Use when a plan is ready and you want to execute it — 'run the plan', 'start building', 'dispatch the tasks'.
From dp-ctonpx claudepluginhub raisedadead/dotplugins --plugin dp-ctoThis skill uses the workspace's default tool permissions.
references/collaborative-dispatch.mdreferences/iterative-dispatch.mdreferences/run-default.mdreferences/run-loop.mdreferences/standard-dispatch-protocol.mdreferences/validator-prompt-template.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 and ${CLAUDE_PLUGIN_ROOT}/shared/dispatch-protocol.md before proceeding.
Before proceeding, detect the current state:
Check for active loop sessions:
ls .claude/ralph/*.md 2>/dev/null
Check beads availability:
bash -c 'source ${CLAUDE_PLUGIN_ROOT}/lib/dp-beads.sh && dp_beads_available && echo ok'
If beads is NOT available, STOP. Report: "Beads not available. Run /dp-cto:plan first to initialize and create a plan."
Check dp-cto stage:
bash -c 'source ${CLAUDE_PLUGIN_ROOT}/lib/dp-beads.sh && dp_beads_active_epic_and_stage'
Returns stage\tepic_id. If it fails or returns empty, treat as idle.
Route based on context:
| Condition | Action |
|---|---|
Running loop exists (.claude/ralph/*.md with status: running) | Present menu via AskUserQuestion: Continue running / Cancel loop / Start new dispatch |
No loop, stage is planned | Start default task-by-task dispatch |
Stage is idle | Report: "No planned work. Run /dp-cto:plan first." and STOP |
| Args are non-empty (internal orchestrator hint) | Use args as mode: loop → loop mode, stop → cancel mode |
Task-by-task dispatch. Read the full execution protocol from ${CLAUDE_SKILL_DIR}/references/run-default.md and follow it.
Iterative autonomous execution. Read the full loop protocol from ${CLAUDE_SKILL_DIR}/references/run-loop.md and follow it.
Pass remaining args as the loop's PROMPT, max-iterations, completion-promise, and quality-gate parameters.
Read each .claude/ralph/*.md file, extract session_id, status, current_iteration, max_iterations from YAML frontmatter.
status is NOT running.If no running sessions: say "No active loop sessions found." and STOP.
On confirmation, update the state file's YAML frontmatter:
status: cancelledcompleted_at: to current ISO timestampDo NOT delete state files. They are permanent records.
status: cancelled in a loop state file