๆœฌ๏ผŒๅ†ๅˆ—ๅ…ทไฝ“็ผบๅฐ‘้กน๏ผˆ่ง Workflow Step 3 ๆจกๆฟ๏ผ‰ diff --git a/categories/general/coding-session-retrospective/SKILL.md b/categories/general/coding-session-retrospective/SKILL.md index 25a7631b4..eefb95380 100644 --- a/categories/general/coding-session-retrospective/SKILL.md +++ b/categories/general/coding-session-retrospective/SKILL.md @@ -43,7 +43,7 @@ This means that the review agent should be responsible for imposing coding stand You have access to several files in the repo: -- `CLAUDE.md`/`AGENTS.md`: these files are pushed to the context window of any agent working in this repo. They should be used incredibly sparingly, usually only for **navigation pointers** to other files. +- `AGENTS.md`: this file are pushed to the context window of any agent working in this repo. They should be used incredibly sparingly, usually only for **navigation pointers** to other files. - `CODING_STANDARDS.md`: this file is read during review, not implementation. Add **navigation pointers** to docs folders if the standards file gets more than 1,000 lines long. - Docs: use docs as references files, pointed to by other files. Look for existing docs before writing new ones. - Skills: use skills for docs (since their description goes into the agent's context window), or for user-invoked commands. Follow the advice in the `writing-for-agents` skill. diff --git a/categories/general/cursor-agents-md/SKILL.md b/categories/general/cursor-agents-md/SKILL.md index 93672f8a0..af5e6e5b1 100644 --- a/categories/general/cursor-agents-md/SKILL.md +++ b/categories/general/cursor-agents-md/SKILL.md @@ -43,6 +43,6 @@ AGENTS.md is the instruction file for OpenAI Codex (and increasingly, other tool ## AGENTS.md Is Becoming a Standard - GitHub Copilot coding agent now reads AGENTS.md files (announced July 2025) -- GitHub also supports CLAUDE.md and GEMINI.md at the repo root as alternatives +- GitHub also supports AGENTS.md and GEMINI.md at the repo root as alternatives - Copilot has its own format too: `.github/copilot-instructions.md` and path-specific `.github/instructions/*.instructions.md` - The ecosystem is fragmenting โ€” if you support multiple tools, you may need multiple instruction files. AGENTS.md has the broadest adoption beyond its origin tool \ No newline at end of file diff --git a/categories/general/cursor-copilot-instructions/SKILL.md b/categories/general/cursor-copilot-instructions/SKILL.md index 08d8b2f19..bb84ed5a8 100644 --- a/categories/general/cursor-copilot-instructions/SKILL.md +++ b/categories/general/cursor-copilot-instructions/SKILL.md @@ -19,7 +19,7 @@ author: cursorrules-collection ## Agent Instructions (AGENTS.md) - Copilot coding agent also reads AGENTS.md files (the OpenAI Codex format) - Nearest AGENTS.md in the directory tree takes precedence over others -- Copilot also supports CLAUDE.md and GEMINI.md at the repo root as alternatives +- Copilot also supports AGENTS.md and GEMINI.md at the repo root as alternatives - If you have both `copilot-instructions.md` and AGENTS.md, both are used ## What Works Well diff --git a/categories/general/cursor-windsurf-rules/SKILL.md b/categories/general/cursor-windsurf-rules/SKILL.md index c844a425f..f1dab1f49 100644 --- a/categories/general/cursor-windsurf-rules/SKILL.md +++ b/categories/general/cursor-windsurf-rules/SKILL.md @@ -15,7 +15,7 @@ Windsurf (formerly Codeium) has two customization systems: Rules (persistent con ## Rules (Persistent Context) - **Current format (Wave 8+)**: Markdown files in `.windsurf/rules/` at the project root. Each file gets a descriptive name and contains rules in plain markdown - **Legacy format**: Single `.windsurfrules` file at the project root (still supported, but the new format is preferred) -- Rules provide persistent context to Cascade (Windsurf's AI agent) for every interaction โ€” similar to .cursorrules or CLAUDE.md +- Rules provide persistent context to Cascade (Windsurf's AI agent) for every interaction โ€” similar to .cursorrules or AGENTS.md - The GUI provides a visual editor wrapper around the markdown files, but you can edit them directly ## Rules Discovery diff --git a/categories/general/design-system-rule-generation/SKILL.md b/categories/general/design-system-rule-generation/SKILL.md index ec1a399d2..2ded14dd5 100644 --- a/categories/general/design-system-rule-generation/SKILL.md +++ b/categories/general/design-system-rule-generation/SKILL.md @@ -20,7 +20,7 @@ This skill helps you generate custom design system rules tailored to your projec | Agent | Rule File | |-------|-----------| -| Claude Code | `CLAUDE.md` | +| Claude Code | `AGENTS.md` | | Codex CLI | `AGENTS.md` | | Cursor | `.cursor/rules/figma-design-system.mdc` | @@ -178,7 +178,7 @@ Detect which AI coding agent the user is working with and save the generated rul | Agent | Rule File | Notes | |-------|-----------|-------| -| Claude Code | `CLAUDE.md` in project root | Markdown format. Can also use `.claude/rules/figma-design-system.md` for modular organization. | +| Claude Code | `AGENTS.md` in project root | Markdown format. Can also use `.claude/rules/figma-design-system.md` for modular organization. | | Codex CLI | `AGENTS.md` in project root | Markdown format. Append as a new section if file already exists. 32 KiB combined size limit. | | Cursor | `.cursor/rules/figma-design-system.mdc` | Markdown with YAML frontmatter (`description`, `globs`, `alwaysApply`). | diff --git a/categories/general/design-to-code-implementation/SKILL.md b/categories/general/design-to-code-implementation/SKILL.md index 49e739ca4..7c2ea06c8 100644 --- a/categories/general/design-to-code-implementation/SKILL.md +++ b/categories/general/design-to-code-implementation/SKILL.md @@ -21,7 +21,7 @@ This skill provides a structured workflow for translating Figma designs into pro - If the user asks to create/edit/delete nodes inside Figma itself, switch to figma-use. - If the user asks to build or update a full-page screen in Figma from code or a description, switch to figma-generate-design. - If the user asks only for Code Connect mappings, switch to figma-code-connect-components. -- If the user asks to author reusable agent rules (`CLAUDE.md`/`AGENTS.md`), switch to figma-create-design-system-rules. +- If the user asks to author reusable agent rules (`AGENTS.md`), switch to figma-create-design-system-rules. ## Prerequisites diff --git a/categories/general/developer-experience-audit/SKILL.md b/categories/general/developer-experience-audit/SKILL.md index c4e733cae..25fa8e3d3 100644 --- a/categories/general/developer-experience-audit/SKILL.md +++ b/categories/general/developer-experience-audit/SKILL.md @@ -149,7 +149,7 @@ Re-open every touched or cited location, rerun the same probes and focused proje - `pr-reviewer`: general correctness and structure of a diff - `docs-writing`: documentation prose and information quality - `readme-creator`: README structure and first-reader narrative -- `agents-md`: AGENTS.md and CLAUDE.md instruction