메뉴
Review completed Codex work for checkpoint readiness, memory hygiene, and reusable sanitized learnings.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Improve, audit, simplify, rewrite, or migrate prompts, tool descriptions, agent instructions, and prompt stacks for GPT-5.6 Sol or the GPT-5.6 family. Use for outcome-first prompt design, autonomy boundaries, tool routing, PTC, grounding, verbosity, reasoning effort, and prompt evals.
Apply a deep, design-minded engineering workflow for complex work that needs careful planning, iteration, and simplification.
Use when preparing or running a Claude CLI agentic engineering review through claude -p for repository audits, architecture analysis, system design, security review, large refactors, specs, RFCs, or evidence-grounded long-form engineering analysis.
Use when preparing or running a ZCode GLM-5.2 agentic builder workflow through zcode --prompt for fast implementation, iterative code generation, focused fixes, and validation on an existing repository.
Apply adversarial opposite-analysis to plans, specs, architecture, code changes, and claims. Use when the user asks for adversarial review, opposing analysis, contrarian review, red-team reasoning, or Z.ai and MiniMax cross-checks through the Ralph MCP router.
Review and adjudicate Bugbot, Cursor, Seer, and similar automated PR feedback with local evidence before accepting, fixing, or dismissing findings.
| name | exit-review |
| description | Review completed Codex work for checkpoint readiness, memory hygiene, and reusable sanitized learnings. |
Close a task or migration phase with clear evidence, no leaked sensitive content, and useful sanitized memory.
Confirm that the scope matches the phase request and that the previous checkpoint requirement was respected. Check that changed files are limited to the intended surface, validations ran, risks are explicit, and PASS or FAIL is justified. No secrets, raw vault content, or RED material may be written.
Classify learnings before saving them. GREEN learnings are reusable and safe for global memory. YELLOW learnings are project-specific and sanitized. RED learnings are not saved.
Write only GREEN/YELLOW summaries to ~/.ralph-codex or the vault when useful.
The handoff should name changed files, validation evidence, decisions, unresolved risks, and next phase readiness.
Do not include raw command dumps unless the exact output is necessary.
