feat(skill): run the pipeline as `graphify pipeline` subcommands, no inline Python (#197) by nothariharan · Pull Request #4275 · Graphify-Labs/graphify

nothariharan · 2026-10-10T06:01:35Z

What this fixes

Closes the remaining work in #197.

The Graphify agent skill delivered every pipeline step — and, on demand, every reference flow — as inline Python inside a bash string:

$(cat graphify-out/.graphify_python) -c "
import json
from graphify.detect import detect
# ... 10-20 lines of Python, with # comments
"

In Claude Code that trips two content-based approval heuristics once per step:

command_substitution — from $(cat graphify-out/.graphify_python).
"Newline followed by # inside a quoted argument" — from the multi-line Python comments.

Neither can be satisfied by permission allow-rules, so a single run cost roughly 30 manual "Yes" clicks and the skill was close to unusable without hand-patching it.

How it's fixed

Every step is now a plain console command. The step bodies live in a new graphify/pipeline.py and are exposed as graphify pipeline <step>:

Old inline block	New command
`detect(...)` + write sidecar	`graphify pipeline detect <path>`
`collect_files` + `extract`	`graphify pipeline extract-ast <path>`
empty `.graphify_semantic.json`	`graphify pipeline empty-semantic`
`check_semantic_cache(...)`	`graphify pipeline cache-check <path> --prompt-file SPEC`
chunk merge	`graphify pipeline merge-chunks`
`save_semantic_cache(...)`	`graphify pipeline save-cache <path> --prompt-file SPEC`
cached+new merge	`graphify pipeline merge-semantic`
AST+semantic merge	`graphify pipeline merge-extraction`
build/cluster/analyze/report	`graphify pipeline build <path> [--directed]`
health check	`graphify pipeline diagnose <path>`
curated labels	`graphify pipeline label <path> --labels '<json>'`
manifest + cost	`graphify pipeline save-manifest <path>`
cleanup	`graphify pipeline cleanup`

The on-demand reference flows are converted the same way, with seven more steps plus existing commands:

query → graphify pipeline vocab, graphify query, graphify path, graphify explain, graphify save-result
update → graphify pipeline detect-incremental | code-only-check | empty-extract | update-merge | graph-diff
add / watch → graphify add, graphify watch (now parses --debounce and defaults to the .graphify_root marker)
transcribe → graphify pipeline transcribe
exports (MCP) → the graphify-mcp console script instead of -m graphify.serve

Because every step is a console-script call, Bash(graphify *) becomes an allowlistable prefix, the cat-to-interpreter indirection disappears, and the security surface shrinks: arguments go through argparse instead of being interpolated into a Python string.

The skill is generated — the fragment is the source of truth

graphify/skill*.md and graphify/skills/*/references/*.md are rendered from tools/skillgen/fragments/ by python -m tools.skillgen. The edits are in the fragments (core/core.md, references/**, query-stub/default.md); the ~200 generated artifacts and the expected/ snapshots are regenerated and blessed (python -m tools.skillgen --bless).

Verification

Byte-identical output. The old inline-Python blocks and the new subcommands were run side by side on a real corpus: .graphify_detect.json, .graphify_ast.json, .graphify_semantic.json, .graphify_extract.json, .graphify_analysis.json, graph.json, manifest.json, and GRAPH_REPORT.md are all identical (report modulo its timestamp). Same graph, different delivery.
No new test failures. Merged against the current v8; the full suite is 4 failures, all pre-existing on v8 (3 in test_hooks.py, 1 in test_unmapped_at_alias_resolution.py) — none introduced by this change. ~4,200 targeted skill/pipeline tests pass.
New tests. tests/test_pipeline_cli.py (pipeline steps end to end, including the incremental-update flow, the #479 shrink guard + --force, --no-gitignore, GRAPHIFY_OUT, and the boolean-flag/positional parsing) and tests/test_skill_no_inline_python.py (a drift guard that fails if any split host or reference reintroduces an inline -c block).
Reviewed twice by a separate agent; all findings fixed (nested graphify-out from a wrong cache_root, merge-chunks erroring on the all-cached path, --no-gitignore/--force silently dropped, a boolean flag swallowing the following path, non-numeric label keys crashing, GRAPHIFY_OUT ignored, stale fallback prose, and the MCP config caveat).