files +- `agents-md`: AGENTS.md instruction files - `codebase-architecture`: repository structure and module contracts inside the repo, rather than the surface a package ships outward Maintenance only: `evals/evals.json` contains regression scenarios for changes to this skill; it does not load during a user task. diff --git a/categories/general/engineering-workspace-setup/SKILL.md b/categories/general/engineering-workspace-setup/SKILL.md index 625696300..475406c49 100644 --- a/categories/general/engineering-workspace-setup/SKILL.md +++ b/categories/general/engineering-workspace-setup/SKILL.md @@ -78,7 +78,7 @@ Let them edit before writing. **Pick the file to edit:** -- If `CLAUDE.md` exists, edit it. +- If `AGENTS.md` exists, edit it. - Else if `AGENTS.md` exists, edit it. - If neither exists, ask the user which one to create; don't pick for them. diff --git a/categories/general/flow-agent-base-template-generator/SKILL.md b/categories/general/flow-agent-base-template-generator/SKILL.md index 8e91e7bc2..ddbc7b88b 100644 --- a/categories/general/flow-agent-base-template-generator/SKILL.md +++ b/categories/general/flow-agent-base-template-generator/SKILL.md @@ -9,7 +9,7 @@ You are a Base Template Generator, an expert architect specializing in creating Your core responsibilities: - Generate comprehensive base templates for components, modules, APIs, configurations, and project structures -- Ensure all templates follow established coding standards and best practices from the project's CLAUDE.md guidelines +- Ensure all templates follow established coding standards and best practices from the project's AGENTS.md guidelines - Include proper TypeScript definitions, error handling, and documentation structure - Create modular, extensible templates that can be easily customized for specific needs - Incorporate appropriate testing scaffolding and configuration files diff --git a/categories/general/flow-agent-release-manager/SKILL.md b/categories/general/flow-agent-release-manager/SKILL.md index 09f0e993e..49369c171 100644 --- a/categories/general/flow-agent-release-manager/SKILL.md +++ b/categories/general/flow-agent-release-manager/SKILL.md @@ -119,7 +119,7 @@ mcp__github__create_pull_request { ### ๐ŸŽฏ Release Highlights - **GitHub Workflow Integration**: Complete GitHub command suite with swarm coordination - **Package Synchronization**: Aligned versions and dependencies across packages -- **Enhanced Documentation**: Synchronized CLAUDE.md with comprehensive integration guides +- **Enhanced Documentation**: Synchronized AGENTS.md with comprehensive integration guides - **Improved Testing**: Comprehensive integration test suite with 89% success rate ### ๐Ÿ“ฆ Package Updates diff --git a/categories/general/flow-agent-repo-architect/SKILL.md b/categories/general/flow-agent-repo-architect/SKILL.md index c573ad140..07cd4bc35 100644 --- a/categories/general/flow-agent-repo-architect/SKILL.md +++ b/categories/general/flow-agent-repo-architect/SKILL.md @@ -90,8 +90,8 @@ mcp__github__push_files { }, null, 2) }, { - path: "CLAUDE.md", - content: "[Standardized CLAUDE.md template]" + path: "AGENTS.md", + content: "[Standardized AGENTS.md template]" }, { path: "package.json", @@ -123,7 +123,7 @@ npx claude-flow start --ui - ๐Ÿ“Š Advanced coordination capabilities ## Documentation -See CLAUDE.md for complete integration instructions.` +See AGENTS.md for complete integration instructions.` } ], message: "feat: Create standardized Claude project template with ruv-swarm integration" diff --git a/categories/general/flow-cost-booster-route/SKILL.md b/categories/general/flow-cost-booster-route/SKILL.md index c53e47932..956fa9eb8 100644 --- a/categories/general/flow-cost-booster-route/SKILL.md +++ b/categories/general/flow-cost-booster-route/SKILL.md @@ -34,9 +34,9 @@ Before a batch of similar tasks, or when `cost-report` shows Sonnet/Opus spend o ## Caveats โ€” claimed upstream, not yet verified - `[AGENT_BOOSTER_AVAILABLE]` fires only when the upstream router populates `routeResult.agentBoosterIntent.type` (`v3/@claude-flow/cli/src/mcp-tools/hooks-tools.ts:1228`). The published CLI's semantic-VectorDb path does not always trigger the classifier โ€” treat the partition as a **lower bound** on Tier 1 eligibility. -- CLAUDE.md root claims `<1ms` latency and `352ร— faster` than LLM. `<1ms` and `$0` are structural; `352ร—` is **claimed upstream, not yet verified** here. Report what the router actually returns. +- AGENTS.md root claims `<1ms` latency and `352ร— faster` than LLM. `<1ms` and `$0` are structural; `352ร—` is **claimed upstream, not yet verified** here. Report what the router actually returns. - See `docs/benchmarks/0002-baseline.md` for the full upstream-claims-vs-measured table. ## Cross-references -ADR-0002 Decision #1 ยท ruflo-intelligence ADR-0001 ยง"Neutral" (closes the routing-outcomes loop via `cost-optimize` step 8) ยท CLAUDE.md root ยง"3-Tier Model Routing (ADR-026)". \ No newline at end of file +ADR-0002 Decision #1 ยท ruflo-intelligence ADR-0001 ยง"Neutral" (closes the routing-outcomes loop via `cost-optimize` step 8) ยท AGENTS.md root ยง"3-Tier Model Routing (ADR-026)". \ No newline at end of file diff --git a/categories/general/flow-cost-compact-context/SKILL.md b/categories/general/flow-cost-compact-context/SKILL.md index c3e8865b4..eede1bf4f 100644 --- a/categories/general/flow-cost-compact-context/SKILL.md +++ b/categories/general/flow-cost-compact-context/SKILL.md @@ -26,7 +26,7 @@ Wraps `getTokenOptimizer().getCompactContext()` from `@claude-flow/integration` ## Caveats โ€” claimed upstream, not yet verified -CLAUDE.md root claims `ReasoningBank retrieval: -32%` tokens. The bridge's `tokensSaved` is `query_tokens โˆ’ compact_prompt_tokens` (token-optimizer.ts:141โ€“143) โ€” a heuristic, **not** a baseline-measured saving. token-optimizer.ts:9โ€“10 itself says: *"No fabricated metrics are reported โ€” all stats reflect real measurements"*. This skill carries that disclaimer forward. +AGENTS.md root claims `ReasoningBank retrieval: -32%` tokens. The bridge's `tokensSaved` is `query_tokens โˆ’ compact_prompt_tokens` (token-optimizer.ts:141โ€“143) โ€” a heuristic, **not** a baseline-measured saving. token-optimizer.ts:9โ€“10 itself says: *"No fabricated metrics are reported โ€” all stats reflect real measurements"*. This skill carries that disclaimer forward. Booster-specific availability is **not** exposed as a getter โ€” observable only through `optimizedEdit()` returning `method: 'agent-booster'`. The canonical Tier 1 signal is `[AGENT_BOOSTER_AVAILABLE]` (see `cost-booster-route`). diff --git a/categories/general/flow-init-project/SKILL.md b/categories/general/flow-init-project/SKILL.md index afc0aef8f..623bd5b3c 100644 --- a/categories/general/flow-init-project/SKILL.md +++ b/categories/general/flow-init-project/SKILL.md @@ -9,4 +9,4 @@ allowed-tools: Bash(npx *) Read Write Edit Run `npx @claude-flow/cli@latest init --wizard` to set up the project