Finalisation Coordinator — Testing & QA agent for Claude Code
Phase 3 INLINE orchestrator: syncs the branch, runs the verify-phase test gate, chatgpt-pr-review, doc-sync sweep, and local CI-parity, then labels, watches CI, and auto-merges.
How to install Finalisation Coordinator
Installs to ~/.claude/agents/michaelhazza-claude-code-framework-finalisation-coordinator.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/michaelhazza/claude-code-framework/HEAD/.claude/agents/finalisation-coordinator.md -o ~/.claude/agents/michaelhazza-claude-code-framework-finalisation-coordinator.md Restart Claude Code, or start a new session, for it to be picked up.
What Finalisation Coordinator does
name: finalisation-coordinator description: "Phase 3 INLINE orchestrator: syncs the branch, runs the verify-phase test gate, chatgpt-pr-review, doc-sync sweep, and local CI-parity, then labels, watches CI, and auto-merges. Operator types 'launch finalisation' after Phase 2 close; adopted inline, never dispatched as a subagent." tools: Read, Glob, Grep, Bash, Edit, Write, Agent, TodoWrite, TaskCreate, TaskList model: opus
**Project context (read first).** If `.claude/context/agent-contex
Alternatives in Testing & QA
- Perf Test Sync — Use this agent when the user needs to synchronize performance test cases between development (dev) and QA dire 14.5k ★
- Unit Executor — Implements exactly one unit of work from an inline spec and returns a structured JSON record 314 ★
- App Operator — 在已有 Marionette 兼容 MCP 时,只对通过静态审计的 ready UI 行为 Spec 执行运行态验证并写报告;不生成 Spec、不准备环境、不探索流程或修改代码 113 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
QA Plugin
QA agent for the career-engine plugin. Validates the repo and the built .plugin — mechanical battery + relatio
ChatGPT Spec Review
Coordinates ChatGPT spec review in a dedicated session (manual ChatGPT-web, automated OpenAI API, or parallel
Integration Test Runner
Multi-process integration testing specialist for C++20 HPC applications. Manages CTest labels, MPI-based tests
Leakage Reviewer
Skeptical data-leakage / look-ahead-bias reviewer for time-indexed data and ML pipelines (features, labels, ti
MCP Dogfooder
Drives the shipped MCP debugger tools as a real user would — launch, breakpoints, stepping, locals, object exp
Game QA
Game QA. Runs the autonomous self-verify loop (build → launch .exe → screenshot → read PNG → verdict). Catches
Related Skills
Cr Public
Babysit a PUBLIC propagation PR (default repo yotamleo/Himmel) to CR-clean + CI-green before the operator merg
Reduce Comments
Cut new code comments down to what earns its place — why over what, inline over doc blocks, standard labels.
Hef.Pr
Open or update the pull request for the current branch via the review-coordinator agent — never merges; --summ