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 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/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/bendrucker/claude/audit"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 150 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00111 | $0.01242 |
| Opus 5.5 | $0.00044 | $0.00497 |
| Sonnet 5.5 | $0.00022 | $0.00248 |
| Haiku 4.5 | $0.00011 | $0.00124 |
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 10d 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 — 86 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 comment earns its place when it adds information not readily available in the adjacent code. The judge returns one action per comment: keep, trim (delete or shorten), or rewrite (keep the fact, strip the AI voice). judge/prompt.md holds the comment model and its carve-outs.
Run three steps in order: preflight (extract, rank, build the job), one judge agent per shard, and apply (write the trims or report them). The run is done when apply has printed its branch name or its report, and every comment it could not splice is listed for the user.
Scope and Flags
- Default,
--base <ref>,--mr <iid>: diff scope. Judges the comments a change introduced. Default is the working tree (staged, unstaged, and untracked).--base maindiffs the same working tree against 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. Use it on a first--allrun on a large repo to cap the agent count.--sort lines|chars|score(defaultscore): rank by comment complexity so the longest, densest comments judge first.--limit <n>: keep only the top N ranked comments.--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. Without it, the limit is the widest line of the comment being replaced or 80 columns, whichever is wider.
Preflight
Run from the repository being audited. The script resolves the git root itself.
bun <plugin-dir>/skills/audit/scripts/audit.ts preflight $ARGUMENTS
The script prints a human summary followed by a machine block:
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.
- 10d ago Changed · -13 lines bcf1c0e10484
- 11d ago Changed eb6d0172c757
- 1mo ago Changed dd2a05032610
- 1mo ago Changed · -89 lines · +1 tokens per session 9b9e272c5ca3
- 1mo ago Changed · +11 lines 077ab4df87a1
- 2mo ago Changed · +7 lines d5c5431e66cf
- 2mo ago First seen · 170 lines · 110 tokens per session scan A 3b9813dfe41a
comments:audit is a skill published in the GitHub repository bendrucker/claude (18 stars, last pushed today), licensed MIT. It adds 111 tokens to every session and 1,242 once invoked, about $0.0004 per session on Opus 5.5. 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.
comments:audit compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| comments:auditbendrucker/claude | Skill | 18 | today | MIT | A | 111 | Claude Code |
| reviewSethGammon/Citadel | Skill | 928 | 4d ago | MIT | A | 17 | Claude Code |
| critical-code-reviewerposit-dev/skills | Skill | 561 | 7d ago | MIT | A | 67 | Claude Code |
| brooks-sweephyhmrright/brooks-lint | Skill | 1.6k | today | MIT | A | 178 | Claude Code |
| pr-reviewnitinjain999/platform-skills | Skill | 71 | yesterday | Apache-2.0 | A | 81 | Claude Code |
| skill-distilleriliaal/whetstone | Skill | 36 | today | MIT | A | 91 | Claude Code |
| review-depthjszmajda/lid | Skill | 118 | today | MIT | A | 93 | Claude Code |