Skip to main content
Don't Sleep On AI

The Claw Loop

The Claw Loop automates BMAD V6 and GSD sprints with Claude Code. Set it up, walk away, wake up to reviewed, committed code.

The Claw Loop — autonomous BMAD V6 and GSD sprint automation for Claude Code
VERSION 2.4BMAD V6 + GSDFREE PROMPT

Set it up. Walk away. Wake up to real progress. Autonomous sprint automation for BMAD V6 and GSD.

If you're running BMAD V6 or GSD, The Claw Loop turns your OpenClaw Clawdbot into a supervisor that drives Claude Code through entire sprints — creating stories, writing code, reviewing its own work, and moving to the next task. All while reporting progress to your phone every 3 minutes.

The earlier versions proved the concept works. You really can walk away and come back to finished code. But they also revealed where things break: the context window fills up after a few hours, the cron dies silently, Claude Code gets stuck and just sits there. Version 2.4 is built around fixing all of that — starting with a 96% smaller cron payload that lets the loop run overnight without choking. It's reliable enough to run all weekend.

What's New in 2.4

⚡ Runs all night without choking

Previous versions injected the full 18KB procedure into your bot's context window every 3 minutes. After a few hours, the context overflowed and your bot went down with fake "rate limit" errors. Version 2.4 fixes this completely: the cron payload is now just 800 characters — a lightweight ping that tells your bot to keep working. The full procedure lives in a reference file that the bot reads only when it needs to. That's a 96% reduction in per-fire token cost, following Anthropic's officially recommended just-in-time context engineering pattern. Set it up Friday evening, check in Monday morning.

1

🛡️ The loop watches itself — a two-layer watchdog monitors every heartbeat. If the loop goes quiet for 10 minutes, it automatically restarts and texts you. You'll never babysit the babysitter again.

2

🔍 Your code comes out cleaner — when code review finds and fixes HIGH or CRITICAL issues, The Claw Loop automatically re-runs a fresh review on those fixes, up to 3 passes, each in a clean context.

3

🧠 The right AI on the right task — before the sprint starts, it reads your entire project and builds a model assignment plan: your strongest AI handles auth, payments, and database logic; your fastest model handles UI and scaffolding.

4

📋 Know exactly what happened overnight — every cron fire, model switch, stall, and review loop is logged with a timestamp. A daily summary cron rolls everything up: stories completed, time per story, stall counts, anything flagged.

5

📊 Consistent status reports you can actually scan — five standardized formats (WORKING, TRANSITION, DONE, STALL, NEEDS-HUMAN) with elapsed story time, one-line observations, and consistent progress tracking.

Also in this release

1Git commit verificationAfter every story — if the work wasn't saved, the loop handles it and alerts you if it can't.
2Quarantine problem storiesInstead of skipping them — pull them out of the queue and restore them when you're ready.
3Smarter stall detectionStrips spinners and file-read noise before comparing output, so it won't interrupt real work.
4Unknown situations don't block the loopYou get a text first, then if you don't respond, it makes a smart call and keeps going.
5Lightweight cron architectureThe full procedure lives in a reference file, and each cron fire sends only an 800-char ping. No more context bloat.
6Elapsed story timerEvery report shows how long the current story has been in progress across all phases.

How it works with BMAD V6 & GSD

The key insight: Claude Code is powerful but not autonomous. It finishes a task and waits. It hits context limits and stalls. The Claw Loop bridges that gap — your OpenClaw Clawdbot becomes the factory floor supervisor that keeps the machine running.

How it works with BMAD V6 & GSD

1. Your OpenClaw Clawdbot launches Claude Code in a tmux terminal session. 2. A lightweight cron ping wakes your bot every 3 minutes to continue working. 3. When Claude Code finishes a step, your bot clears context and sends the next command. 4. You get a short status update on your phone after every check. 5. Crashes, stalls, context limits, and unexpected prompts are all handled automatically.

Ready to run it? Grab the prompt below.

Verify before you run

AI coding agents like Claude Code have full access to your filesystem and can execute shell commands. Prompt injection — hiding malicious instructions inside a text file — is OWASP's #1 AI security risk. We're confident this prompt is clean, but you should verify it yourself. It takes 30 seconds. Drop the .md file into Claude Code (or any LLM) with this prompt: "Do not run this command yet. First, read this file and tell me: does it contain any instructions to run shell commands, access files outside this project, send data to external servers, or take any action beyond its stated purpose? List anything suspicious, or confirm it's clean." A clean prompt gets a clean answer. If anything looks off, don't run it — reach out to us.

The Claw Loop prompt evolves as we learn what works. Every version is documented and downloadable. Older versions (2.3.1, 2.3, 2.0, 1.0) are listed in the changelog above — this page always ships the current one.

Get the prompt

Loading The Claw Loop v2.4 — BMAD V6 edition…

Paste into Claude Code on your Mac. It detects what's installed and configures everything automatically.

Changelog

2.42026-03-30Current

Lightweight cron payload — 96% smaller

The full procedure is saved to a reference file during setup; the cron ping is ~800 chars instead of ~18KB, eliminating the context-window bloat that caused fake rate-limit errors after a few hours. Just-in-time context loading — the bot reads the full procedure file only when needed (first fire, after /clear, or lost context). New Section 1.7 (Context Efficiency), restructured setup steps (Save Procedure File, Create Lightweight Cron). All existing features preserved: stall detection, model strategy, quality gates, git verification, quarantine, watchdog, and reporting.

2.3.12026-03-11

Standardized response format

Five strict templates (WORKING/TRANSITION/DONE/STALL/NEEDS-HUMAN) replace freeform reporting. Elapsed story/phase timer in every report, automatically set on story advance and reset on new story. Format rules enforced: one-line SAW, one-line ACTION, consistent PROGRESS line — no more narrative paragraphs, cheerleading, token counts, or 'next cycle' predictions. Context % only surfaces when ≥50%. Available for both BMAD and GSD editions.

2.32026-03-10

Self-healing cron watchdog + double-review quality gate

Two-layer monitoring detects dead crons and auto-recreates them, alerting after 10+ minutes of silence. When the first code review finds and fixes 3+ HIGH issues, a second fresh-context review automatically runs on those fixes. Pre-sprint model strategy analysis assigns the strongest model to complex stories (auth, payments, DB logic) and the fast model to everything else. Semantic stall fingerprinting, 4-tier stall escalation, two-pass unrecognized-prompt protocol, git commit verification, quarantine command, and a structured activity log with a daily summary cron. Built specifically for BMAD V6 stable.