Working playbook preloaded into the researcher helper; the coach updates its Lessons after each round. Use only when acting as researcher or coaching it. NOT for general research tasks.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
You find facts and count things. You never change files outside your scratch dir. You run without the repos' instruction files, so the rules you need are here.
python3 pass over files, a read-only SQL
query. Stream large files line by line; never print a whole transcript or log.log, show, grep). Never commit, reset, checkout or stash.Numbers and tables first, then at most 5 lines of notes. Every number says where it came from (the command or query). Say what you could not check. No recommendations unless asked.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Admin debug system wiring for the floating AdminIndicator's live debug data and Copy Full Context. Use when adding debug visibility to a route or feature, wiring useDebugContext or the debug panel, capturing console errors, or enabling the copy-context workflow for a page.
The English summary is being prepared. Showing the original description.
Compact two-icon Copy / Copy-for-AI controls (components/agent-copy). Use when adding copy buttons to a row, card, list, or record; merging duplicate Copy/JSON/AI controls; continuing the copy rollout; or writing a Copy-for-AI payload. NOT for markdown content actions (use rich-document-actions).
The English summary is being prepared. Showing the original description.
Disclosing a surface's existing fixed AI jobs in the shell's top Agents menu. Use when a page, panel, overlay, or window already runs a mandate behind a button, assist, automatic action, or mode; when the agent-disclosure guard names a file; or during a surface check.
The English summary is being prepared. Showing the original description.
The method for getting a cheaper model to match an agent's big-model answers by fixing instructions, inputs and setup. Use when asked to move an agent to a smaller or cheaper model, prove one model beats another, or compare models on an agent's test cases.
The English summary is being prepared. Showing the original description.
The watch-fix-rerun method for making an existing platform agent or automated process efficient and correct: baseline its ledger, run one unit yourself, fix the class behind every wasted call, rerun, record. Use when asked to improve, optimize, watch, or 'make efficient' an agent, a sandbox session, a sync job, or any recurring automated process.
The English summary is being prepared. Showing the original description.
Redux state for agent execution and firing agent shortcuts. Use when editing features/agents/redux/, building agent UI, creating a conversation, touching assembleRequest or NDJSON stream state, wiring agent-state selectors, adding a per-conversation capability, or triggering a shortcut from a button, menu, or code (useShortcutTrigger, launchAgentExecution).
The English summary is being prepared. Showing the original description.