Known blocker / deliberately out of scope: the aider & devin monoliths

skill-aider.md and skill-devin.md still contain inline Python (37 and 39 -c blocks). This is not a capability gap — it's a deliberately isolated, high-blast-radius change, and it is not what #197 reports (those are Aider and Devin, not Claude Code).

Why they're separate:

They aren't generated from core.md + references. gen.render() returns _read_fragment("core/{aider|devin}.md") verbatim — each is a hand-maintained 1,300–1,400-line single file that duplicates the entire pipeline and every reference flow inline. Converting them is the same work as everything in this PR, repeated twice.
They're frozen against a pinned v8 blob. monolith_roundtrip (tools/skillgen/gen.py:1232) diffs the rendered monolith against roundtrip_ref (a pinned v8 commit) and requires every non-blank changed line to match a predicate in _SANCTIONED_MONOLITH_DIFFS (19 predicates). So a conversion there also has to add a new sanctioned-diff predicate and re-validate the round-trip — the guard exists precisely to stop arbitrary drift, and touching it is a wide, cross-cutting change.
Different hosts. Aider and Devin have their own delivery mechanism; the Claude Code heuristics in Skill should use CLI subcommands instead of inline python -c #197 don't apply to them.

I chose to keep this PR scoped, correct, and low-risk rather than fold a 76-block rewrite of two frozen files into it. The monolith conversion is a clean follow-up PR on its own.

Scope summary

✅ Claude Code skill set (skill.md + skills/claude/references/*): zero inline Python, zero $(cat graphify-out/.graphify_python). Only Step 1's one-time interpreter detection remains (inherent to installing/detecting graphify, and it is a single block, not per-step).
✅ All other split hosts (Codex, Windows, opencode, kilo, copilot, claw, droid, amp, trae, kiro, pi, vscode, agents) and all references: zero non-bootstrap inline -c.
⏭️ aider/devin monoliths: unchanged, tracked as a follow-up (see above).

Ref #114 (which fixed only the save_query_result block).

Graphify-Labs#197) The agent skill carried each pipeline step as an inline `$(cat graphify-out/.graphify_python) -c "..."` block. That form trips Claude Code's command_substitution and "newline followed by #" approval prompts once per step and cannot be allowlisted, so a run cost ~30 manual confirmations. Add `graphify pipeline <step>` so every step is a plain console command: no inline script, no command substitution, and `Bash(graphify *)` is allowlistable. The step bodies live in graphify.pipeline and are transcriptions of the inline blocks they replace, so a run produces the same graph.json. Regenerate the skill artifacts from the updated core/shell fragments, and move the drift, cross-shell parity, and Graphify-Labs#2490 curated-label guards to follow the flow to the subcommands. The hand-authored aider/devin monoliths keep their inline pipelines for now.

) Follow-up fixes to the graphify pipeline steps, found in review: - detect: pass the directory that CONTAINS graphify-out as cache_root, not graphify-out itself, so the stat cache and Google-Workspace conversions are not written to a nested graphify-out/graphify-out. - merge-chunks: write an empty .graphify_semantic_new.json on zero chunks instead of erroring, so the all-cached path (which routes through B3) still produces the sidecar Part C reads unconditionally (Graphify-Labs#1392). - empty-semantic: return fresh lists per call rather than sharing module state. - cli: honor --no-gitignore (was silently dropped) and thread --force to build/label so the documented Graphify-Labs#479 remediation actually overrides the guard. - cli: reject non-integer --labels keys with a clean error instead of a traceback, and honor --help anywhere after the step. - out dir: honor the GRAPHIFY_OUT env override like the rest of the CLI (Graphify-Labs#686). - restore the @@INTERP_GUARD@@ block so the on-demand reference flows that still read .graphify_python keep their re-resolve safety net. Regenerate the skill artifacts.

