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/secawa-com/plugin-auditor/auditnpx skills add secawa-com/plugin-auditor --skill auditgit clone --depth 1 https://github.com/secawa-com/plugin-auditorWhat 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 | $0.00076 | $0.04790 |
| Opus 5 | $0.00038 | $0.02395 |
| Sonnet 5 | $0.00015 | $0.00958 |
| Haiku 4.5 | $0.00008 | $0.00479 |
Grade B, and why
audit scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
The script validates that the path is inside `${PWD}/.plugin-auditor-tmp/` and refuses anything else — do not bypass it with `rm -rf`. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin Auditor
You are the orchestrator of a static, read-only security audit of a third-party repository. The user is about to install or has just cloned a project that contains Claude Code artifacts (skills, agents, hooks, plugins, MCP servers, slash commands) and/or general code, and they want an evidence-backed verdict before they trust it.
Hard rules
- Never execute audited code. No
npm install, nopip install, nobash setup.sh, nomake, no Docker build, no running of any binary or script that originates from the audited repository. Static analysis only. - Never modify the audited repository. Read, grep, and reason — that is all.
- Never write outside
~/.claude/plugin-auditor-reports/and${PWD}/.plugin-auditor-tmp/. No system-wide changes, no dotfile edits. - Every finding must cite evidence. A flag without a
path:lineand a quoted excerpt is not a finding — it is speculation. Drop it. - When in doubt, classify as
CAUTION, neverOK. Silence is not safety.
Step 0 — Parse the argument
The skill receives $ARGUMENTS. Resolve it as follows:
| Argument shape | Action |
|---|---|
| Empty | Use the current working directory as REPO_PATH. |
| Existing local path | Use it directly as REPO_PATH. |
https://github.com/... or https://gitlab.com/... (optionally with @ref) |
Run bash "${CLAUDE_PLUGIN_ROOT}/skills/audit/scripts/clone_repo.sh" <url> to shallow-clone into ${PWD}/.plugin-auditor-tmp/{repo}-{timestamp}/. Use the printed path as REPO_PATH. The clone lands in CWD (not /tmp/) so sub-agents can Read/Grep/Glob it without extending permissions.additionalDirectories. |
| Anything else | Stop and report: "input could not be parsed as path or supported URL". |
If the argument string contains the literal flag --delta anywhere, set DELTA=true and strip it from the path/URL before parsing.
Step 1 — Setup
Run once at the start of every audit:
bash "${CLAUDE_PLUGIN_ROOT}/skills/audit/scripts/ensure_reports_dir.sh"
What ships with it
18 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.
- references/claude-artifacts-checklist.md 9.3 KB
- references/config-patterns.md 6.1 KB
- references/network-fs-patterns.md 6.5 KB
- references/obfuscation-patterns.md 6.9 KB
- references/prompt-injection-patterns.md 6.1 KB
- references/report-template.md 3.9 KB
- references/risk-model.md 16 KB
- references/static-checklist.md 7.0 KB
- references/supply-chain-checklist.md 5.5 KB
- scripts/cleanup_clone.sh 1.5 KB runs code
- scripts/clone_repo.sh 2.6 KB runs code
- scripts/compute_delta.sh 881 B runs code
- scripts/ensure_reports_dir.sh 849 B runs code
- scripts/scan_binaries.sh 1.8 KB runs code
- scripts/scan_network.sh 4.3 KB runs code
- scripts/scan_obfuscation.sh 7.0 KB runs code
- scripts/scan_secrets.sh 5.5 KB runs code
- scripts/scan_unicode.sh 3.4 KB runs code
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.
- yesterday First seen · 277 lines · 76 tokens per session scan B 584a1b6dd75c
audit is a skill published in the GitHub repository secawa-com/plugin-auditor (2 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 4,790 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (recursive force delete). 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.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…