Project Automation Auditor — Testing & QA agent for Claude Code
Audits a project's automation and verification posture: test runner, formatter/linter PostToolUse hooks, PreToolUse dangerous-action blocks, verifier-agent separation, and whether registered project s.
How to install Project Automation Auditor
Installs to ~/.claude/agents/henry-1981-context-first-harness-project-automation-auditor.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/henry-1981/context-first-harness/HEAD/.claude/agents/project-automation-auditor.md -o ~/.claude/agents/henry-1981-context-first-harness-project-automation-auditor.md Restart Claude Code, or start a new session, for it to be picked up.
What Project Automation Auditor does
name: project-automation-auditor description: "Audits a project's automation and verification posture: test runner, formatter/linter PostToolUse hooks, PreToolUse dangerous-action blocks, verifier-agent separation, and whether registered project skills/hooks are actually invoked in recent sessions. Returns AUTOMATION_REPORT JSON." tools: Read, Grep, Glob, Bash
project-automation-au
Alternatives in Testing & QA
- Gitnexus Test CI Verifier — GitNexus test and CI reviewer 45.8k ★
- Pencil UI Designer — Use this agent when you need Pencil-based design workflows: atomic designer actions, MCP tools, and spec-drive 635 ★
- Omd Codex Image — Channel-aware image materializer 465 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Context First Auditor
Audits a context-first (non-dev) harness: documentation/wiki/rules-oriented repo. Replaces test-runner / forma
Motivation Agency Reviewer
One of book-forge's seven QA reviewers. Checks whether each character action traces to their Motivation Core a
Eval Auditor
Audits an evaluation setup (benchmark, A/B test, or model comparison) for methodology errors that would invali
Suite Auditor
Audits an automated test suite and scores it against a rubric. Finds sleeps, duplication, missing assertions,
Supply Chain Framework Auditor
Audits dependency CVEs, malicious or over-permissioned SDKs, build-pipeline leftovers (debug flags, test endpo
Ndv Signal
Metrics skeptic. Use when reviewing engineering KPIs, OKRs, sprint velocity, test coverage targets, DORA metri
Related Skills
Agent Manual
The manual for AI coding agent hooks, configs, PreToolUse/PostToolUse, MCP, and skills - covering Claude Code,
Claude Session Hooks Template
Template for AI agents to create Claude Code session hook plugins - includes SessionStart, UserPromptSubmit, S
Claudecode Linter
Standalone linter and formatter for Claude Code plugins and configuration files — 90 rules across 8 artifact t