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.
npx skills add jerseycheese/agent-skills --skill comment-reapergit clone --depth 1 https://github.com/jerseycheese/agent-skillsWrote 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.
[](https://agentmods.dev/skills/jerseycheese/agent-skills/comment-reaper)<a href="https://agentmods.dev/skills/jerseycheese/agent-skills/comment-reaper"><img src="https://agentmods.dev/badge/skills/jerseycheese/agent-skills/comment-reaper/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.
<a href="https://agentmods.dev/skills/jerseycheese/agent-skills/comment-reaper"><img src="https://agentmods.dev/badge/skills/jerseycheese/agent-skills/comment-reaper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00154 | $0.02238 |
| Opus 5 | $0.00077 | $0.01119 |
| Sonnet 5 | $0.00031 | $0.00448 |
| Haiku 4.5 | $0.00015 | $0.00224 |
Grade A, and why
comment-reaper 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Comment Reaper
Most comment cleanup fails one of two ways: it deletes a comment that was carrying a constraint nobody could reconstruct, or it stops at commented-out code and calls the job done. This skill exists because the second failure is the common one in a well-kept repo. The obvious rot is already gone; what remains is comments that are technically accurate and still worthless.
The rule this enforces is in the user's CLAUDE.md under "Code hygiene: comments & naming": explain WHY, not WHAT. That file names issue/PR citations as "the single most common violation of this section," and until this skill existed nothing looked for them.
The core discipline, inherited from doc-rot: a comment is not reapable because it looks obvious. It is reapable because the code already says it. Those differ. Read the code under the comment before cutting.
Sibling skills, so you don't do their job
doc-rotfixes comments that contradict the code. If the comment is wrong, that's rot, not bloat - hand it over.plain-language-auditfixes comments that are hard to read. Jargon and verbosity are quality problems; this skill is an existence problem.dead-code-cleanupremoves the code itself. If the function is dead, reap the function, not its docblock.
A comment can qualify for two skills at once. When it does, deletion wins: don't spend a rewrite on a comment that shouldn't exist.
Pre-flight
git fetch && git status. Confirm the base branch (developif it exists, elsemain) and that you're current. Auditing a stale checkout is the most common way this work gets wasted.- Scope it and say the scope out loud. A directory, a domain, the files a recent change touched. Do not sweep a whole repo in one pass - the diff becomes unreviewable and one bad deletion poisons the whole thing.
- Get the numbers before you touch anything. If the repo has an audit script (
npm run audit:comments), run it. Otherwise use the grep block below. You want a before count so the after count means something.
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.
- 9d ago First seen · 119 lines · 154 tokens per session scan A be659fd6b4ff
comment-reaper is a skill published in the GitHub repository jerseycheese/agent-skills (1 stars, last pushed 7d ago), licensed MIT. It adds 154 tokens to every session and 2,238 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
chorus-council
Run an LLM council — Claude (correctness), Gemini (edge cases), Cursor (integration), Kilo (maintainability), and you (scope) tackle the same task in parallel. Use when the user wants multiple independent perspectives on a decision, approach, or problem.
chorus-parallel-review
Parallel code review of the current git diff from multiple agents — Claude (correctness/security), Gemini (edge cases), Cursor (integration), Kilo (maintainability), and you (scope/simplicity). Use when the user says "parallel review", "review with all agents", or "chorus review".
install-gemini-code-review-action
Installs, configures, or upgrades Dazbo's PR code review & issue triage GitHub Action (gemini-review-action) in a target repository. Use when the user wants to set up, configure, or update automated AI code reviews, issue triaging, or Gemini model workflows for their GitHub repository.
pr-sweep
Use when you want to sweep all open pull requests across all repos, triage their status, run code reviews on unreviewed PRs, merge what's ready, fix quick blockers, and produce a full status report. Trigger when the user says "check my PRs", "close out open PRs", "what's the status of my PRs", "sweep my PRs", "PR…
rubber-ducky
Use when you've planned a non-trivial change and are about to implement it, finished a complex or multi-file piece of work, just wrote tests, or are stuck on repeated failures — and any time the user says "rubber duck this", "rubber ducky", "get a second opinion", "sanity-check my plan", "poke holes in this", "what am…
open-pr
Use when wrapping up a development task and getting a PR ready — runs local tests, creates a PR (if one doesn't exist) with a structured description template, conducts a code review via the review skill, and checks CI status with quick fixes. Trigger when the user says they're done with a feature, want to open a PR…