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 agentmods add skills/bendrucker/claude/auditnpx skills add bendrucker/claude --skill auditgit clone --depth 1 https://github.com/bendrucker/claudeWrote 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/bendrucker/claude/audit)<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>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 | $0.00110 | $0.02008 |
| Opus 5 | $0.00055 | $0.01004 |
| Sonnet 5 | $0.00022 | $0.00402 |
| Haiku 4.5 | $0.00011 | $0.00201 |
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.
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 — 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 mainis the merge-base with a ref.--mr <iid>is a GitLab merge request overglab. --all: repo scope. Judges every tracked code file's comments.--path <glob>: narrow either scope to matching paths. Repeatable. Prefer it on a first--allrun on a large repo to cap the agent count.--sort lines|chars|score(defaultscore): 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 exceedncolumns. Width goes unchecked when the flag is absent.
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.
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.
- 3d ago First seen · 170 lines · 110 tokens per session scan A 3b9813dfe41a
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
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.
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.
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.
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…