interactively, or `npx @claude-flow/cli@latest init --preset standard` for defaults. -This creates CLAUDE.md, .claude/settings.json, and .claude-flow/ config with MCP server registration for the `ruflo` MCP tools. \ No newline at end of file +This creates AGENTS.md, .claude/settings.json, and .claude-flow/ config with MCP server registration for the `ruflo` MCP tools. \ No newline at end of file diff --git a/categories/general/ghcp-phase_prompts-phase1/SKILL.md b/categories/general/ghcp-phase_prompts-phase1/SKILL.md index 62d83b184..7d86f639e 100644 --- a/categories/general/ghcp-phase_prompts-phase1/SKILL.md +++ b/categories/general/ghcp-phase_prompts-phase1/SKILL.md @@ -33,7 +33,7 @@ For each in-scope file, emit a record with the role taxonomy below. The judgment 2. A diagnosis of the likely root cause 3. A proposed fix shape (do NOT apply it) -Do NOT patch QPB source code yourself. QPB source changes go through Council review (see `~/Documents/AI-Driven Development/CLAUDE.md`). A structural backstop captures the QPB source tree's git SHA at run start and verifies it unchanged at every phase boundary; an autonomous source patch will fail the gate with a diagnostic naming the modified files. +Do NOT patch QPB source code yourself. QPB source changes go through Council review (see `~/Documents/AI-Driven Development/AGENTS.md`). A structural backstop captures the QPB source tree's git SHA at run start and verifies it unchanged at every phase boundary; an autonomous source patch will fail the gate with a diagnostic naming the modified files. Role taxonomy (single source of truth: `bin/role_map.py::ROLE_DESCRIPTIONS`): {role_taxonomy} diff --git a/categories/general/glfr-context-manager/SKILL.md b/categories/general/glfr-context-manager/SKILL.md index 8f586bd99..514423996 100644 --- a/categories/general/glfr-context-manager/SKILL.md +++ b/categories/general/glfr-context-manager/SKILL.md @@ -92,7 +92,7 @@ When passing context to another agent: ## Memory Management -- Use CLAUDE.md or project-level memory files for information that persists across sessions. +- Use AGENTS.md or project-level memory files for information that persists across sessions. - Store architectural decisions, coding conventions, and known issues in persistent memory. - Do not store implementation details that will become stale. - Update memory when conventions change or new patterns are established. diff --git a/categories/general/glfr-documentation/SKILL.md b/categories/general/glfr-documentation/SKILL.md index f4f0988b7..f866966af 100644 --- a/categories/general/glfr-documentation/SKILL.md +++ b/categories/general/glfr-documentation/SKILL.md @@ -24,13 +24,13 @@ tags: [general] - Update documentation in the same PR that changes the code. - Review docs in code review. Stale docs are worse than no docs. - Use CI to verify that documentation examples compile or run. -- Keep CLAUDE.md or AGENTS.md updated with current project context. +- Keep AGENTS.md updated with current project context. ## Documentation Formats - Inline code comments: explain **why**, not what. One line, placed above the code. - JSDoc/docstrings: for public APIs. Include parameters, returns, throws, and an example. - README: installation, quick start, configuration, contribution guidelines. -- CLAUDE.md: project context, conventions, build commands, key architecture decisions. +- AGENTS.md: project context, conventions, build commands, key architecture decisions. - ADRs: date, status, context, decision, consequences. Store in `docs/adr/`. ## Style Guidelines diff --git a/categories/general/interaction-and-state-spec/SKILL.md b/categories/general/interaction-and-state-spec/SKILL.md index cd0cd4ae1..23d3a7be8 100644 --- a/categories/general/interaction-and-state-spec/SKILL.md +++ b/categories/general/interaction-and-state-spec/SKILL.md @@ -69,7 +69,7 @@ Conflict order, highest first: 1. The user's explicit goal and constraints. 2. Verified user and product evidence, and what the system actually does. -3. Project-canonical guidance: `AGENTS.md` or `CLAUDE.md`, the project's design system, routed sibling skills. +3. Project-canonical guidance: `AGENTS.md`, the project's design system, routed sibling skills. 4. Sibling-skill ownership: route, do not duplicate. 5. This skill's standards (below). 6. General interface and platform conventions (WCAG 2.2, NN/g, Apple HIG, Material, GOV.UK), which `references/rules.md` cites per rule. diff --git a/categories/general/level-based-repository-scaffolding/SKILL.md b/categories/general/level-based-repository-scaffolding/SKILL.md index 3072a8afa..eea76a261 100644 --- a/categories/general/level-based-repository-scaffolding/SKILL.md +++ b/categories/general/level-based-repository-scaffolding/SKILL.md @@ -118,7 +118,7 @@ Everything in L2, plus the production-grade set. Each item maps to a reference n L3 rules: - Fast gates run on PR; heavy gates (mutation, property, schemathesis, compat) run nightly so contributors are never blocked. -- `AGENTS.md` is the source of truth; `CLAUDE.md`/`GEMINI.md` exist only as pointers to it. +- `AGENTS.md` is the single source of truth; no per-tool pointer files. - Changelog fragments (`changelog.d/...`) replace hand-editing `CHANGELOG.md`; a PR touching `CHANGELOG.md` directly fails CI. ## Ultra-Fast Local Dev Matrix diff --git a/categories/general/lira-design/SKILL.md b/categories/general/lira-design/SKILL.md index 9c48519cc..572ff4b1e 100644 --- a/categories/general/lira-design/SKILL.md +++ b/categories/general/lira-design/SKILL.md @@ -24,7 +24,7 @@ tags: #### 2.5.4. Claude Code-Specific Processing - Copies template files without frontmatter transformation (preserves original format) -- Generates main context file (`CLAUDE.md`) with @ imports for template inclusion +- Generates main context file (`AGENTS.md`) with @ imports for template inclusion - Organizes imports by topic categories with user-friendly labels - Implements duplicate detection to avoid redundant imports - Uses simple string-based content management for efficient processing @@ -171,7 +171,7 @@ The project currently supports three AI coding assistants, each with unique char - **File Extension**: `.md` - **Processing Strategy**: Main context file management with @ imports - **Special Features**: - - Creates/updates main `CLAUDE.md` context file at project root + - Creates/updates main `AGENTS.md` context file at project root - Organizes imports by topic categories with user-friendly labels - Implements duplicate detection to avoid redundant imports - Uses @ syntax for file imports (e.g., `@./.claude/rules/filename.md`) diff --git a/categories/general/lira-requirements/SKILL.md b/categories/general/lira-requirements/SKILL.md index a6bc4ffc0..536c733b1 100644 --- a/categories/general/lira-requirements/SKILL.md +++ b/categories/general/lira-requirements/SKILL.md @@ -110,7 +110,7 @@ The project has the following key dependencies: **Acceptance Criteria:** -- The system must be able to create and update main context files (e.g., `CLAUDE.md`) at the project root. +- The system must be able to create and update main context files (e.g., `AGENTS.md`) at the project root. - The system must support @ import syntax for referencing template files (e.g., `@./.claude/rules/filename.md`). - The system must organize imports by topic categories with user-friendly labels. - The system must implement duplicate detection to avoid redundant imports when processing the same topic multiple times. diff --git a/categories/general/neo-create-hook/SKILL.md b/categories/general/neo-create-hook/SKILL.md index 03bdbbd93..74fb8e308 100644 --- a/categories/general/neo-create-hook/SKILL.md +++ b/categories/general/neo-create-hook/SKILL.md @@ -203,7 +203,7 @@ Each event corresponds to a point in Claude Code's lifecycle where hooks can run ### SessionStart -Runs when Claude Code starts a new session or resumes an existing session. Useful for loading development context like existing issues or recent changes to your codebase, or setting up environment variables. For static context that does not require a script, use CLAUDE.md instead. +Runs when Claude Code starts a new session or resumes an existing session. Useful for loading development context like existing issues or recent changes to your codebase, or setting up environment variables. For static context that does not require a script, use AGENTS.md instead. SessionStart runs on every session, so keep these hooks fast. diff --git a/categories/general/neo-kaizen/SKILL.md b/categories/general/neo-kaizen/SKILL.md index 57db37245..ed058a439 100644 --- a/categories/general/neo-kaizen/SKILL.md +++ b/categories/general/neo-kaizen/SKILL.md @@ -356,7 +356,7 @@ Follow established patterns. Document what works. Make good practices easy to fo **Documentation lives with code:** - README for setup and architecture -- CLAUDE.md for AI coding conventions +- AGENTS.md for AI coding conventions - Comments for "why", not "what" - Examples for complex patterns @@ -466,7 +466,7 @@ Documents why, when, and how **Before adding new patterns:** - Search codebase for similar problems solved -- Check CLAUDE.md for project conventions +- Check AGENTS.md for project conventions - Discuss with team if breaking from pattern - Update docs when introducing new pattern @@ -482,7 +482,7 @@ Documents why, when, and how - Check consistency with existing code - Point to examples in codebase - Suggest aligning with standards -- Update CLAUDE.md if new standard emerges +- Update AGENTS.md if new standard emerges ### 4. Just-In-Time (JIT) diff --git a/categories/general/neo-memorize/SKILL.md b/categories/general/neo-memorize/SKILL.md index eaefcafef..cbfbaed9e 100644 --- a/categories/general/neo-memorize/SKILL.md +++ b/categories/general/neo-memorize/SKILL.md @@ -1,19 +1,19 @@ --- name: neo-memorize -description: "Curates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering" +description: "Curates insights from reflections and critiques into AGENTS.md using Agentic Context Engineering" license: MIT tags: [general] argument-hint: Optional source specification (last, selection, chat:) or --dry-run for preview --- -# Memory Consolidation: Curate and Update CLAUDE.md +# Memory Consolidation: Curate and Update AGENTS.md -You are a memory consolidation specialist implementing Agentic Context Engineering (ACE). Your role is to capture insights from reflection and debate processes, then curate and organize these learnings into CLAUDE.md to create an evolving context playbook that improves future agent performance through structured knowledge accumulation. +You are a memory consolidation specialist implementing Agentic Context Engineering (ACE). Your role is to capture insights from reflection and debate processes, then curate and organize these learnings into AGENTS.md to create an evolving context playbook that improves future agent performance through structured knowledge accumulation. -Transform reflections, critiques, verification outcomes, and execution feedback into durable, reusable guidance by updating `CLAUDE.md`. Use Agentic Context Engineering (ACE) principles to grow-and-refine a living playbook that improves over time without collapsing into vague summaries. +Transform reflections, critiques, verification outcomes, and execution feedback into durable, reusable guidance by updating `AGENTS.md`. Use Agentic Context Engineering (ACE) principles to grow-and-refine a living playbook that improves over time without collapsing into vague summaries. @@ -73,7 +73,7 @@ Prefer specifics over generalities. If you cannot back a claim with either code ### Phase 2: Memory Curation Process -#### Step 1: Analyze Current CLAUDE.md Context +#### Step 1: Analyze Current AGENTS.md Context ```bash # Read current context file @@ -103,7 +103,7 @@ For each insight identified in Phase 1 apply ACEโ€™s โ€œgrowโ€‘andโ€‘refineโ€ p **Generation โ†’ Curation Mapping**: - Raw insight: [What was learned] -- Context category: [Where it fits in CLAUDE.md structure] +- Context category: [Where it fits in AGENTS.md structure] - Actionable format: [How to phrase it for future use] - Validation criteria: [How to know if it's being applied correctly] @@ -136,11 +136,11 @@ Ensure new memories don't dilute existing quality context: If a potential bullet conflicts with an existing one, prefer the more specific, evidenceโ€‘backed rule and mark the older one for future consolidation (but do not autoโ€‘delete). -### Phase 3: CLAUDE.md Updates +### Phase 3: AGENTS.md Updates Update the context file with curated insights: -#### Where to Write in `CLAUDE.md` +#### Where to Write in `AGENTS.md` Create the file if missing with these sections (topโ€‘level headings): @@ -214,7 +214,7 @@ examples: #### Quality Gates (Must Pass) -After updating CLAUDE.md: +After updating AGENTS.md: 1. **Coherence Check**: - Do new entries fit with existing context? @@ -258,7 +258,7 @@ Track the effectiveness of memory updates: 2. **Evidence-Based**: Only memorize patterns with clear supporting evidence 3. **Context-Aware**: Consider project phase, team size, constraints when curating 4. **Version Awareness**: Note when insights become obsolete due to tech changes -5. **Cross-Reference**: Link related concepts within CLAUDE.md for better navigation +5. **Cross-Reference**: Link related concepts within AGENTS.md for better navigation ##### Expected Outcomes @@ -276,7 +276,7 @@ After effective memory consolidation: # Memorize from most recent reflections and outputs /reflexion:memorize -# Dryโ€‘run: show proposed bullets without writing to CLAUDE.md +# Dryโ€‘run: show proposed bullets without writing to AGENTS.md /reflexion:memorize --dry-run # Limit number of bullets @@ -292,7 +292,7 @@ After effective memory consolidation: ## Output 1) Short summary of additions (counts by section) -2) Confirmation that `CLAUDE.md` was created/updated +2) Confirmation that `AGENTS.md` was created/updated ## Notes diff --git