No comments

Spawn the astack:comment-critic agent. Act on accepted findings.

Defer to the comment-critic's fresh perspective.

Scope

Use the caller's files or diff. Otherwise use the current diff against main, including uncommitted edits: git diff $(git merge-base main HEAD). Notebook markdown cells that narrate code count as comments. Markdown that states a finding for a reader stays in the findings report and is out of scope.

Steps

1. Spawn the Agent tool with subagent_type astack:comment-critic. Pass the scope. Do not restate its rules.
2. Inspect its report and diff. Reject application-code edits, scope escapes, exception-protected deletions, misstated MUST KILL reasons, and flags that treat kept intentional code as guilty. Reshape flags on our-code surprises stay actionable. Do not restore those comments. A keep survives only with proof it is about something we cannot change. Audit missed scoped lint and type suppressions (# noqa, # type: ignore, # ty: ignore, and the SQL or notebook equivalents). Correctness or safety suppressions stay actionable MUST KILLs. Restore deletions only with exact exceptions and scoped proof. Before accepting thin IMPORTANT or do not remove kills or keeps, run the how or why skill on their symbol. If a kill is ambiguous, do not restore. If a keep is refuted or still ambiguous, delete it. Revert and rerun one rejected report with the failure named. Reject a second, report it open, and fail /astack:no-comments.
3. Fix trivial accepted flags directly by deleting a dead path, dropping a parameter, or using the real API. If any fix needs a shape, run the architect skill once for the accepted set and surrounding code. Stop at the sketch. Architect shapes. Step 4 implements.
4. Implement the smallest root-cause fix in scope. Remove every named workaround. If the root cause is out of scope, land the smallest in-scope fix and report the rest open. The principle-fix-root-causes skill guides intent only. It does not authorize widening the fence nor fixing instances outside it. Never bolt on symptom guards.
5. Constraint comments say do not remove, do not change wording, or talk to X before changing. Leave keeps about things we cannot change. Offer the cheapest in-scope type, runtime, test, or lint check, such as a ruff rule or a schema assertion. Wait for interactive approval. Unattended and eval runs require caller pre-approval. If approved, encode then delete. Otherwise delete, report the constraint open, and sketch out-of-scope work.
6. Report the deletion count, restored comments, reruns, architect sketch, fixes, encoding offers, encodings, unenforced constraints, and other open work.