メニュー
Four-role sequential pipeline for complex, high-risk changes. Scout surveys the codebase, Coder implements with TDD, Analyst finds problems, Verifier gates the merge. Use for large refactors, architectural shifts, and interdependent multi-phase work.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Multi-hypothesis research campaign protocol. Use for open-ended optimization goals ("make X faster", "improve the metric") where several candidate ideas compete for a limited budget. Triages ideas cheaply, confirms survivors with full preregistered experiments, and keeps a committed ledger so dead ideas stay dead.
Controlled benchmark experiment protocol for solver, performance, routing, and optimization work. Use when testing a hypothesis against metrics, comparing implementations, or deciding whether to promote or abandon a benchmark-driven change.
Coordination-only protocol. You dispatch subagents, you do not execute code. Restricts tools to Read, Write (prompts/ and notes- only), Agent, Glob, Grep. Use when orchestrating multi-agent work.
Background knowledge for writing and launching subagent prompts. Covers prompt file conventions, worker identity declarations, batch dispatch patterns, and parallel swarm safety. Auto-invocable when dispatching agents.
Deletion-first fixed-point protocol for refactors, cleanup, migrations, and architectural convergence. Use when replacing old surfaces, removing helper debt, shrinking code, moving ownership boundaries, or auditing every symbol in a slice.
Read-only design review against project principles. Checks whether a design or implementation aligns with or violates the project's stated principles. Does not check code quality, bugs, tests, style, or performance — only directional alignment.
| name | gauntlet |
| description | Four-role sequential pipeline for complex, high-risk changes. Scout surveys the codebase, Coder implements with TDD, Analyst finds problems, Verifier gates the merge. Use for large refactors, architectural shifts, and interdependent multi-phase work. |
| disable-model-invocation | false |
Use when: complex, multi-phase, interdependent work where each phase builds on the previous. High-risk changes. Large refactors. Architectural shifts.
Do NOT use for: simple fixes, independent parallel tasks, straightforward test additions.
Scout -> Coder -> Analyst -> Verifier
Each role is a real dispatchable agent type shipped by this plugin — dispatch with subagent_type: scout, coder, analyst, or verifier, not just a prose instruction. Each is tool-scoped (scout/analyst/verifier have no Edit; coder has Edit + Write) and writes its report to reports/.
| Role | subagent_type | Job | Key instruction |
|---|---|---|---|
| Scout | scout | Survey codebase, find patterns | "Do NOT implement" |
| Coder | coder | Implement with TDD | "RED -> GREEN -> REFACTOR. All three." |
| Analyst | analyst | Find problems | "Your job is to find problems, not approve" |
| Verifier | verifier | Final gate | "Default is NO-MERGE. Code must earn it." |
Must do full TDD:
Cannot deviate from plan:
Include this in EVERY coder prompt:
## HARD CONSTRAINT: No Deviation
You implement the plan exactly as specified. You do not have authority to change the architecture.
If you believe the plan is wrong:
1. STOP immediately
2. Write your objection to reports/{task}-coder.md
3. Exit without implementing anything
You are NOT authorized to:
- Choose a "more pragmatic" approach
- Implement a partial solution
- Rationalize why the plan should be different
Implement the plan or report why you cannot. There is no third option.
Foreman only reads verifier verdict. Don't read scout/analyst reports yourself.