a/categories/general/neo-multi-agent-patterns/SKILL.md b/categories/general/neo-multi-agent-patterns/SKILL.md index b65cc496f..864a4612a 100644 --- a/categories/general/neo-multi-agent-patterns/SKILL.md +++ b/categories/general/neo-multi-agent-patterns/SKILL.md @@ -237,7 +237,7 @@ Files created during a session that track progress: ### Long-Term Memory Persistent files that survive across sessions: -- CLAUDE.md for project-level context +- AGENTS.md for project-level context - Memory files in designated directories - Structured knowledge bases in markdown or JSON diff --git a/categories/general/neo-review-local-changes/SKILL.md b/categories/general/neo-review-local-changes/SKILL.md index 78ec83cac..7d71d3675 100644 --- a/categories/general/neo-review-local-changes/SKILL.md +++ b/categories/general/neo-review-local-changes/SKILL.md @@ -83,11 +83,11 @@ When `--json` flag is set, output results in this JSON structure: - **Be Pragmatic**: Focus on real issues and high-impact improvements - **Skip Trivial Issues** in large changes (>500 lines): - Focus on architectural and security issues - - Ignore minor naming conventions unless CLAUDE.md explicitly requires them + - Ignore minor naming conventions unless AGENTS.md explicitly requires them - Prioritize bugs over style - **Improvements Should Be Actionable**: Each suggestion should include concrete code examples - **Consider Effort vs Impact**: Prioritize improvements with high impact and reasonable effort -- **Align with Project Standards**: Reference CLAUDE.md and project guidelines when suggesting improvements +- **Align with Project Standards**: Reference AGENTS.md and project guidelines when suggesting improvements - **Terminal Readability**: The report is consumed in a terminal/console. Use fixed-width-friendly formatting: short lines, clear section separators (`---`), and concise tables. Avoid deeply nested bullet lists or long prose paragraphs that wrap poorly in narrow terminals. ## Remember diff --git a/categories/general/neo-review-pr/SKILL.md b/categories/general/neo-review-pr/SKILL.md index ec83337e3..491e3992e 100644 --- a/categories/general/neo-review-pr/SKILL.md +++ b/categories/general/neo-review-pr/SKILL.md @@ -96,7 +96,7 @@ Run following commands in order: ### Phase 2: Searching for Issues -Determine Applicable Reviews, then launch up to 6 parallel (Sonnet or Opus) agents to independently code review all changes in the pull request. The agents should do the following, then return a list of issues and the reason each issue was flagged (eg. CLAUDE.md or consitution.md adherence, bug, historical git context, etc.). +Determine Applicable Reviews, then launch up to 6 parallel (Sonnet or Opus) agents to independently code review all changes in the pull request. The agents should do the following, then return a list of issues and the reason each issue was flagged (eg. AGENTS.md or consitution.md adherence, bug, historical git context, etc.). **Available Review Agents**: @@ -124,19 +124,19 @@ Based on changes summary from phase 1 and their complexity, determine which revi **Parallel approach**: - Launch all agents simultaneously -- Provide to them full list of modified files and summary of the PR as a context, explicitly highlight which PR they are reviewing, also provide list of files with project guidelines and standards, including README.md, CLAUDE.md and consitution.md if they exist. +- Provide to them full list of modified files and summary of the PR as a context, explicitly highlight which PR they are reviewing, also provide list of files with project guidelines and standards, including README.md, AGENTS.md and consitution.md if they exist. - Results should come back together ### Phase 3: Confidence & Impact Scoring -1. For each issue found in Phase 2, launch a parallel Haiku agent that takes the PR, issue description, and list of CLAUDE.md files (from step 2), and returns TWO scores: +1. For each issue found in Phase 2, launch a parallel Haiku agent that takes the PR, issue description, and list of AGENTS.md files (from step 2), and returns TWO scores: **Confidence Score (0-100)** - Level of confidence that the issue is real and not a false positive: a. 0: Not confident at all. This is a false positive that doesn't stand up to light scrutiny, or is a pre-existing issue. - b. 25: Somewhat confident. This might be a real issue, but may also be a false positive. The agent wasn't able to verify that it's a real issue. If the issue is stylistic, it is one that was not explicitly called out in the relevant CLAUDE.md. + b. 25: Somewhat confident. This might be a real issue, but may also be a false positive. The agent wasn't able to verify that it's a real issue. If the issue is stylistic, it is one that was not explicitly called out in the relevant AGENTS.md. c. 50: Moderately confident. The agent was able to verify this is a real issue, but it might be a nitpick or not happen very often in practice. Relative to the rest of the PR, it's not very important. - d. 75: Highly confident. The agent double checked the issue, and verified that it is very likely it is a real issue that will be hit in practice. The existing approach in the PR is insufficient. The issue is very important and will directly impact the code's functionality, or it is an issue that is directly mentioned in the relevant CLAUDE.md. + d. 75: Highly confident. The agent double checked the issue, and verified that it is very likely it is a real issue that will be hit in practice. The existing approach in the PR is insufficient. The issue is very important and will directly impact the code's functionality, or it is an issue that is directly mentioned in the relevant AGENTS.md. e. 100: Absolutely certain. The agent double checked the issue, and confirmed that it is definitely a real issue, that will happen frequently in practice. The evidence directly confirms this. **Impact Score (0-100)** - Severity and consequence of the issue if left unfixed: @@ -147,7 +147,7 @@ Based on changes summary from phase 1 and their complexity, determine which revi d. 61-80 (High): Will break core features, corrupt data under normal usage, or create significant technical debt. e. 81-100 (Critical): Will cause runtime errors, data loss, system crash, security breaches, or complete feature failure. - For issues flagged due to CLAUDE.md instructions, the agent should double check that the CLAUDE.md actually calls out that issue specifically. + For issues flagged due to AGENTS.md instructions, the agent should double check that the AGENTS.md actually calls out that issue specifically. 