stale-comments-audit

stale-comments-audit is a skill for Claude Code, Codex from PaulRBerg/agent-skills. It costs 32 tokens per session (1,187 once invoked), scanned A, original, MIT.

A skill for checking comments in JavaScript, TypeScript, and Go code against the code they describe, then fixing comments that are outdated, misleading, unused, or repetitive.

In plain words
What is it for?
Scanning supported source files, excluding generated and test-related files by default, reviewing comments in manageable groups, and correcting confirmed mismatches.
Why use it?
Comments can become incorrect after code changes and confuse future developers. This skill limits the work to confirmed comment problems rather than changing program behavior.

Skill for Claude CodeCodex

Written for Claude Code and Codex: argument-hint in frontmatter, but also agents/openai.yaml present. Also seen: mentions subagents.

Good fit Scanning supported source files, excluding generated and test-related files by default, reviewing comments in manageable groups, and correcting confirmed mismatches.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/paulrberg/agent-skills/stale-comments-audit
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add PaulRBerg/agent-skills --skill stale-comments-audit
Clone the repo
git clone --depth 1 https://github.com/PaulRBerg/agent-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for stale-comments-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/paulrberg/agent-skills/stale-comments-audit/github.svg)](https://agentmods.dev/skills/paulrberg/agent-skills/stale-comments-audit)
Your own site
<a href="https://agentmods.dev/skills/paulrberg/agent-skills/stale-comments-audit"><img src="https://agentmods.dev/badge/skills/paulrberg/agent-skills/stale-comments-audit/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for stale-comments-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/paulrberg/agent-skills/stale-comments-audit"><img src="https://agentmods.dev/badge/skills/paulrberg/agent-skills/stale-comments-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,187 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.01187
Opus 5 $0.00016 $0.00593
Sonnet 5 $0.00006 $0.00237
Haiku 4.5 $0.00003 $0.00119

Measured 11d ago against content hash dd882b34f066, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

stale-comments-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/stale-comments-audit/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stale Comments Audit

Audit source comments against the code they describe, then fix every confirmed mismatch or source of noise in the same run. Limit edits to comments; never change executable code merely to make a comment true.

Scope

Accept zero or more file or directory paths. With no arguments, use the current repository root. Resolve every path from the current working directory and report any path that cannot be read.

Discover JavaScript, JSX, TypeScript, TSX, and Go source files. By default exclude:

  • tests, testdata, fixtures, snapshots, and stories;
  • generated, vendor, dependency, coverage, cache, and build-output directories;
  • minified JavaScript and generated Go files.

An explicitly named test file or test directory overrides only the test exclusion. Generated, vendored, minified, and build-output files remain excluded unless the user explicitly requests them.

Use repository-aware discovery when available (git ls-files or rg --files) and preserve the user's path order. Do not impose an arbitrary result cap.

Analysis

Split discovered files into non-overlapping batches of about ten. Delegate independent batches to read-only subagents when supported; otherwise inspect them directly. Continue useful work while delegated batches run.

For every line, block, and documentation comment, compare the claim with adjacent code, referenced symbols, callers, configuration, and relevant repository history when current code alone is inconclusive. Classify only clear findings:

  • STALE: describes behavior the code no longer has;
  • ORPHANED: references a symbol, path, flag, or concept that no longer exists;
  • MISLEADING: materially suggests behavior different from the implementation;
  • REDUNDANT: merely narrates self-explanatory code and carries no intent, constraint, or context.

Do not report style preferences, imperfect wording, useful rationale, or uncertainty as findings.

Behavior-Bearing Go Comments

Treat these as part of program behavior or required documentation, not ordinary prose:

Read the full file on GitHub · 124 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 124 lines · 32 tokens per session scan A dd882b34f066

Subscribe to this mod's changes

stale-comments-audit is a skill published in the GitHub repository PaulRBerg/agent-skills (70 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 1,187 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.