Audit Tests — Security skill for Claude Code
Audit unit and integration test coverage, quality, and CI performance across all packages and apps.
How to install Audit Tests
Installs to ~/.claude/skills/macanderson-agent-harness-audit-tests/SKILL.md
mkdir -p ~/.claude/skills/macanderson-agent-harness-audit-tests && curl -fsSL https://raw.githubusercontent.com/macanderson/agent-harness/HEAD/commands/audit-tests.md -o ~/.claude/skills/macanderson-agent-harness-audit-tests/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Audit Tests does
description: Audit unit and integration test coverage, quality, and CI performance across all packages and apps. Outputs a standalone HTML report with per-package scores and a fix plan. allowed-tools: Bash, Read, Grep, Glob, Agent, TodoWrite, ToolSearch, TaskCreate, TaskGet, TaskList, TaskOutput, TaskStop, TaskUpdate
/audit-tests
Audit the unit and integration test suite across the full monorepo. Work autonomously top to bottom.
Phase 0 — Load context
- Read
CLAUDE.md, `AGENTS
Alternatives in Security
- Skill Coverage Audit — Trace codepaths in diffs, map against tests, auto-generate missing coverage — use before shipping PRs 2.8k ★
- Review Artifact — Creates one polished, self-contained HTML artifact from review findings, audit notes, PR feedback, code review 652 ★
- Data Viz Audit — Audit a data visualization for chart type selection, accessible color palette, annotations, and anti-patterns 309 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Audit E2e
Audit end-to-end test coverage of critical Playwright paths. Identifies missing flows, flaky tests, slow suite
API Test Suite
Add unit/integration/security tests to a FixIt API module via questionnaire-driven scoping and agent dispatch
Horde Test Skill
Execute comprehensive testing plans using horde-swarm to dispatch parallel test agents across multiple test ca
Review Test Quality
Audit test suite quality: coverage gaps, weak assertions, missing negative cases, over-mocking, and tests that
Project Init Skill
A Claude Code skill that runs a 3-round project kickoff interview before writing any code — outputs full archi
Audit Soc2
Audit SOC 2 Type II readiness across the codebase. Checks access controls, audit logging, secrets management,
Related Agents
Profile Synthesizer
Synthesizes voice profiles from self-report scores and computational writing analysis. Merges dual outputs usi
Kernel Testing Critic
Specialist critic for linux-kernel-dev answers · scores ONLY testing — does the answer come with correct, well
Report Generator
Assembles the workspace's 01–12 outputs into the final deliverables (4 in pilot scope, 5 in full — sector_them