…phify-Labs#197) The core pipeline was converted in the prior commit, but the reference flows it loads on demand (update, query, add/watch, transcribe, exports) still ran $(cat graphify-out/.graphify_python) -c "...", so /graphify update, /graphify query, /graphify add, transcription, and the MCP export still triggered the same Claude Code approval prompts. Convert them too, so the whole Claude Code skill set is free of inline Python and interpreter substitution. New pipeline steps: vocab, transcribe, detect-incremental, code-only-check, empty-extract, update-merge, graph-diff. Reference rewrites: - query: vocab step, graphify query/path/explain, graphify save-result; the obsolete inline NetworkX traversal fallback (which duplicated the CLI) is removed, and the query stub no longer promises it. - update: detect-incremental / code-only-check / empty-extract / update-merge / graph-diff replace the six inline blocks. - add-watch: graphify add, graphify watch (which now parses --debounce and defaults to the .graphify_root marker instead of the cwd). - transcribe: the transcribe step. - exports: graphify-mcp console script instead of -m graphify.serve. The drift guard now also covers graphify/skills/*/references/*.md, so a future inline block in any split host fails the test.

…abs#197) - cli: boolean pipeline flags (--directed/--force/--no-gitignore/ --google-workspace) no longer consume the next token, so detect --no-gitignore <path> scans the corpus instead of the cwd. - cli: watch --debounce with no value errors instead of silently defaulting. - query reference: drop stale prose about the removed inline fallback. - exports reference: note the absolute-interpreter fallback for a GUI Claude Desktop that lacks graphify-mcp on PATH. - tests: cover the boolean-flag ordering and the watch debounce error.

github-actions · 2026-10-10T06:01:42Z

Thanks for the pull request, @nothariharan. A maintainer will review it soon.

Want to talk it through while it is in review? Come join us on our Discord server. For longer-form discussion there is also GitHub Discussions.

A couple of things that speed up review: make sure the test suite passes on Python 3.10 and 3.13, and that the change keeps extraction deterministic.

graphify-labs

Graphify reviewed this change.

Formal verification could not match the changed code to the code graph, so it may not have checked the code this PR changed.

Worth a look — the grounded gate found no coupling regressions or blocking issues, but 1 advisory finding(s) below merit a look before merge.

Not checked: tests were not run; formal verification proved 0 of 1 changed function(s) (1 not verified).

Formal verification. PR-changed functions: 0/1 verified (0 proven, 0 may-equivalent, 0 distinguished) · 1 not verified (1 vacuous).

Not verified on this run: dispatch\_command (vacuous: never exercised).

Graphify review — findings

Adds a graphify pipeline <step> command that exposes each stage of the agent skill as a plain CLI step: detect, AST and semantic extraction with cache hits/misses, merging, build, the read-only diagnose health gate, labeling, manifest/cost tracking, cleanup, plus the query, transcribe and incremental-update steps. The generated skill files for every agent call these steps instead of inline python -c blocks, so they no longer need interpreter path substitution. Step sidecars default to the cwd, and boolean flags like --no-gitignore and --directed never swallow the following path.

Worth a look

step_label writes the report and labels before the shrink-guard can refuse — graphify/pipeline.py · Escalate · medium
- agreed by 2 of 2 members but NOT verified (no proof, no reproducing execution) — consensus is not a verdict; needs human review

Review partial — this diff was larger than one review pass covers, so later files were not reviewed; some findings may be missing.

Analysis details — impact, health, verification

Impact & health

Graphify review

Impact — 2073 functions depend on the 1834 functions this change touches.

