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/benahammond/code-auditor-mcp/code-auditornpx skills add BenAHammond/code-auditor-mcp --skill code-auditorgit clone --depth 1 https://github.com/BenAHammond/code-auditor-mcpWhat 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 | $0.00025 | $0.03054 |
| Opus 5 | $0.00013 | $0.01527 |
| Sonnet 5 | $0.00005 | $0.00611 |
| Haiku 4.5 | $0.00003 | $0.00305 |
Grade A, and why
code-auditor 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 2d 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Auditor Skill
Version 3.4.8 • Run
code-audit --versionto check your installed version. If versions differ, the CLI is authoritative — usecode-audit <command> --helpto see what your install actually supports.
You have the code-audit CLI available. It indexes every function, component, and struct in the codebase for semantic search and invariant enforcement. Use these commands instead of raw grep/find whenever possible.
When to use which command
code-audit search — find code by meaning, not just text
Use code-audit search <query> with its operator syntax instead of grep or rg. The full operator reference is in SKILL-SEARCH.md.
Key operators:
calls:<fn>— every caller of a function (uses the call graph, not regex)dep:<module>— everything importing a modulelang:<lang> complexity:>N— complex functions in a specific languageexported:— public API surfacefile:<glob>— scope to matching file pathsunused-imports— dead imports to clean up
Free-text terms search function names, signatures, JSDoc, and bodies via FTS5. This is almost always faster and more accurate than grepping.
code-audit search "calls:validateUser lang:typescript complexity:>5" --limit 20 --json
code-audit search --definition "UserService.createUser" # look up a specific symbol
code-audit search "dep:express exported:" --language go # Go functions that import express and are exported
code-audit audit — run analysis before claiming work is done
Run an audit before declaring a task complete:
code-audit audit --path . # Full audit
code-audit changed --json --fail-on critical # Diff-scoped audit (hook contract)
Use code-audit changed after edits to confirm you haven't introduced violations. If the hook is active it already runs code-audit changed --fail-on critical automatically on Write/Edit — pay attention to its output.
Expected output: JSON violation list (with --json) or colored terminal summary. Non-zero exit code means violations at or above --fail-on severity were found.
What ships with it
2 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.
- 2d ago First seen · 217 lines · 25 tokens per session scan A 53891dba9a1d
code-auditor is a skill published in the GitHub repository BenAHammond/code-auditor-mcp (7 stars, last pushed 6d ago), licensed MIT. It adds 25 tokens to every session and 3,054 once invoked, about $0.0001 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
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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…