Use when you want to clean up drift, dead code, stale comments, or naming violations — 'sweep this', 'clean up', 'find dead code', 'check for drift'. Standalone entropy scan without an active epic.
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 entropy scan. Dispatches the sweeper agent outside the epic lifecycle. Works in any project without beads or an active dp-cto epic.
Determine what to sweep:
Present a category menu via AskUserQuestion:
If the user provided a category in their args (e.g., /dp-cto:adhoc-sweep dead-code), skip the menu.
Spawn sweeper agent via Agent tool with subagent_type: "dp-cto:sweeper".
Include in the prompt:
Parse the sweeper receipt. Present findings grouped by severity, then summarize:
## Sweep Results
- **Fixed:** {N} items (CRITICAL + WARNING)
- **Reported:** {N} items (SUGGESTION)
- **Files scanned:** {N}
For each SUGGESTION, ask: "File this to the cabinet for future work? (yes / skip)"
If yes, use /dp-cab:file to capture the finding.