Health — this change adds coupling hotspots:

worse: dispatch_command() — 2 callers, 131 callees
new: _cmd_pipeline() — 1 callers, 23 callees
new: step_build() — 1 callers, 13 callees
new: step_label() — 1 callers, 9 callees
new: step_extract_ast() — 1 callers, 7 callees
new: step_save_manifest() — 1 callers, 7 callees
new: step_update_merge() — 1 callers, 7 callees
new: step_graph_diff() — 1 callers, 6 callees
…and 1 more — each is listed as a finding

Verification — 2073 functions in the blast radius were not formally verified this run (proofs are advisory here).

Gate & verification

graphify gate

PASS — objectively clean (no health regressions, tests not run — proofs not run this pass (advisory)). Grounded, not self-assessed.

Advisory (not blocking):

verification_scope: 2005 function(s) in the blast radius were not formally verified this run

Test selection

357 of 357 test file(s) selected (100%) via static blast radius.

Escalated to a full run for safety — the selection is not trustworthy on its own (see below). CI should run the whole suite.

tests/test_affected_cli.py — impact, full-run-safety
tests/test_affected_member_seed.py — full-run-safety
tests/test_agents_platform.py — impact, full-run-safety
tests/test_analyze.py — full-run-safety
tests/test_anthropic_custom_endpoint.py — full-run-safety
tests/test_antigravity_install.py — full-run-safety
tests/test_apm_fallback_version.py — full-run-safety
tests/test_architecture_doc.py — full-run-safety
tests/test_astro_extraction.py — full-run-safety
tests/test_astro_import_ids.py — full-run-safety
tests/test_atomic_canvas_export.py — full-run-safety
tests/test_atomic_version_stamp.py — full-run-safety
tests/test_atomic_writes.py — full-run-safety
tests/test_backend_env_isolation.py — full-run-safety
tests/test_backend_extras.py — full-run-safety
tests/test_benchmark.py — full-run-safety
tests/test_benchmark_raw_graph.py — full-run-safety
tests/test_blade_extractor.py — full-run-safety
tests/test_build.py — full-run-safety
tests/test_build_located_semantic_identity.py — full-run-safety
tests/test_build_merge_dedup_scope.py — full-run-safety
tests/test_build_merge_hyperedges_and_prune.py — full-run-safety
tests/test_build_merge_shrink_guard.py — full-run-safety
tests/test_builtin_global_type_refs.py — full-run-safety
tests/test_cache.py — full-run-safety
tests/test_cache_stale_import_target.py — full-run-safety
tests/test_callflow_html.py — full-run-safety
tests/test_cargo_introspect.py — full-run-safety
tests/test_cargo_missing_manifest.py — full-run-safety
tests/test_carried_hyperedge_remap.py — full-run-safety
tests/test_case_sensitive_resolution.py — full-run-safety
tests/test_charmap_encoding.py — full-run-safety
tests/test_chunking.py — full-run-safety
tests/test_cjs_module_extension.py — full-run-safety
tests/test_claude_cli_backend.py — full-run-safety
tests/test_claude_md.py — full-run-safety
tests/test_cli_broken_pipe.py — full-run-safety
tests/test_cli_export.py — full-run-safety
tests/test_cli_help.py — full-run-safety
tests/test_cloud_cta.py — impact, full-run-safety
tests/test_cluster.py — full-run-safety
tests/test_cluster_ambiguous_scale.py — full-run-safety
tests/test_cluster_exclude_hubs.py — full-run-safety
tests/test_cobol_extractor.py — full-run-safety
tests/test_codebuddy.py — impact, full-run-safety
tests/test_community_hub_labels.py — full-run-safety
tests/test_community_labels_skill.py — impact, changed-test, full-run-safety
tests/test_confidence.py — full-run-safety
tests/test_corrupt_graph_json.py — full-run-safety
tests/test_cpp_method_declarations.py — full-run-safety
… and 307 more

non-code file(s) changed (graphify/skill-agents.md, graphify/skill-amp.md, graphify/skill-claw.md, graphify/skill-codex.md, graphify/skill-copilot.md …) → running the full suite for safety (a code graph can't see config/fixture/data deps)

changed code file(s) with no mapped test (graphify/skill-agents.md, graphify/skill-amp.md, graphify/skill-claw.md, graphify/skill-codex.md, graphify/skill-copilot.md …) — a coverage gap or a missing link — running the full suite rather than only the selected tests

Selection is safe under the controlled-regression assumption; always-run tests + a periodic full run are the backstops. Advisory — it never changes the check verdict.

