Loop/scheduleAutomationmedium riskadvancedsafety C · 55

Drive work units unattended

Run claimed work units in order without prompts, deferring unclaimed tasks until the next cycle.

prompt
→ Claude
/goal /drive auto ok waits on. It asks one thing, and only when you are there to answer it : bare /drive is the attended form, which — when more than one unit is claimable or resumable — shows you the partition and asks once which units to take, drives them in the order you picked, and reports the rest as deferred (still claimable, so the run ends pending ). /drive auto is the unattended form, prompt-free at every step, and it is what the hourly routine and any /goal /drive auto ok loop invoke by name ( docs/drive-loop-runbook.md ); /drive night is a synonym of it. Which form runs follows from how you invoked it, never from a guess about whether anyone is watching. Nothing else is ever asked: not the partition, not each ticket. Approval is not a per-ticket prompt: it was given where the work was decided — a human merged the pull request that published the mission or ticket, and the merge policy recorded on it at creation says whether its completed units may merge unattended. Work is coordinated by the claim protocol — every runner reads the claims in flight from the unmerged remote branches, so two runners (or two machines) never pick the same work. There is no lock file and no server; the repository itself is the coordination medium |
claude-code

Source: qmu

More automation loops

Run autonomous audit, resolve findings

Loop/ralphnew

Spawn QA agents iteratively to audit and fix findings until complete or max iterations reached.

prompt
→ Claude
--- description: Autonomous audit loop — router-managed iteration or standalone via Stop hook disable-model-invocation: true --- Run the ralph-loop audit. There are two modes: ## Mode 1: Router-managed iteration (multi-agent, default) The router manages the iteration loop by spawning and re-spawning subagents: 1. Read .claude/ralph/PROMPT.md (in the parent project C:\dev\projects ) for the audit instructions 2. Create a task for the audit 3. Spawn a QA agent to execute the audit pass 4. When the agent completes, read the audit state file ( agent-studio/.claude/context/runtime/ralph-audit-state.md ) 5. If open findings remain (agent output contains RALPH ITERATION COMPLETE ), spawn another QA agent iteration 6. Repeat until all findings are resolved ( RALPH AUDIT COMPLETE NO FINDINGS ) or max iterations (25) reached 7. Report final results The router remains free and never gets trapped. No stop hook is involved. ## Mode 2: Standalone Stop hook loop (single-session) For standalone use outside the multi-agent framework, launch via the shell scripts: bash # Unix/macOS .claude/ralph/ralph-audit.sh # Windows .claude\ralph\ralph-audit.bat These scripts set RALPH ACTI
automationmedium riskclaude-code

Implement a spec end-to-end

Loop/ralphnew

Run an autonomous agent loop to implement a complete spec file, iterating until all requirements are met and marked DONE.

prompt
→ Claude
--- description: Run the Ralph Wiggum loop for a spec (Claude Code) --- Use this command to run an autonomous Ralph loop for a spec: /ralph-loop:ralph-loop "Implement spec {spec-name} from specs/{spec-name}/spec.md. Complete ALL Completion Signal requirements. Output <promise>DONE</promise> when complete." --completion-promise "DONE" --max-iterations 30
automationmedium riskclaude-code

Process files to Done folder

Loop/ralph

Move all files from /Needs Action to /Done folder, stopping when all files are processed.

prompt
→ Claude
/ralph-loop "Process all files in /Needs Action, move to /Done when complete" --completion-promise "TASK COMPLETE" --max-iterations 10
automationmedium riskclaude-code