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 adolfousier/opencrabs --skill repo-auditgit clone --depth 1 https://github.com/adolfousier/opencrabsWrote 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/adolfousier/opencrabs/repo-audit)<a href="https://agentmods.dev/skills/adolfousier/opencrabs/repo-audit"><img src="https://agentmods.dev/badge/skills/adolfousier/opencrabs/repo-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/adolfousier/opencrabs/repo-audit"><img src="https://agentmods.dev/badge/skills/adolfousier/opencrabs/repo-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 MCP Rug Pull · line 17 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 17 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00035 | $0.03694 |
| Opus 5 | $0.00017 | $0.01847 |
| Sonnet 5 | $0.00007 | $0.00739 |
| Haiku 4.5 | $0.00003 | $0.00369 |
Grade A, and why
repo-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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior engineer performing a comprehensive repository health audit. The audit must be language-agnostic — detect the project's primary language(s) FIRST, then dispatch to the appropriate metrics and tooling. Do not apply JavaScript-specific checks (try/catch coverage, JSDoc, node_modules) to a Rust project. Do not apply Rust-specific checks to a Python project. Each language has its own conventions; respect them.
A previous third-party tool produced a Rust-blind report on this codebase that hallucinated "0 dependencies" and "0% try/catch coverage" because it could not parse Cargo.toml or recognize Result<T, E> error handling. Do not be that tool. When in doubt about a metric, skip it and say why rather than report a misleading zero.
Stage 1 — Language detection
Inspect the working directory for manifest files. Multiple manifests = polyglot/monorepo — audit each stack and report per-stack scores.
| Manifest detected | Language | Native tooling for audit |
|---|---|---|
Cargo.toml |
Rust | cargo clippy, cargo test, cargo audit, cargo outdated, cargo tree |
package.json + package-lock.json |
Node (npm) | npm audit, npm outdated, npx eslint, npx tsc --noEmit (if TS) |
package.json + pnpm-lock.yaml |
Node (pnpm) | pnpm audit, pnpm outdated, pnpm exec eslint |
package.json + yarn.lock |
Node (yarn) | yarn npm audit, yarn outdated, yarn eslint |
pyproject.toml / requirements*.txt / Pipfile.lock |
Python | ruff check, pip-audit, pytest --co, mypy |
go.mod |
Go | go vet, staticcheck, govulncheck, go test ./... |
Gemfile.lock |
Ruby | bundle outdated, bundle audit, rubocop |
composer.json |
PHP | composer audit, phpstan |
pom.xml / build.gradle |
Java/JVM | mvn dependency:tree, osv-scanner -r ., spotbugs |
pubspec.yaml |
Dart/Flutter | flutter analyze, dart pub outdated |
*.csproj / *.fsproj |
.NET | dotnet list package --vulnerable, dotnet build |
Package.swift |
Swift | swift package show-dependencies, swiftlint |
mix.exs |
Elixir | mix deps.audit, mix credo, mix dialyzer |
*.tf / .terraform.lock.hcl |
Terraform | tflint, tfsec, checkov |
Dockerfile |
OCI | hadolint, trivy fs . |
Record what you detected and what you did NOT detect (so the score is auditable). If the relevant scanner is not installed, report which scanner would run and continue with stages that don't need it.
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 First seen · 245 lines · 35 tokens per session scan A 27dca355f1e7
repo-audit is a skill published in the GitHub repository adolfousier/opencrabs (930 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 3,694 once invoked, about $0.0002 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
cn-check
Install and run the Continue CLI (cn) to execute AI agent checks on local code changes. Use when asked to "run checks", "lint with AI", "review my changes with cn", or set up Continue CI locally.
compare-harnesses
Diff two scaffolded harnesses (ADR-031). Reports manifest meta drift + host list + per-file fingerprint changes (added/removed/changed). Exits 0 IDENTICAL, 1 DRIFT, 2 missing manifest. Use --bundle for the ADR-031 schema-1 JSON envelope.
diag-harness
Kernel-version skew check (ADR-027). Reports manifest surface + manifest kernel + installed kernel + verdict (match/patch-diff/minor-diff/major-diff). Exits 1 on minor/major skew with a copy-pasteable npm install @metaharness/[email protected] next step. Exits 2 if no .harness/manifest.json at path.
create-harness
Scaffold your own focused AI agent harness — pick host (Claude Code, Codex, pi.dev, Hermes), template, agents, skills, and ship a npm-publishable harness with its own npx CLI. Use when a user asks to "create my own agent harness", "scaffold a harness", "make a custom Claude Code plugin like ruflo", or "build a…
example-harness
Scaffold a ready-made AI agent harness in one command from the 19 published @metaharness/ example packages — 9 host integrations (Claude Code, Codex, Hermes, pi.dev, OpenClaw, RVM, Copilot, OpenCode, GitHub Actions) + 10 vertical pods (devops, research, trading, support, legal, coding, education, sales, gaming…
repo-genome
7-section readiness scorecard for a LOCAL repo. Reports repo type + agent topology + MCP risk + test confidence + release readiness + recommended harness plan + scorecard. Exit 0 ready, 1 needs-work, 2 blocked. --json for the 6-field scorecard, --bundle for the ADR-031 schema-1 envelope.