Docs that may be stale (advisory)

CHANGELOG.md § 0.9.44 (2026-08-15) (lines 519-531): references changed symbols corpus
CHANGELOG.md § 0.9.33 (2026-08-05) (lines 641-647): references changed symbols corpus
CHANGELOG.md § 0.9.18 (2026-07-17) (lines 805-818): references changed symbols corpus
CHANGELOG.md § 0.9.17 (2026-07-16) (lines 819-848): references changed symbols corpus
CHANGELOG.md § 0.9.12 (2026-07-10) (lines 929-948): references changed symbols corpus
CHANGELOG.md § 0.8.1 (2026-05-15) (lines 1592-1603): references changed symbols corpus
docs/how-it-works.md § Token benchmark (lines 53-70): references changed symbols corpus
docs/superpowers/plans/2026-05-04-incremental-updates-dedup.md § Task 4: Incremental updates — semantic cache + manifest in __main__.py (lines 603-911): references changed symbols corpus
docs/translations/README.ja-JP.md § 実例 (lines 193-202): references changed symbols corpus
docs/translations/README.ko-KR.md § 실전 예제 (lines 233-242): references changed symbols corpus

…and 10 more.

Formal verification

Could not verify: Could not verify dispatch\_command.

The verifier did not have enough to check dispatch\_command, so it is saying so rather than guessing. No false assurance is the whole point.

Guarantee: No guarantee either way, this is an honest abstention, not a pass.

Note: Reason: no capturable inputs from the test suite; property tier: not verifiable: all 40 sampled inputs raised on both versions — the function never executed, so 'no divergence' would be vacuous (mostly SystemExit — names the real obstacle, not a sampling gap)

· 9 grounded finding(s) anchored inline below.

graphify-labs · 2026-10-10T06:07:12Z

+    return "\n".join(lines)
+
+
+def _cmd_pipeline(argv: list[str]) -> None:


⚠️ Health regression — _cmd_pipeline()

fans out to 23 callees (efferent coupling).

Grounded coupling-delta finding (deterministic), not an LLM guess.

graphify-labs · 2026-10-10T06:07:12Z

+        sys.exit(1)
+
+
 def dispatch_command(cmd: str) -> None:


⚠️ Health regression — dispatch_command()

fans out to 131 callees (efferent coupling).

Grounded coupling-delta finding (deterministic), not an LLM guess.

graphify-labs · 2026-10-10T06:07:12Z

+# --------------------------------------------------------------------------
+
+
+def step_extract_ast(


⚠️ Health regression — step_extract_ast()

fans out to 7 callees (efferent coupling).

Grounded coupling-delta finding (deterministic), not an LLM guess.

graphify-labs · 2026-10-10T06:07:12Z

+# --------------------------------------------------------------------------
+
+
+def step_merge_chunks(


⚠️ Health regression — step_merge_chunks()

fans out to 6 callees (efferent coupling).

Grounded coupling-delta finding (deterministic), not an LLM guess.

graphify-labs · 2026-10-10T06:07:12Z

+# --------------------------------------------------------------------------
+
+
+def step_build(


⚠️ Health regression — step_build()

fans out to 13 callees (efferent coupling).

Grounded coupling-delta finding (deterministic), not an LLM guess.

graphify-labs · 2026-10-10T06:07:13Z

+# --------------------------------------------------------------------------
+
+
+def step_label(


⚠️ Health regression — step_label()

fans out to 9 callees (efferent coupling).

