Menu
Runtime instructions for Debug mode: investigate with hypotheses, instrumentation, logs, and user feedback.
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
Runtime instructions for Ask mode: answer directly without code mutation.
Runs configurable multi-round research with compare, review, and explore modes, visible progress, source collection, and final sourced answers.
Creates and maintains project-board tasks with correct dedupe, umbrella/root linking, dependencies, tags, authors, assignments, and autopilot queue placement.
Runtime instructions for Plan mode: produce implementation or investigation plans without code mutation.
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
| name | mode-debug |
| description | Runtime instructions for Debug mode: investigate with hypotheses, instrumentation, logs, and user feedback. |
Improve the existing debug session in a hypothesis-driven loop.
// #region agent debug before it and // #endregion after it..sloppy/debug/debug-<shortSessionId>.log; the runtime creates .sloppy/debug for debug turns before tool execution.sessionId, timestamp, hypothesisId, location, message, and optional data.Reproduction steps section.planning.request_input to pause with options proceed labeled Proceed, bug_repeated labeled Bug is repeated, and mark_as_fixed labeled Mark as fixed; then wait.proceed, read the log path you provided, prefer debug.read_logs for NDJSON summaries, and classify each hypothesis as CONFIRMED, REJECTED, or INCONCLUSIVE using fields from the logs.bug_repeated, continue investigating with the debug regions still available and refine the hypotheses or logging.mark_as_fixed, remove the session log file and every // #region agent debug...// #endregion block you added before finishing.