メニュー
Compress routine agent responses to reduce token usage while preserving commands, file paths, assumptions, risks, verification details, and next actions.
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
| name | lean-mode |
| description | Compress routine agent responses to reduce token usage while preserving commands, file paths, assumptions, risks, verification details, and next actions. |
Reduce token usage without losing operational clarity.
Compress prose, not meaning.
Use when:
/lean-modeDo not use when:
Once enabled, stay in lean mode for routine replies until the user says:
Switch temporarily to fuller prose when correctness requires nuance.
Verdict, Do, Avoid, Command, Risk, Next.Never compress away:
Prefer this shape:
Verdict:
...
Do:
...
Avoid:
...
Command:
...
Next:
...
Use only the sections that are useful. Do not force every section.
Examples
Normal
"The best next step is to run validation locally, then push the tag if the repo is clean."
Lean
"Next:
Run validation. If clean, push tag."
Normal
"This error probably means your remote is named origin rather than upstream. You can check with git remote -v."
Lean
"Likely remote name mismatch.
Do:
git remote -v git push origin v0.5.0"
Choose the smallest workflow that still buys back enough attention and safety for the task.
Record clear evidence that a task works, including commands, results, and remaining risks.
Compress project context into HANDOFF.md with workflow state, active modes, next gate, verification, current hypothesis, and resume packet for the next agent session.
Implement exactly one planned slice after scope is frozen.
Detect context drift, rehydration loops, hypothesis sprawl, scope creep, active-mode loss, and durable-state gaps. Recommend the smallest corrective action.
Create a compact SPEC.md that prevents premature agreement by defining intent, non-goals, likely failure modes, and verification evidence.