Grounded coupling-delta finding (deterministic), not an LLM guess.

graphify-labs · 2026-10-10T06:07:13Z

+# --------------------------------------------------------------------------
+
+
+def step_save_manifest(


⚠️ Health regression — step_save_manifest()

fans out to 7 callees (efferent coupling).

Grounded coupling-delta finding (deterministic), not an LLM guess.

graphify-labs · 2026-10-10T06:07:13Z

+    return {"created": True}
+
+
+def step_update_merge(


⚠️ Health regression — step_update_merge()

fans out to 7 callees (efferent coupling).

Grounded coupling-delta finding (deterministic), not an LLM guess.

graphify-labs · 2026-10-10T06:07:13Z

+    }
+
+
+def step_graph_diff(


⚠️ Health regression — step_graph_diff()

fans out to 6 callees (efferent coupling).

Grounded coupling-delta finding (deterministic), not an LLM guess.

…mands # Conflicts: # graphify/skill-agents.md # graphify/skill-amp.md # graphify/skill-claw.md # graphify/skill-codex.md # graphify/skill-copilot.md # graphify/skill-droid.md # graphify/skill-kilo.md # graphify/skill-kiro.md # graphify/skill-opencode.md # graphify/skill-pi.md # graphify/skill-trae.md # graphify/skill-vscode.md # graphify/skill-windows.md # graphify/skill.md # graphify/skills/agents/references/update.md # graphify/skills/amp/references/update.md # graphify/skills/claude/references/update.md # graphify/skills/claw/references/update.md # graphify/skills/codex/references/update.md # graphify/skills/copilot/references/update.md # graphify/skills/droid/references/update.md # graphify/skills/kilo/references/update.md # graphify/skills/kiro/references/update.md # graphify/skills/opencode/references/update.md # graphify/skills/pi/references/update.md # graphify/skills/trae/references/update.md # graphify/skills/vscode/references/update.md # graphify/skills/windows/references/update.md # tools/skillgen/expected/graphify__skill-agents.md # tools/skillgen/expected/graphify__skill-amp.md # tools/skillgen/expected/graphify__skill-claw.md # tools/skillgen/expected/graphify__skill-codex.md # tools/skillgen/expected/graphify__skill-copilot.md # tools/skillgen/expected/graphify__skill-droid.md # tools/skillgen/expected/graphify__skill-kilo.md # tools/skillgen/expected/graphify__skill-kiro.md # tools/skillgen/expected/graphify__skill-opencode.md # tools/skillgen/expected/graphify__skill-pi.md # tools/skillgen/expected/graphify__skill-trae.md # tools/skillgen/expected/graphify__skill-vscode.md # tools/skillgen/expected/graphify__skill-windows.md # tools/skillgen/expected/graphify__skill.md # tools/skillgen/expected/graphify__skills__agents__references__update.md # tools/skillgen/expected/graphify__skills__amp__references__update.md # tools/skillgen/expected/graphify__skills__claude__references__update.md # tools/skillgen/expected/graphify__skills__claw__references__update.md # tools/skillgen/expected/graphify__skills__codex__references__update.md # tools/skillgen/expected/graphify__skills__copilot__references__update.md # tools/skillgen/expected/graphify__skills__droid__references__update.md # tools/skillgen/expected/graphify__skills__kilo__references__update.md # tools/skillgen/expected/graphify__skills__kiro__references__update.md # tools/skillgen/expected/graphify__skills__opencode__references__update.md # tools/skillgen/expected/graphify__skills__pi__references__update.md # tools/skillgen/expected/graphify__skills__trae__references__update.md # tools/skillgen/expected/graphify__skills__vscode__references__update.md # tools/skillgen/expected/graphify__skills__windows__references__update.md # tools/skillgen/fragments/core/core.md # tools/skillgen/fragments/references/shared/update.md

