Claude-code-agents full-audit
Run all 11 audit agents in parallel, then consolidate findings with fix-planner
install
source · Clone the upstream repo
git clone https://github.com/undeadlist/claude-code-agents
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/undeadlist/claude-code-agents "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/full-audit" ~/.claude/skills/undeadlist-claude-code-agents-full-audit && rm -rf "$T"
manifest:
skills/full-audit/SKILL.mdsource content
Full Audit Workflow
Run a comprehensive audit of the entire codebase. Use before major releases or as a weekly health check.
Phase 1: Parallel Audit
Spawn ALL of the following agents in parallel (single response with multiple Task calls):
| Agent | Output File | Focus |
|---|---|---|
| | Code quality |
| | Runtime bugs |
| | OWASP deep scan |
| | Documentation gaps |
| | Infrastructure config |
| | UI/UX and accessibility |
| | Database performance |
| | Performance issues |
| | Dependency health |
| | SEO optimization |
| | API validation |
Each agent targets the project's source code. Provide each with a prompt like:
Audit [target directory]. Save report to [output file].
Phase 2: Consolidation
After all auditors complete, spawn:
- Read allfix-planner
files and create.claude/audits/AUDIT_*.md
with prioritized action items.claude/audits/FIXES.md
Post-Audit Actions
- Review
- Prioritize based on your timelineFIXES.md - Run
- Implement P1 (critical) fixescode-fixer - Run
- Verify fixes worktest-runner - Re-audit affected areas if needed