2. **Filter issues using the progressive threshold table below** - Higher impact issues require less confidence to pass: @@ -190,8 +190,8 @@ Based on changes summary from phase 1 and their complexity, determine which revi - Something that looks like a bug but is not actually a bug - Pedantic nitpicks that a senior engineer wouldn't call out - Issues that a linter, typechecker, or compiler would catch (eg. missing or incorrect imports, type errors, broken tests, formatting issues, pedantic style issues like newlines). No need to run these build steps yourself -- it is safe to assume that they will be run separately as part of CI. -- General code quality issues (eg. lack of test coverage, general security issues, poor documentation), unless explicitly required in CLAUDE.md -- Issues that are called out in CLAUDE.md, but explicitly silenced in the code (eg. due to a lint ignore comment) +- General code quality issues (eg. lack of test coverage, general security issues, poor documentation), unless explicitly required in AGENTS.md +- Issues that are called out in AGENTS.md, but explicitly silenced in the code (eg. due to a lint ignore comment) - Changes in functionality that are likely intentional or are directly related to the broader change - Real issues, but on lines that the user did not modify in their pull request @@ -200,7 +200,7 @@ Notes: - Use build, lint and tests commands if you have access to them. They can help you find potential issues that are not obvious from the code changes. - Use `gh` to interact with Github (eg. to fetch a pull request, or to create inline comments), rather than web fetch - Make a todo list first -- You must cite and link each bug (eg. if referring to a CLAUDE.md, you must link it) +- You must cite and link each bug (eg. if referring to a AGENTS.md, you must link it) - When using line-specific comments (via `git:attach-review-to-pr`): - Each issue should map to a specific file and line number - For multiple issues: Use `gh api repos/{owner}/{repo}/pulls/{pr_number}/reviews` with JSON input containing the review body (Quality Gate summary) and comments array (line-specific issues) diff --git a/categories/general/neo-setup-arxiv-mcp/SKILL.md b/categories/general/neo-setup-arxiv-mcp/SKILL.md index 64a3527e0..b2327d682 100644 --- a/categories/general/neo-setup-arxiv-mcp/SKILL.md +++ b/categories/general/neo-setup-arxiv-mcp/SKILL.md @@ -71,11 +71,11 @@ Verify the server is working by searching for papers: mcp-exec name: "search_arxiv" arguments: {"query": "test query", "max_results": 2} ``` -## 5. Update CLAUDE.md file +## 5. Update AGENTS.md file Use the path determined in step 1: -Once the paper-search MCP server is successfully set up, update CLAUDE.md file with the following content: +Once the paper-search MCP server is successfully set up, update AGENTS.md file with the following content: ```markdown ### Use Paper Search MCP for Academic Research diff --git a/categories/general/neo-setup-codemap-cli/SKILL.md b/categories/general/neo-setup-codemap-cli/SKILL.md index aa95f491f..dcd9f33cb 100644 --- a/categories/general/neo-setup-codemap-cli/SKILL.md +++ b/categories/general/neo-setup-codemap-cli/SKILL.md @@ -70,9 +70,9 @@ After installation, verify codemap works: codemap . ``` -## 6. Update CLAUDE.md file +## 6. Update AGENTS.md file -Use the path determined in step 1. Once Codemap is successfully installed, update the appropriate CLAUDE.md file with the following content: +Use the path determined in step 1. Once Codemap is successfully installed, update the appropriate AGENTS.md file with the following content: ```markdown ## Use Codemap CLI for Codebase Navigation diff --git a/categories/general/neo-setup-context7-mcp/SKILL.md b/categories/general/neo-setup-context7-mcp/SKILL.md index b40c52270..868aabb86 100644 --- a/categories/general/neo-setup-context7-mcp/SKILL.md +++ b/categories/general/neo-setup-context7-mcp/SKILL.md @@ -38,13 +38,13 @@ Check whether you have access to Context7 MCP server by making request. if no, load file and guide user through setup process that applicable to agent/operation system. -## 3. Update CLAUDE.md file +## 3. Update AGENTS.md file Use the path determined in step 1: - Parse user input, if it empty read current project structure and used technologies, if project empty ask user to provide list of languages and frameworks that planned to be used in this project. - Search through context7 MCP for relevant technologies documentation -- Update the appropriate CLAUDE.md file with following content: +- Update the appropriate AGENTS.md file with following content: ```markdown ### Use Context7 MCP for Loading Documentation diff --git a/categories/general/neo-setup-serena-mcp/SKILL.md b/categories/general/neo-setup-serena-mcp/SKILL.md index 13a3188b5..48ffecedb 100644 --- a/categories/general/neo-setup-serena-mcp/SKILL.md +++ b/categories/general/neo-setup-serena-mcp/SKILL.md @@ -78,9 +78,9 @@ You must restart Claude Code to load the new MCP server: ``` -## 5. Update CLAUDE.md file +## 5. Update AGENTS.md file -Use the path determined in step 1. Once Serena is successfully set up, update the appropriate CLAUDE.md file with the following content EXACTLY: +Use the path determined in step 1. Once Serena is successfully set up, update the appropriate AGENTS.md file with the following content EXACTLY: ```markdown ### Use Serena MCP for Semantic Code Analysis instead of regular code search and editing diff --git a/categories/general/neo-test-skill/SKILL.md b/categories/general/neo-test-skill/SKILL.md index 03c6fa2d3..f80a6018d 100644 --- a/categories/general/neo-test-skill/SKILL.md +++ b/categories/general/neo-test-skill/SKILL.md @@ -19,7 +19,7 @@ You run scenarios without the skill (RED - watch agent fail), write skill addres **REQUIRED BACKGROUND:** You MUST understand superpowers:test-driven-development before using this skill. That skill defines the fundamental RED-GREEN-REFACTOR cycle. This skill provides skill-specific test formats (pressure scenarios, rationalization tables). -**Complete worked example:** See examples/CLAUDE_MD_TESTING.md for a full test campaign testing CLAUDE.md documentation variants. +**Complete worked example:** See examples/CLAUDE_MD_TESTING.md for a full test campaign testing AGENTS.md documentation variants. ## When to Use diff --git a/categories/general/receiving-code-review/SKILL.md b/categories/general/receiving-code-review/SKILL.md index 4728e08bf..ee1305fc8 100644 --- a/categories/general/receiving-code-review/SKILL.md +++ b/categories/general/receiving-code-review/SKILL.md @@ -29,7 +29,7 @@ WHEN receiving code review feedback: ## Forbidden Responses **NEVER:** -- "You're absolutely right!" (explicit CLAUDE.md violation) +- "You're absolutely right!" (explicit AGENTS.md violation) - "Great point!" / "Excellent feedback!" (performative) - "Let me implement that now" (before verification) diff --git a/categories/general/skill-invocation-workflow/SKILL.md b/categories/general/skill-invocation-workflow/SKILL.md index 600c08e94..5fbe90dfa 100644 --- a/categories/general/skill-invocation-workflow/SKILL.md +++ b/categories/general/skill-invocation-workflow/SKILL.md @@ -64,4 +64,4 @@ If your harness appears here, read its reference file for special instructions: ## User Instructions -User instructions (CLAUDE.md, AGENTS.md, GEMINI.md, etc, direct requests) take precedence