…Graphify-Labs#197, Graphify-Labs#4240) The split hosts no longer carry an inline detect block, so the Graphify-Labs#4240 guard now exercises graphify.pipeline.step_detect / step_detect_incremental, and the monoliths' remaining inline blocks are still executed. Same contract, new path.

nothariharan added 4 commits October 9, 2026 22:54

nothariharan requested a review from safishamsi as a code owner October 10, 2026 06:01

nothariharan mentioned this pull request Oct 10, 2026

Skill should use CLI subcommands instead of inline python -c #197

Open

graphify-labs Bot reviewed Oct 10, 2026

View reviewed changes

nothariharan added 2 commits October 10, 2026 11:45

Navigation Menu

Repository navigation

feat(skill): run the pipeline as `graphify pipeline` subcommands, no inline Python (#197) - #4275

feat(skill): run the pipeline as `graphify pipeline` subcommands, no inline Python (#197)#4275
nothariharan wants to merge 6 commits into
Graphify-Labs:v8from
nothariharan:fix/197-pipeline-subcommands

nothariharan commented Oct 10, 2026 •

edited

Loading

Uh oh!

github-actions Bot commented Oct 10, 2026

Uh oh!

graphify-labs Bot left a comment •

edited

Loading

Uh oh!

graphify-labs Bot Oct 10, 2026

Uh oh!

graphify-labs Bot Oct 10, 2026

Uh oh!

graphify-labs Bot Oct 10, 2026

Uh oh!

graphify-labs Bot Oct 10, 2026

Uh oh!

graphify-labs Bot Oct 10, 2026

Uh oh!

graphify-labs Bot Oct 10, 2026

Uh oh!

graphify-labs Bot Oct 10, 2026

Uh oh!

graphify-labs Bot Oct 10, 2026

Uh oh!

graphify-labs Bot Oct 10, 2026

Uh oh!

This branch has not been deployed

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

		return "\n".join(lines)


		def _cmd_pipeline(argv: list[str]) -> None:

		# --------------------------------------------------------------------------


		def step_extract_ast(

		# --------------------------------------------------------------------------


		def step_merge_chunks(

		# --------------------------------------------------------------------------


		def step_build(

		# --------------------------------------------------------------------------


		def step_label(

		# --------------------------------------------------------------------------


		def step_save_manifest(

Conversation

nothariharan commented Oct 10, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

What this fixes

How it's fixed

The skill is generated — the fragment is the source of truth

Verification

Known blocker / deliberately out of scope: the aider & devin monoliths

Scope summary

Uh oh!

github-actions Bot commented Oct 10, 2026

Uh oh!

graphify-labs Bot left a comment • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Graphify review — findings

Impact & health

Graphify review

Gate & verification

graphify gate

Test selection

Test selection

Docs that may be stale (advisory)

Formal verification

Uh oh!

graphify-labs Bot Oct 10, 2026

Choose a reason for hiding this comment

Uh oh!

graphify-labs Bot Oct 10, 2026

Choose a reason for hiding this comment

Uh oh!

graphify-labs Bot Oct 10, 2026

Choose a reason for hiding this comment

Uh oh!

graphify-labs Bot Oct 10, 2026

Choose a reason for hiding this comment

Uh oh!

graphify-labs Bot Oct 10, 2026

Choose a reason for hiding this comment

Uh oh!

graphify-labs Bot Oct 10, 2026

Choose a reason for hiding this comment

Uh oh!

graphify-labs Bot Oct 10, 2026

Choose a reason for hiding this comment

Uh oh!

graphify-labs Bot Oct 10, 2026

Choose a reason for hiding this comment

Uh oh!

graphify-labs Bot Oct 10, 2026

Choose a reason for hiding this comment

Uh oh!

This branch has not been deployed

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

nothariharan commented Oct 10, 2026 •

edited

Loading

graphify-labs Bot left a comment •

edited

Loading