audit — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited audit (Plugin) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
A pre-ship audit suite for [Claude Code](https://claude.com/claude-code) — 13 skills under one plugin. Run any audit on its own, or `/audit:all` to orchestrate the whole suite into a single combined scorecard.
This is a Claude Code plugin marketplace. The whole suite installs as one plugin (audit); every audit is then an individually invocable, namespaced command (/audit:security, /audit:a11y, …). One install, no per-repo sprawl, no drift between siblings.
| Command | Focus |
|---|---|
/audit:all | Orchestrator — runs the suite in sequence, merges into one scorecard with a SHIP / WARNINGS / DO NOT SHIP verdict |
/audit:security | Attack surface — 33 vectors (OWASP, auth, API, client-side, AI) |
/audit:deep | Code quality + security + injection surface (3 parallel agents) |
/audit:deps | Dependency health — licenses, outdated, unused, duplicates, bundle size, vulns |
/audit:compliance | Regulatory — GDPR, ISO 27001:2022, ISO 9001:2015 (+ HIPAA/SOC2/PCI), 7 dimensions |
/audit:tech-stack | Stack-convention conformance — 8 checks, adapts to your detected stack |
/audit:forms | Form hardening — 38-point spam/bot/security checklist |
/audit:a11y | Accessibility — WCAG 2.1 AA, 29 checks |
/audit:seo | SEO + technical SEO + GEO (generative-engine optimization) |
/audit:deploy | Pre-deploy production-readiness checklist |
/audit:responsive | Responsive / mobile optimization across viewports |
/audit:hallucination | LLM fabrication-risk audit — 46 vectors for prompts, AI-integration code, and generated content |
/audit:diff | Compare two audit reports — what improved, regressed, or is new |
Every audit is report-only by default; the ones that can remediate take an opt-in --fix. All findings carry file:line evidence, and each skill enforces its own anti-hallucination rules (no invented identifiers, evidence-mandated findings).
# 1. Add this marketplace (Git-based; owner/repo shorthand):
/plugin marketplace add soreavis/claude-audit-skills
# 2. Install the suite:
/plugin install audit@soreavis-skills
# 3. Activate without restarting:
/reload-pluginsThen run any audit, e.g.:
/audit:security --fix
/audit:all --tier=full --scope=src/ --report
/audit:a11yTeam setup (project .claude/settings.json):
{
"extraKnownMarketplaces": {
"soreavis-skills": {
"source": { "source": "github", "repo": "soreavis/claude-audit-skills" }
}
},
"enabledPlugins": {
"audit@soreavis-skills": true
}
}/audit:all tiers| Tier | Audits | When |
|---|---|---|
quick | security, deploy | Fast sanity check / MVP |
standard (default) | security, deploy, forms, a11y, responsive | Most public-facing web projects |
full | hallucination, security, deep, deps, compliance, tech-stack, forms, a11y, seo, responsive, deploy | Pre-launch of a paid / regulated / customer-facing product |
/audit:all # standard tier
/audit:all --tier=full --skip=hallucination # everything except the AI-risk pass
/audit:all --tier=quick --include=a11y # compose tier + include/skip(/audit:diff isn't part of a run-all — it compares two existing reports. Run /audit:all twice across a fix sprint, then /audit:diff.)
claude-audit-skills/
├── .claude-plugin/
│ └── marketplace.json # lists the `audit` plugin
└── plugins/
└── audit/
├── .claude-plugin/plugin.json
└── skills/
├── all/SKILL.md → /audit:all
├── security/SKILL.md → /audit:security
├── deep/SKILL.md → /audit:deep
└── … (13 skills total)Grep / Glob / Read against the codebase--report / --fix reports: a _local/ directory (skills create one if needed)No external services. No API keys. Pure methodology + Claude Code execution.
MIT — copy it, ship it, improve it.
Built with Claude Code. Vector and checklist catalogs assembled from OWASP, WCAG 2.1, web.dev, GDPR / ISO 27001:2022, and real shipping experience.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.