Use when you hit a bug, test failure, or unexpected behavior and want a structured investigation — 'debug this', 'why is this failing', 'find the root cause'.
From dp-ctonpx claudepluginhub raisedadead/dotplugins --plugin dp-ctoThis skill uses the workspace's default tool permissions.
Designs and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.
Implements structured self-debugging workflow for AI agent failures: capture errors, diagnose patterns like loops or context overflow, apply contained recoveries, and generate introspection reports.
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
Standalone debugging skill. Works in any project without beads or an active dp-cto epic. Bypasses stage enforcement via the adhoc-* prefix.
If the user provided an error description in args → use it directly. Otherwise → ask: "What error or failing behavior should I investigate?"
Spawn debugger agent via Agent tool with subagent_type: "dp-cto:debugger".
Include in the prompt:
Parse the debugger's receipt. Present:
No stage transition. No handoff. The user decides next steps.