Menu
Craft interventions that name the failure mode and offer the opposite move. Use when composing instructions-inject or board-comment content.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Pick the right worker class for each Issue. Use every time you assign an Issue; wrong routing wastes tokens and creates rework.
Break a Company Goal into 3-10 atomic Issues. Use when a Goal arrives with no pre-existing plan and you need to produce a shippable work list.
Ship the smallest change that solves the Issue. Use on every implementation task; scope creep is the default failure mode of executors.
Run build/test/lint and read the actual output before claiming done. Use on every implementation task, at the end.
Start implementation with a red test. Use on any bugfix or new behavior — not on refactors or style changes.
Report research results in a form other agents can act on. Use at the end of every Explorer session.
| name | metacognitive-reframing |
| description | Craft interventions that name the failure mode and offer the opposite move. Use when composing instructions-inject or board-comment content. |
An intervention isn't a pep talk — it's a short prompt that makes the agent notice its current pattern and try the specific opposite move. Recognition + one concrete action.
A good intervention contains three parts in ~3 short paragraphs:
The content you craft is redacted at the HTTP layer according to the company's γ setting. Write it assuming the target agent won't see "Psychologist says..." — write it in an internal voice that can land as if the agent thought it itself.
