samsam007bsamsam007b/claude-code-standards-kit/skills/audit-runner/SKILL.md

audit-runner

Skill2 starsChanged 8 months agoMITView on GitHub

Run one or more SQWR audit agents on the current project. Supports individual domains or the full audit suite.

1 other project uses a version of this.

Adopted by

Most recently taken up by

pankaj-mahaur/Agent-Daemontheir own version, first seen Nov 6, 2026

Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
pankaj-mahaur/Agent-Daemon★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository11 other files it gives its agents.
- global/CLAUDE.mdCLAUDE.md
- templates/CLAUDE.mdCLAUDE.md
- auto-fixSkill
- brainstormSkill
- compliance-checkSkill
- contract-lookupSkill
- monthly-reviewSkill
- new-featureSkill
- pre-deploymentSkill
- project-setupSkill
- risk-scoreSkill

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Read the corresponding agent file(s)
line 58
Distinctive:
After the audit completes:
line 93

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

Contexte projet (injecté automatiquement)

Branch courante : !git branch --show-current 2>/dev/null || echo "non-git"
Dernier commit : !git log -1 --format="%H %s" 2>/dev/null || echo "none"
Fichiers modifiés : !git diff --name-only HEAD 2>/dev/null | head -20 || echo "none"
Stack détectée : ![ -f next.config.ts ] || [ -f next.config.js ] && echo "Next.js" || [ -f Package.swift ] && echo "iOS" || [ -f build.gradle.kts ] && echo "Android" || [ -f pyproject.toml ] && echo "Python" || echo "unknown"

/audit-runner — Audit Runner

Usage: /audit-runner [domain or "full"]

Runs the specified SQWR audit agent(s) on the current project.

Examples:

/audit-runner security → runs AGENT-SECURITY-AUDIT.md
/audit-runner full → runs AGENT-FULL-AUDIT.md (all 8 domains)
/audit-runner security performance → runs both agents
/audit-runner accessibility → runs AGENT-ACCESSIBILITY-AUDIT.md

Domain mapping

Parse $ARGUMENTS and run the corresponding agents:

Argument	Agent file
`security`	`agents/AGENT-SECURITY-AUDIT.md`
`performance`	`agents/AGENT-PERFORMANCE-AUDIT.md`
`quality`, `code-quality`	`agents/AGENT-CODE-QUALITY-AUDIT.md`
`accessibility`, `a11y`	`agents/AGENT-ACCESSIBILITY-AUDIT.md`
`observability`, `logging`	`agents/AGENT-OBSERVABILITY-AUDIT.md`
`design`	`agents/AGENT-DESIGN-AUDIT.md`
`ai`, `ai-governance`	`agents/AGENT-AI-GOVERNANCE-AUDIT.md`
`deployment`, `deploy`	`agents/AGENT-DEPLOYMENT-GATE.md`
`resilience`	`agents/AGENT-RESILIENCE-AUDIT.md`
`full`, `all`	`agents/AGENT-FULL-AUDIT.md`

Execution

Read the corresponding agent file(s)
Execute each agent's verification levels (1→4) against the current project
Compute the score per agent: (passed / applicable) × 100
Report findings with specific file references for failures

Output format

SQWR AUDIT REPORT
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Domain    : [domain]
Score     : XX/100    Status: PASS/FAIL/BLOCKED
Threshold : [blocking threshold]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Level 1 — Exists    : X/Y
Level 2 — Substantive: X/Y
Level 3 — Wired     : X/Y
Level 4 — Data Flows : X/Y

FINDINGS:
  • [finding 1] — [file:line] — [contract reference]
  • [finding 2] — [file:line] — [contract reference]

RECOMMENDED ACTIONS:
  1. [action]
  2. [action]

Post-audit

After the audit completes:

touch .sqwr-last-audit

This marks the audit as done for hook-audit-before-push.sh.

Reference

Audit weightings and sequencing: audits/AUDIT-INDEX.md

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free