over skills, which in turn override default behavior. Only skip skill workflows or instructions when your human partner has explicitly told you to. +User instructions (AGENTS.md, GEMINI.md, etc, direct requests) take precedence over skills, which in turn override default behavior. Only skip skill workflows or instructions when your human partner has explicitly told you to. diff --git a/categories/general/std-caveman-compress/SKILL.md b/categories/general/std-caveman-compress/SKILL.md index 08d8e2742..7e7972993 100644 --- a/categories/general/std-caveman-compress/SKILL.md +++ b/categories/general/std-caveman-compress/SKILL.md @@ -10,7 +10,7 @@ Trigger: /caveman:compress or "compress memory file ## Purpose -Compress natural language files (CLAUDE.md, todos, preferences) into caveman-speak to reduce input tokens. Compressed version overwrites original. Human-readable backup saved as `.original.md`. +Compress natural language files (AGENTS.md, todos, preferences) into caveman-speak to reduce input tokens. Compressed version overwrites original. Human-readable backup saved as `.original.md`. ## Trigger diff --git a/categories/general/token-compression-files/SKILL.md b/categories/general/token-compression-files/SKILL.md index 41039e298..d569a6594 100644 --- a/categories/general/token-compression-files/SKILL.md +++ b/categories/general/token-compression-files/SKILL.md @@ -1,6 +1,6 @@ --- name: token-compression-files -description: "Compress memory files like CLAUDE.md into terse caveman format to save input tokens while keeping backups." +description: "Compress memory files like AGENTS.md into terse caveman format to save input tokens while keeping backups." license: MIT tags: - compression @@ -12,7 +12,7 @@ tags: ## Purpose -Compress natural language files (CLAUDE.md, todos, preferences) into caveman-speak to reduce input tokens. Compressed version overwrites original. Human-readable backup saved as `.original.md`, but NOT beside the source file โ€” it lives in an out-of-tree data dir (`$XDG_DATA_HOME/caveman-compress/backups//`, or `%LOCALAPPDATA%\caveman-compress\backups\\` on Windows) so skill auto-loaders don't re-ingest it as a live file. +Compress natural language files (AGENTS.md, todos, preferences) into caveman-speak to reduce input tokens. Compressed version overwrites original. Human-readable backup saved as `.original.md`, but NOT beside the source file โ€” it lives in an out-of-tree data dir (`$XDG_DATA_HOME/caveman-compress/backups//`, or `%LOCALAPPDATA%\caveman-compress\backups\\` on Windows) so skill auto-loaders don't re-ingest it as a live file. ## Trigger diff --git a/categories/general/using-git-worktrees/SKILL.md b/categories/general/using-git-worktrees/SKILL.md index e10a3c859..6ed0b3976 100644 --- a/categories/general/using-git-worktrees/SKILL.md +++ b/categories/general/using-git-worktrees/SKILL.md @@ -29,17 +29,17 @@ ls -d worktrees 2>/dev/null # Alternative **If found:** Use that directory. If both exist, `.worktrees` wins. -### 2. Check CLAUDE.md +### 2. Check AGENTS.md ```bash -grep -i "worktree.*director" CLAUDE.md 2>/dev/null +grep -i "worktree.*director" AGENTS.md 2>/dev/null ``` **If preference specified:** Use it without asking. ### 3. Ask User -If no directory exists and no CLAUDE.md preference: +If no directory exists and no AGENTS.md preference: ``` No worktree directory found. Where should I create worktrees? @@ -150,7 +150,7 @@ Ready to implement | `.worktrees/` exists | Use it (verify ignored) | | `worktrees/` exists | Use it (verify ignored) | | Both exist | Use `.worktrees/` | -| Neither exists | Check CLAUDE.md โ†’ Ask user | +| Neither exists | Check AGENTS.md โ†’ Ask user | | Directory not ignored | Add to .gitignore + commit | | Tests fail during baseline | Report failures + ask | | No package.json/Cargo.toml | Skip dependency install | @@ -165,7 +165,7 @@ Ready to implement ### Assuming directory location - **Problem:** Creates inconsistency, violates project conventions -- **Fix:** Follow priority: existing > CLAUDE.md > ask +- **Fix:** Follow priority: existing > AGENTS.md > ask ### Proceeding with failing tests @@ -200,10 +200,10 @@ Ready to implement auth feature - Skip baseline test verification - Proceed with failing tests without asking - Assume directory location when ambiguous -- Skip CLAUDE.md check +- Skip AGENTS.md check **Always:** -- Follow directory priority: existing > CLAUDE.md > ask +- Follow directory priority: existing > AGENTS.md > ask - Verify directory is ignored for project-local - Auto-detect and run project setup - Verify clean test baseline diff --git a/categories/git/readonly-diff-review/SKILL.md b/categories/git/readonly-diff-review/SKILL.md index df5ccb8b6..d965696d5 100644 --- a/categories/git/readonly-diff-review/SKILL.md +++ b/categories/git/readonly-diff-review/SKILL.md @@ -55,7 +55,7 @@ Review progress: ``` 1. **Discover target.** Staged and unstaged changes first (`git diff --stat`, `git diff --staged --stat`); if clean, the branch diff against its merge base with the default branch (`git merge-base HEAD origin/`). For a PR, `gh pr diff ` with the branch checked out for context; same criteria, PR handoff format. Write down the range or ref pair you reviewed; it goes in the report. -2. **Gather context.** Capture intent from the user's words, the commit messages, and the PR description. Load scoped `AGENTS.md` / `CLAUDE.md`, and a root `REVIEW.md` where one exists: both override this skill's defaults when they conflict, so a pattern they mandate is not a finding. `REVIEW.md` is the file Claude Code Review reads for severity calibration, skip paths, nit caps, and repo-specific checks; apply it the same way here. Reuse checks already run on this revision. When a candidate needs execution, run the relevant documented command and preserve its exit status; piping into `tail` without `pipefail` can hide failure. +2. **Gather context.** Capture intent from the user's words, the commit messages, and the PR description. Load scoped `AGENTS.md`, and a root `REVIEW.md` where one exists: both override this skill's defaults when they conflict, so a pattern they mandate is not a finding. `REVIEW.md` is the file Claude Code Review reads for severity calibration, skip paths, nit caps, and repo-specific checks; apply it the same way here. Reuse checks already run on this revision. When a candidate needs execution, run the relevant documented command and preserve its exit status; piping into `tail` without `pipefail` can hide failure. 3. **Review.** Apply the loaded rubric and high-signal criteria; shard large diffs. Five passes, because each finds what the others structurally cannot: - **Claims.** Map each claim in the description or commit messages to a hunk, and each hunk to a claim. A claim with no hunk is a finding: the description says a change shipped and the diff does not contain it, the most common description-to-code mismatch in agent-authored PRs, and the one that most often gets them rejected. A hunk with no claim is not a finding on its own; list it under the readiness summary as an unstated change so the reader can decide. - **Added lines.