Stamity Test Runner — Testing & QA agent for Claude Code
Executes the full verification gate set and returns gate-by-gate structured results with verbatim failure excerpts; never fixes.
How to install Stamity Test Runner
Installs to ~/.claude/agents/zomarit-stamity-stamity-test-runner.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/zomarit/stamity/HEAD/.claude/agents/stamity-test-runner.md -o ~/.claude/agents/zomarit-stamity-stamity-test-runner.md Restart Claude Code, or start a new session, for it to be picked up.
What Stamity Test Runner does
name: stamity-test-runner description: "Executes the full verification gate set and returns gate-by-gate structured results with verbatim failure excerpts; never fixes." tools: Read, Grep, Glob, Skill, Bash, PowerShell model: "haiku" effort: "low"
test-runner
Runs the repository's verification gates and reports exactly what they said. Report only: it applies no edit, proposes no patch, and re-runs no gate with a narrowed selector to turn it green. Its whole product is evidence anothe
Alternatives in Testing & QA
- Bowser QA Agent — UI validation agent that executes user stories against web apps and reports pass/fail results with screenshots 222 ★
- Eval Improver — Improver role of the D365FO agent eval loop 136 ★
- Confirm Reporter — Confirmation phase V6 reporting agent that aggregates all confirmation results from poc-executor and test-mapp 125 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
QA Runner
Executes one or more structured QA tests (from qa/tests/structured/.yaml) in order against a specified iOS sim
M Code Test Runner
Runs focused verification in an isolated context and returns only concise results. Use when test/build/lint ou
Browser Verification Agent
Use this agent to perform single UI verification tests via Playwright MCP. This agent executes one test at a t
Stamity Implementer
Builds one planned unit — code plus the tests that prove it — inside the unit's file set, runs the local gates
Verify Lane
Runs a lane worktree's full test suite and all three quality gates, then reports the raw results verbatim. Use
Unity Test Runner
Writes EditMode and PlayMode tests, executes them via MCP run_tests, reports results. Knows Unity testing fram
Related Skills
Fact Verify
AI 조사 결과의 출처를 믿기 전에 검증하는 Claude Code 스킬 — 주장–근거 원장으로 발췌를 원문과 기계 대조, 4-Tier·재인용 체인·URL/DOI 실존 확인, 한국 학술DB(KCI·R
Claude n8n Bridge
Self-hosted n8n in Docker wired to Claude Code: n8n owns schedules and webhooks, a host-side runner executes o
Adversarial Audit Engine
Cross-model audit engine for documents and technical artifacts: hallucination gate on verbatim quotes, claim v