Use when encountering a bug, error, or failing test that needs structured investigation — 'this is broken', 'why does this fail', 'trace this error'. Enforces diagnosis before any fix attempt.
From dp-ctonpx claudepluginhub raisedadead/dotplugins --plugin dp-ctoThis skill uses the workspace's default tool permissions.
references/anti-rationalization.mdreferences/no-root-cause-protocol.mdreferences/quick-reference.mdreferences/red-flags.mdreferences/user-signals.mdDesigns 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.
Read ${CLAUDE_PLUGIN_ROOT}/shared/cto-boundaries.md
NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST
If you have not completed the investigation phase, you are not allowed to propose a fix. No exceptions.
Collect from the user:
If the user's description is vague, ask clarifying questions before dispatch. One question per message.
Dispatch debugger via the Agent tool with subagent_type: "dp-cto:debugger".
The agent prompt must include:
The debugger agent runs the 4-phase root cause investigation protocol (reproduce, analyze, hypothesize, report). It is read-only — it cannot modify code.
On agent completion, extract the structured receipt from <!-- RECEIPT:START/END --> markers. Validate:
root_cause — file:line with explanation (not vague)evidence — commands run and their outputsuggested_fix — concrete change descriptionconfidence — high, medium, or lowIf the receipt is missing or incomplete, report the gap. Do not fabricate findings.
Present the debugger's findings to the user with root cause, evidence, and suggested fix. Then offer next steps:
/dp-cto:run) with the suggested fix and file scopeRead ${CLAUDE_SKILL_DIR}/references/red-flags.md before proceeding.
Read ${CLAUDE_SKILL_DIR}/references/user-signals.md before proceeding.
Read ${CLAUDE_SKILL_DIR}/references/anti-rationalization.md before proceeding.
Read ${CLAUDE_SKILL_DIR}/references/quick-reference.md before proceeding.
Read ${CLAUDE_SKILL_DIR}/references/no-root-cause-protocol.md before proceeding.