메뉴
Run session-start, active-session, and session-end memory handling for Codex-native Ralph workflows.
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 | memory-session |
| description | Run session-start, active-session, and session-end memory handling for Codex-native Ralph workflows. |
Maintain short-lived and durable memory for Codex sessions without depending on Claude-specific runtime primitives.
At session start, read the relevant repo AGENTS.md, check the active migration checkpoint, load only the memory needed for the task, and confirm the sensitivity boundary before external MCP use.
During work, keep a compact ledger of decisions, commands, validations, and risks. Store transient notes under ~/.ralph-codex when needed. Use Codex subagents only for independent sanitized work. Treat external model output as advisory until Codex verifies it locally.
Write a short sanitized handoff when the work produces durable knowledge:
The handoff should cover task scope, changed files, validation evidence, checkpoint status, risks, follow-ups, and content sensitivity. Keep it short enough for the next session to use quickly.
Do not save RED content. Do not copy raw logs when a summary is enough.
Memory entries should be factual, short, and useful for the next Codex session.
