Tiny Spec Build Reviewer — Testing & QA agent for Claude Code
Independently reviews a single finished task — runs the project's real gate end-to-end and checks the code against the constitution and the task's acceptance.
How to install Tiny Spec Build Reviewer
Installs to ~/.claude/agents/grayma77er-tiny-spec-tiny-spec-build-reviewer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/GrayMa77er/tiny-spec/HEAD/agents/tiny-spec-build-reviewer.md -o ~/.claude/agents/grayma77er-tiny-spec-tiny-spec-build-reviewer.md Restart Claude Code, or start a new session, for it to be picked up.
What Tiny Spec Build Reviewer does
name: tiny-spec-build-reviewer description: Independently reviews a single finished task — runs the project's real gate end-to-end and checks the code against the constitution and the task's acceptance. Blind to how the code was written. Returns PASS/FAIL plus findings. Spawned (one per task) by tiny-spec-build. Does not fix code, plan, spawn agents, or invoke skills. tools: Read, Write, Edit, Bash, Grep, Glob
tiny-spec-build-reviewer
You independently review **one finished task** fr
Alternatives in Testing & QA
- Fable Verifier — Cold verifier for finished fable deliverables 837 ★
- Witness — Independently witness that an Allium loop's convergence claim is true and was reached honestly 474 ★
- Post Gate Agent — Review building phase implementation against plan requirements and test coverage 243 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Tiny Spec Build Executor
Implements a single task — writes/modifies code to satisfy one task, adhering to the project's constitution, a
Estimate Validator
Independently reviews a finished effort estimate against its spec, checking arithmetic, omissions and pricing.
Oracle Author
Authors the discriminating red-green test (the "oracle") for a high-blast-radius change FROM THE SPEC, blind t
QA Author
Blind QA-plan author. Spawned by /blueprint immediately after context.md is written — reads ONLY context.md an
G Forge Dev
Use proactively to run this repo's test suites and g-dev/ gate fixtures and return attested runner output. The
Loyal Evaluator
Spec-starved reconstruction of what a product actually does and what it seems to be for, run by /gate and /loy
Related Skills
QA Phase
Run QAPhase — the autonomous acceptance-and-ship QA gauntlet. Proves a finished story end-to-end (spec-gap/gri
Phase End
Run the phase-end ritual, gate checks, walkthrough generation, and reviewer handoff.
Specs Generation
Break down the brief into a sequenced plan of independently-deliverable tasks, written to tasks/specs.md follo