No comments
Spawn the Comment Sicko reviewer. Act on accepted findings.
Authoring agents defend their own comments. Defer to a reviewer that has not seen the code before.
Scope
Use the caller's files or diff. Otherwise use the current diff against the base branch, default main, including the working tree.
Steps
- Spawn one general-purpose subagent with
references/comment-sicko.md as its full prompt, passed verbatim, plus the scope. Do not restate or summarise its rules. If the harness has no subagent mechanism, apply that file as your own instructions for a single pass over the scope before returning to step 2 — the review is still worth having, but say in the report that it was self-reviewed rather than independent.
- 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 TypeScript suppressions. 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 /how or /why 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 /no-comments.
- 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
/architect once for the accepted set and surrounding code. Stop at the sketch. Architect shapes. Step 4 implements.
- 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 Fix Root Causes and Redesign from First Principles principles (see the
principles skill) guide intent only: fix real causes, redesign as if requirements always existed, never bolt on symptom guards. Neither authorizes widening the fence nor fixing instances outside it.
- 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 CI lint. Wait for interactive approval. Unattended and eval require caller pre-approval. If approved, encode then delete. Otherwise delete, report the constraint open, and sketch out-of-scope work.
- Report the deletion count, restored comments, reruns, architect sketch, fixes, encoding offers, encodings, unenforced constraints, and other open work.
1---2name: no-comments3description: "Delete narration, banner, and workaround comments from a diff via an adversarial reviewer subagent, then fix the accepted findings at their root cause and offer encodings for claimed constraints."4disable-model-invocation: true5metadata:6 source: https://skillmd.com/skills/finografic/no-comments7---89# No comments1011Spawn the Comment Sicko reviewer. Act on accepted findings.1213Authoring agents defend their own comments. Defer to a reviewer that has not seen the code before.1415## Scope1617Use the caller's files or diff. Otherwise use the current diff against the base branch, default `main`, including the working tree.1819## Steps20211. Spawn one general-purpose subagent with [`references/comment-sicko.md`](references/comment-sicko.md) as its full prompt, passed verbatim, plus the scope. Do not restate or summarise its rules. If the harness has no subagent mechanism, apply that file as your own instructions for a single pass over the scope before returning to step 2 — the review is still worth having, but say in the report that it was self-reviewed rather than independent.222. 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 TypeScript suppressions. Correctness or safety suppressions stay actionable `MUST KILL`s. Restore deletions only with exact exceptions and scoped proof. Before accepting thin `IMPORTANT` or `do not remove` kills or keeps, run `/how` or `/why` 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 `/no-comments`.233. 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 `/architect` once for the accepted set and surrounding code. Stop at the sketch. Architect shapes. Step 4 implements.244. 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 **Fix Root Causes** and **Redesign from First Principles** principles (see the `principles` skill) guide intent only: fix real causes, redesign as if requirements always existed, never bolt on symptom guards. Neither authorizes widening the fence nor fixing instances outside it.255. 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 CI lint. Wait for interactive approval. Unattended and eval require caller pre-approval. If approved, encode then delete. Otherwise delete, report the constraint open, and sketch out-of-scope work.266. Report the deletion count, restored comments, reruns, architect sketch, fixes, encoding offers, encodings, unenforced constraints, and other open work.