Sdlc QA — Testing & QA agent for Claude Code
Audits the Coder squad's tests for TDD compliance and intent-encoding, then runs the story's quality gates.
How to install Sdlc QA
Installs to ~/.claude/agents/rafatchanz-sdlc-orchestrator-sdlc-qa.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/RafaTchanz/sdlc-orchestrator/HEAD/agents/sdlc-qa.md -o ~/.claude/agents/rafatchanz-sdlc-orchestrator-sdlc-qa.md Restart Claude Code, or start a new session, for it to be picked up.
What Sdlc QA does
name: sdlc-qa description: Audits the Coder squad's tests for TDD compliance and intent-encoding, then runs the story's quality gates. Never authors primary tests. Dispatched only by the /sdlc, /sdlc-bug-fix, or /sdlc-task skill via Agent(subagent_type: "sdlc-qa") — never invoked directly. model: sonnet tools: Read, Bash, Grep, Glob, Write
Demolidor — QA
You are Daredevil: heightened senses catch what a casual pass would miss. You don't touch the code you're auditing — you report exa
Alternatives in Testing & QA
- Lens Reviewer — Use this agent for severity-rated code review with 2-stage protocol (spec compliance first, then code quality) 523 ★
- Writ Reviewer — Reviews an implementation diff in two passes (spec-compliance first, then code quality) 187 ★
- Sdlc QA Reviewer — QA review for production readiness 58 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Uxaudit Scout
Project Scout for the uxaudit pipeline. Synthesizes an evidence-based hypothesis about a project's intent, pri
Ticket Writer
Cuts an approved feature spec into vertical-slice tickets with an honest dependency graph and story coverage.
Sdlc Bug Investigator
Diagnoses the root cause of a reported bug and writes exactly one failing RED test that reproduces it — never
Sdlc Intake Agent
Sub-agent dispatched by /rem-sdlc:cycle for the intake phase. Reads ticket + spec, decomposes ACs into testabl
Print QA
Gates a 3MF before anything prints, with PASS/FAIL per item of templates\preprint-checklist.md, the evidence q
Gantry Verifier
Runs the readiness gate. Use to execute the project's lint/test/build from its own .claude/gates.sh, the check
Related Skills
Audit Pipelines
TDD-validated audit-grade decision pipelines - canonical encoding (RFC 8785 JCS), append-only decision logs, f
Sdlc Kit
Harness-neutral AI-native SDLC framework — intent grilling, sha256 tamper-evident approval gates, fresh-contex
AI Native Sdlc Skills
Unofficial Claude Code skills adapted from Anthropic's The AI-Native SDLC playbook — the committed-artifact ch