comments:audit

comments:audit is a skill for Claude Code, Codex from bendrucker/claude. It costs 110 tokens per session (2,008 once invoked), scanned A, original, MIT.

A code-comment review process that finds comments adding little useful information, such as restatements or narration.

In plain words
What is it for?
It reviews comments in a code change or whole repository, ranks them, asks judging agents whether to keep, shorten, or rewrite them, and can apply the results on a new branch.
Why use it?
It helps reduce comments that make code harder to read without explaining something the code does not already show.

Skill for Claude CodeCodex

Part of the comments plugin — 1 skill shipped together

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.

agentmods
npx agentmods add skills/bendrucker/claude/audit
Any agent
npx skills add bendrucker/claude --skill audit
Clone the repo
git clone --depth 1 https://github.com/bendrucker/claude

Made for: Claude Code, Codex.

Or install comments, the plugin that ships this one along with the rest of its 1 skill.

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 comments:audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/bendrucker/claude/audit.svg)](https://agentmods.dev/skills/bendrucker/claude/audit)
Your own site
<a href="https://agentmods.dev/skills/bendrucker/claude/audit"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,008 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00110 $0.02008
Opus 5 $0.00055 $0.01004
Sonnet 5 $0.00022 $0.00402
Haiku 4.5 $0.00011 $0.00201

Measured 3d ago against content hash 3b9813dfe41a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 3d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/apply.ts, scripts/audit.test.ts, scripts/audit.ts, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/comments/skills/audit/SKILL.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Comments Audit

Find low-value comments and act on them. A deterministic Shiki pass extracts comments over TextMate grammars, the scope selects which to judge, a fan-out of Claude Code agents judges each against the owner's comment model, and a deterministic applier writes the changes to a branch. The judge returns one of three actions per comment: keep (it earns its place), trim (it carries no fact, delete or shorten it), or rewrite (it carries a real fact under AI voice, strip the voice and keep the fact). A comment earns its place when it adds information not readily available in the adjacent code. See judge/prompt.md for the full model and carve-outs.

Model-invocable so ship can run it as its comment pass. The consent gate at Preflight caps the cost of a misfire at one cheap extraction.

The pipeline is three steps: preflight (extract, rank, build the job), the Workflow tool (judge), and apply (write the trims or report them).

Scope and Flags

Two scopes run the same pipeline. The flags select scope and narrow it:

  • Default, --base <ref>, --mr <iid>: diff scope. Judges the comments a change introduced. Default is the working tree (staged plus unstaged). --base main is the merge-base with a ref. --mr <iid> is a GitLab merge request over glab.
  • --all: repo scope. Judges every tracked code file's comments.
  • --path <glob>: narrow either scope to matching paths. Repeatable. Prefer it on a first --all run on a large repo to cap the agent count.
  • --sort lines|chars|score (default score): rank by intrinsic comment complexity so the longest, densest comments judge first.
  • --limit <n>: keep only the top N ranked comments.

Both scopes exempt machine-meaningful comments deterministically: lint and compiler directives (eslint-disable, noqa, go:generate), shebang lines, and license headers never reach the judge.

  • --fix: ask the judge for a concrete suggestion per finding.
  • --report: at apply time, print findings instead of writing a branch.
  • --format <template>: at apply time, pipe each edited file through a formatter before committing.
  • --max-width <n>: at apply time, refuse a splice that would exceed n columns. Width goes unchecked when the flag is absent.

Read the full file on GitHub · 170 lines

Files

What ships with it

5 files 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. 3d ago First seen · 170 lines · 110 tokens per session scan A 3b9813dfe41a

Subscribe to this mod's changes

comments:audit is a skill published in the GitHub repository bendrucker/claude (16 stars, last pushed today), licensed MIT. It adds 110 tokens to every session and 2,008 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens