autoworker
An auto-loop workflow for Claude Code that breaks a task into subtasks, implements code, runs tests, and iterates through quality gates until the work is complete.

An auto-loop workflow for Claude Code that breaks a task into subtasks, implements code, runs tests, and iterates through quality gates until the work is complete.
Auto-loop execution workflow with quality gates. Use when starting any non-trivial implementation task. Provides automatic task…
Record progress to subtask: Phase completion (from autoworker:code) or test results (from autoworker:test). Auto-detects upstream…
Implement ONE pending Phase from subtask plan. Only write code, do not mark checkboxes or run tests. Called by…
Structured deep discussion for Plan Mode. Runs inside EnterPlanMode to ensure thorough questioning before writing a plan. Covers…
Read subtask.md checkbox state and route to next skill. The ONLY routing point in the execution loop. Called after…
Final quality gate before reporting task completion (Gate 3). Fills confidence assessment, runs supplementary verification for…
Create subtask document (first half): user confirmation, goals, assumptions. Auto-runs assumption verification experiments and…
Complete subtask verification plan: upstream traceability table + L1-L4 test plan + self-check. Call after…
Update subtask with fixes or new steps. Two trigger modes: (A) Auto-called by autoworker:gate-check on FAIL — reads FAIL info,…
Sync tracking documents based on current conversation results. Updates subtask, progress, findings, task_plan, project CLAUDE.md.…
Execute ONE test level (L1/L2/L3/L4) from subtask verification plan. Only run tests, do not record results. Called by…
Start the autoworker execution workflow for any non-trivial task.
Is this you? Claim your profilePut a plugin at the top of Plugins, from $9