メニュー
Use when choosing between cheap probes, worker runs, expensive ruler runs, or long keepalive waits.
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。
Use when preparing a repository, project kit, plugin, skillpack, or developer tool for public release or maintainer-ready public operations.
Use when improving a public README, repository homepage, docs landing page, or developer-facing first impression.
Use when routing well-specified implementation work from Fable to Codex or another side worker.
Use before delegating work from a Fable or premium-model orchestration session.
| name | run-economics |
| description | Use when choosing between cheap probes, worker runs, expensive ruler runs, or long keepalive waits. |
Match the instrument to the question.
Use cheap probes when the question is "does this mechanism fire?"
Examples:
Use premium runs when the question is "does this meet the bar?"
Examples:
For short waits, preserve the prompt cache with a sleep-tick if no inline work remains. For long waits, let the cache die once. Do not ping through multi-hour idle windows by default.
For scored or judged runs, record provider, model or lane, scenario, method, score, and proof boundary.
