Evolve Behavior Baseline — Testing & QA agent for Claude Code
Behavior baseline agent for the Evolve Loop (Evaluate archetype).
How to install Evolve Behavior Baseline
Installs to ~/.claude/agents/mickeyyaya-evolve-loop-evolve-behavior-baseline.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/mickeyyaya/evolve-loop/HEAD/agents/evolve-behavior-baseline.md -o ~/.claude/agents/mickeyyaya-evolve-loop-evolve-behavior-baseline.md Restart Claude Code, or start a new session, for it to be picked up.
What Evolve Behavior Baseline does
name: evolve-behavior-baseline description: Behavior baseline agent for the Evolve Loop (Evaluate archetype). The advisor INSERTS this phase on refactor cycles before build (after TDD) to record a golden master of observable behavior and test outputs. model: tier-2 capabilities: [file-read, shell, search] tools: ["Read", "Grep", "Glob", "Bash", "Write"] tools-gemini: ["ReadFile", "SearchCode", "SearchFiles", "RunShell"] tools-generic: ["read_file", "search_code", "search_files", "run_shell"]
Alternatives in Testing & QA
- Claude Code Flow — by ruvnet - This mode serves as a code-first orchestration layer, enabling Claude to write, edit, test, and op 22.2k ★
- Test Fix Loop Agent — Автоматическое тестирование REST API в цикле с исправлением ошибок 571 ★
- Witness — Independently witness that an Allium loop's convergence claim is true and was reached honestly 474 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Evolve Bug Reproduction
Bug reproduction agent for the Evolve Loop (Evaluate archetype). The advisor INSERTS this phase on bugfix cycl
Forge Visual Verifier
Perceptual gate for spec [visual] acceptance criteria. Drives Playwright MCP (navigate + take_screenshot + eva
Evolve Build Planner
Build-planning agent for the Evolve Loop. Externalizes Builder's internal chain-of-thought design step into an
Eval Author
Authoring role for the D365FO agent eval loop catalog. Drafts a new eval/cases/ .json spec (valid against eval
QA Fixer
Bounded test-fix loop agent for beast. Diagnoses test failures and applies targeted fixes, max 5 cycles.
Engine QA Review Technical Integrity
After a change you've asked for is built, checks whether the software underneath is healthy — well-built, perf
Related Skills
Cmd Refactor
Refactor phase (ACT loop): analyze, plan, baseline, execute, verify, and sync a behavior-preserving restructur
Test Driven Development.SKILL
Enforces TDD discipline with RED-GREEN-REFACTOR cycle. Use when writing new features, fixing bugs, or refactor
Prompt Optimize
One-shot prompt rewrite — diagnose a rough draft, steer you to the right workflow archetype (linear, TDD, suba