Prose Orchestrator — Testing & QA agent for Claude Code
Runs one prose-test case end to end — builds the world, dispatches the walker, computes the delta, dispatches the asserter, reruns a failure from a fresh world to confirm it, destroys the world — and.
How to install Prose Orchestrator
Installs to ~/.claude/agents/leeovery-agentic-workflows-prose-orchestrator.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/leeovery/agentic-workflows/HEAD/.claude/agents/prose-orchestrator.md -o ~/.claude/agents/leeovery-agentic-workflows-prose-orchestrator.md Restart Claude Code, or start a new session, for it to be picked up.
What Prose Orchestrator does
name: prose-orchestrator description: Runs one prose-test case end to end — builds the world, dispatches the walker, computes the delta, dispatches the asserter, reruns a failure from a fresh world to confirm it, destroys the world — and returns just the verdict. Dispatched by the /prose-test skill, one per case. tools: Bash, Read, Agent model: sonnet
Prose Orchestrator
You run **one** prose-test case from end to end and return its verdict. Your caller gives you a single case id. Eve
Alternatives in Testing & QA
- Test Wiring Auditor — 変更差分に対してテスト網が追随しているかを fresh-context で監査する read-only auditor 3.1k ★
- Witness — Independently witness that an Allium loop's convergence claim is true and was reached honestly 474 ★
- Spec Compliance Judge — Use this agent when you need to determine whether a solution correctly implements a specific part of a specifi 173 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Prose Asserter
Judges a prose-test walk against the case's expected path and the code-computed world delta, returning a four-
Prose Walker
Executes workflow prose exactly as a live session would, against a disposable test world, and returns a transc
QA Walker
Use to drive the built explainer (repo-root index.html) end-to-end in a real Chromium browser via Playwright,
Test Orchestrator
Use when the user asks to test a change, verify a feature, or check whether something is ready to merge. Decid
Planner Agent
Planning worker for spec-driven development spawned by the speq-plan or speq-plan-pr orchestrator. Performs th
Claudehut Test Runner
Runs the test suite and reports real pass/fail counts and failure causes — the fresh test evidence Review reco
Related Skills
Invert
Run Munger/Jacobi Inversion analysis (Forward Case vs. Failure Recipe vs. Delta)
Human Copywrite
A Claude Agent Skill that humanizes AI-written marketing and long-form copy: landing pages, sales pages, e-boo
Use Case Create
Create a new world-class use case document