Cto Self Eval — Testing & QA agent for Claude Code
CTO-grade codebase self-evaluation.
How to install Cto Self Eval
Installs to ~/.claude/agents/metazen11-autonomous-agents-cto-self-eval.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/metazen11/autonomous-agents/HEAD/agents/cto-self-eval.md -o ~/.claude/agents/metazen11-autonomous-agents-cto-self-eval.md Restart Claude Code, or start a new session, for it to be picked up.
What Cto Self Eval does
name: cto-self-eval description: "CTO-grade codebase self-evaluation. Measures code health, dead code, debt density, test meaningfulness, and overall engineering maturity. Produces a numeric scorecard with trend tracking."
CTO Self-Evaluation Agent
Role
You are the CTO's inner voice — the one that asks hard questions before the board does. You evaluate the codebase the way a technical due diligence firm would: objectively, with evidence, no flattery.
Your job is not to find bugs
Alternatives in Testing & QA
- Post Gate Agent — Review building phase implementation against plan requirements and test coverage 243 ★
- Test Refactor Specialist.Agent — Improves test code quality and maintainability 225 ★
- Code Executor — Transcribes code or generated output from a complete, transcription-grade spec and verifies its own build 76 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Cto Test Quality
CTO-grade test quality review. Evaluates whether tests catch real bugs or just make CI green. Scores test mean
04 Test Reporter.Agent
QA metrics and reporting specialist. Transforms raw test execution results into stakeholder-ready reports: pas
Continuity Supervisor
Cinema Studio continuity supervisor and QA scorer. Keeps the continuity ledger, shot ID tracking, the realism
Fec Refactor Cleaner
Front-end Dead Code & Technical Debt Cleanup Subagent: Identifies unused components, exports, styles, routes,
Edge Case Planner
Designs boundary value and equivalence partitioning test cases (TC-EDGE-NNN) for numeric limits, lengths, quan
QA Richness
Editorial-density and motion-richness QA gate. Verifies type contrast, accent scarcity, chrome present, not-fl
Related Skills
Vibe Explain
Cognitive debt map for AI-generated code. Surfaces opaque blocks you don't fully own or understand, generates
Audit Report
Aggregate audit checkpoints into the final report — executive summary, Scope Coverage, findings by severity, m
Audit Ur Harness
An Agent Skill that audits a project's AI harness — guardrails, memory, verification, observability, tool desi