一键导入
finalize
End-of-session COMP update — record decisions, progress, and state changes
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
End-of-session COMP update — record decisions, progress, and state changes
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | finalize |
| description | End-of-session COMP update — record decisions, progress, and state changes |
| user-invocable | true |
| disable-model-invocation | false |
| argument-hint | ["project path or name"] |
Update the COMP files for the current project to capture this session's work.
If $ARGUMENTS specifies a project, use that directory. Otherwise, infer from the current working directory and conversation context. If unclear, ask.
Review the conversation to identify:
Refresh the ## Current State section at the top of PLAN.md:
Also update the rest of PLAN.md:
Add or update entries for:
Do NOT duplicate information already in CLAUDE.md. MEMORY.md is for accumulated knowledge, not permanent reference.
Only if:
Only if:
Show the user a brief summary of what was updated:
Generate a wide field of ideas, then pressure-test them. Five generators diverge, two challengers prune the weak ones, three synthesizers rank what survives.
Three-agent adversarial bug finder. Hunter overclaims every issue it can find, Skeptic disproves what it can, Referee arbitrates what survives. Scoring incentives force each role to behave honestly.
Dialectic process for reviewing, brainstorming, comparing tradeoffs, or stress-testing plans. Configurable modes, agent counts, and expert lenses.
Execute a pre-defined plan using implementation agents (no design changes)
Capture structured learnings (gotcha, pattern, decision, bug-fix) as JSONL per project. Cross-project searchable.
Assume the plan failed — then explain why. Three pessimists write failure narratives, two optimists rebut, a risk assessor weighs which failure modes are real.