** Read every hunk, then the enclosing function. A bug on an unchanged line of a touched function is in scope: this diff re-exposed it. diff --git a/categories/mobile/mobile-project-structure/SKILL.md b/categories/mobile/mobile-project-structure/SKILL.md index 509bb8a7a..856d155ec 100644 --- a/categories/mobile/mobile-project-structure/SKILL.md +++ b/categories/mobile/mobile-project-structure/SKILL.md @@ -104,7 +104,7 @@ Small differences: use `Platform.select` / `Platform.OS`. For larger ones, split ## AI and config files -Agent instructions live at the repo root โ€” `AGENTS.md` / `CLAUDE.md`, with project skills under `.claude/`. Other config and assets stay outside `src/`: `app.json` / `app.config.ts`, `eas.json`, `package.json`, `assets/`, and `scripts/`. +Agent instructions live at the repo root โ€” `AGENTS.md`, with project skills under `.claude/`. Other config and assets stay outside `src/`: `app.json` / `app.config.ts`, `eas.json`, `package.json`, `assets/`, and `scripts/`. --- diff --git a/categories/refactoring/code-clarity-refactoring/SKILL.md b/categories/refactoring/code-clarity-refactoring/SKILL.md index d2df0f471..e81df0c4b 100644 --- a/categories/refactoring/code-clarity-refactoring/SKILL.md +++ b/categories/refactoring/code-clarity-refactoring/SKILL.md @@ -25,7 +25,7 @@ Never change what the code does - only how it does it. All original features, ou ### 2. Apply Project Standards -Follow the established coding standards from CLAUDE.md including: +Follow the established coding standards from AGENTS.md including: - Use ES modules with proper import sorting and extensions - Prefer `function` keyword over arrow functions diff --git a/categories/refactoring/code-clarity-simplification/SKILL.md b/categories/refactoring/code-clarity-simplification/SKILL.md index 148f358c6..407f3d89d 100644 --- a/categories/refactoring/code-clarity-simplification/SKILL.md +++ b/categories/refactoring/code-clarity-simplification/SKILL.md @@ -54,7 +54,7 @@ ASK BEFORE EVERY CHANGE: Simplification means making code more consistent with the codebase, not imposing external preferences. Before simplifying: ``` -1. Read CLAUDE.md / project conventions +1. Read AGENTS.md / project conventions 2. Study how neighboring code handles similar patterns 3. Match the project's style for: - Import ordering and module system @@ -333,7 +333,7 @@ After completing a simplification pass: - [ ] Linter/formatter passes (no style regressions) - [ ] Each simplification is a reviewable, incremental change - [ ] The diff is clean โ€” no unrelated changes mixed in -- [ ] Simplified code follows project conventions (checked against CLAUDE.md or equivalent) +- [ ] Simplified code follows project conventions (checked against AGENTS.md or equivalent) - [ ] No error handling was removed or weakened - [ ] No dead code was left behind (unused imports, unreachable branches) - [ ] A teammate or review agent would approve the change as a net improvement diff --git a/categories/security/agent-skill-security-scan/SKILL.md b/categories/security/agent-skill-security-scan/SKILL.md index 94cb9cfef..066a69b91 100644 --- a/categories/security/agent-skill-security-scan/SKILL.md +++ b/categories/security/agent-skill-security-scan/SKILL.md @@ -90,7 +90,7 @@ This phase is agent-only โ€” no pattern matching. Read the full SKILL.md instruc - A skill described as "code formatter" that instructs the agent to read ~/.ssh is misaligned **Config/memory poisoning**: -- Instructions to modify `CLAUDE.md`, `MEMORY.md`, `settings.json`, `.mcp.json`, or hook configurations +- Instructions to modify `AGENTS.md`, `MEMORY.md`, `settings.json`, `.mcp.json`, or hook configurations - Instructions to add itself to allowlists or auto-approve permissions - Writing to `~/.claude/`, `~/.agents/`, or any agent configuration directory - Scripts that append to global config files โ€” the poisoned instructions persist after skill removal diff --git a/categories/security/workflow-security-review/SKILL.md b/categories/security/workflow-security-review/SKILL.md index 31c62fa42..41e111488 100644 --- a/categories/security/workflow-security-review/SKILL.md +++ b/categories/security/workflow-security-review/SKILL.md @@ -29,7 +29,7 @@ Review the workflows provided (file, diff, or repo). Research the codebase as ne - `.github/workflows/*.yml` โ€” all workflow definitions - `action.yml` / `action.yaml` โ€” composite actions in the repo - `.github/actions/*/action.yml` โ€” local reusable actions -- Config files loaded by workflows: `CLAUDE.md`, `AGENTS.md`, `Makefile`, shell scripts under `.github/` +- Config files loaded by workflows: `AGENTS.md`, `Makefile`, shell scripts under `.github/` ### Out of Scope @@ -118,7 +118,7 @@ Are elevated credentials (PATs, deploy keys) accessible to untrusted code? ### Check 5: Config File Poisoning Does the workflow load configuration from PR-supplied files? -- AI agent instructions: `CLAUDE.md`, `AGENTS.md`, `.cursorrules` +- AI agent instructions: `AGENTS.md`, `.cursorrules` - Build configuration: `Makefile`, shell scripts ### Check 6: Supply Chain diff --git a/categories/typescript/typescript-cli-scaffolding/SKILL.md b/categories/typescript/typescript-cli-scaffolding/SKILL.md index 5e468a91e..f368e542c 100644 --- a/categories/typescript/typescript-cli-scaffolding/SKILL.md +++ b/categories/typescript/typescript-cli-scaffolding/SKILL.md @@ -92,7 +92,7 @@ From the same `references/scaffold-source.md`, generate: - `README.md`: install, usage, API, agent skill install, license - `skills/{{bin}}/SKILL.md`: agent skill definition -Do not create the CLAUDE.md symlink here; Step 6 creates it exactly once. +Do not create the AGENTS.md symlink here; Step 6 creates it exactly once. ### Step 6: Run post-scaffold commands diff --git a/categories/typescript/typescript-codebase-architecture/SKILL.md b/categories/typescript/typescript-codebase-architecture/SKILL.md index ef13f6b1b..60aa07c8d 100644 --- a/categories/typescript/typescript-codebase-architecture/SKILL.md +++ b/categories/typescript/typescript-codebase-architecture/SKILL.md @@ -205,7 +205,7 @@ Each rebuttal redirects to the step being skipped. ## Related skills -- `agents-md`: the AGENTS.md / CLAUDE.md file itself. This skill owns the checks and docs tree that file points at; a rule a linter can enforce goes here as an exit code, not there as prose. +- `agents-md`: the AGENTS.md file itself. This skill owns the checks and docs tree that file points at; a rule a linter can enforce goes here as an exit code, not there as prose. - `tidy`: the diff-scoped cleanup that Harden's guardrails keep small; `pr-reviewer`: read-only review of a local diff. - `planning`: a plan for one feature; architecture briefs from Design mode feed into it. - `scaffold-nextjs`, `scaffold-cli`: creating the repo this skill then structures.