Skip to content
Back to skills

No Comments

ASecurity

Review comments, remove redundancy, and encode real constraints.

  • 2 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added October 1, 2026
ai-agentsdocumentation

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned October 6, 2026

npx -y skills add williamwue/oh-my-stack --skill no-comments --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of No Comments?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for No Comments
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/williamwue-no-comments-oh-my-stack/badge)](https://www.skillsdirectory.com/skills/williamwue-no-comments-oh-my-stack)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: no-comments
description: "Review comments, remove redundancy, and encode real constraints."
---

# No comments

## Codex delegation binding

For every delegated worker in this workflow, derive the exact `model`,
`reasoning_effort`, and complete role-plus-task `message` with
`../../scripts/codex-delegation.mjs prepare` relative to this Skill. It resolves
the nearest project manifest first, then the user manifest. Supply the named
route/panel entry where configured; otherwise supply the canonical role
and the observed parent model and effort. Pass
the returned `task_name`, `fork_turns=none`, model, effort, and message
explicitly to the spawn call. Do not use a generated custom-role name as a selector or
claim its TOML was activated. After the worker finishes, run the helper's
`verify` mode on the persisted parent and child records when available; it
checks the spawn metadata, parent link, and child `turn_context`.
The persisted spawn message may be encrypted; disclose when its exact
role/task text cannot be audited. If records are unavailable, state that
runtime model resolution is unverified.

## Child session handoff

Read [the handoff contract](../poteto-mode/references/subagent-handoff.md).
New tasks, repair rounds, retries, and queue items use fresh child sessions
with the original brief, every later directive, prior findings and responses,
and unresolved objections. Reuse only for required costly live state, and
only when the host allows it. Stop and fence active writers before replacement.
A host-owned orchestrator's model catalog, workspace binding, child tools,
and review-round rules take precedence over the native binding above.
Keep its task handles and attribution receipts. Do not use a backing child
conversation as a new delegated review, or claim native-record verification
for a host-owned child. Report attribution evidence gaps explicitly.

Review the files or diff named by the user; otherwise use the current diff
against the actual base branch, including uncommitted changes. Freeze that
scope first. Ask a distinct reviewer to flag comments that merely narrate code,
stale warnings, unexplained suppressions, and constraints that could be types,
tests, or checks. Root-only review is a fallback, not independent review.

Inspect every finding and the actual diff. Preserve license notices,
public-interface documentation, external protocol requirements, and necessary
historical rationale. Do not treat a useful comment as guilty merely because
it looks emphatic. For disputed constraints, use [how](../how/SKILL.md) or
[why](../why/SKILL.md) on the symbol and cite the result.

Delete accepted redundant comments without changing behavior. For a
suppression, identify the underlying error and the narrowest real fix; never
remove a safety suppression while leaving the hazard. If changing code is
authorized, make the minimal root-cause change in scope and run the matching
checks. A substantial shape change can use a design sketch, but the review
does not authorize an unrelated refactor.

Offer type, test, lint, or runtime encodings for genuine constraints. Apply an
encoding only when within the requested edit scope. Where the source of truth
is external or the constraint remains unenforced, retain a concise useful
comment. Reinspect the final diff for missed suppressions and accidental code
edits. Return removed, retained, and revised comments, fixes and checks, plus
constraints still needing enforcement. Never claim a clean review from a
reviewer summary that the root has not checked.

Files in this skill

  • SKILL.md2.7 KB
  • agents/openai.yaml234 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…