Landed from X, the showcase, or a friend's README? This is the shortest path from zero to a running loop.
Week one rule: report only. No auto-fix, no auto-merge. Read what the loop writes before you let it act.
Not sure which loop? Use the interactive pattern picker on the showcase — it recommends a pattern, scaffold command, first /loop line, and a token estimate.
Or start with Daily Triage if you just want to learn loop discipline with low risk.
Run this in the root of any git project (no clone required):
npx @cobusgreyling/loop-init . --pattern daily-triage --tool grokSwap --tool grok for claude or codex if needed. Swap --pattern for any pattern from patterns/registry.yaml.
loop-init copies the starter kit, creates STATE.md, LOOP.md, loop-budget.md, and loop-run-log.md, then prints your first command.
npx @cobusgreyling/loop-cost --pattern daily-triage --level L1 --cadence 1dAdjust --pattern, --level (L1 → L2 → L3), and --cadence to match what you plan to run. High-frequency loops (CI Sweeper at 5m) can burn tokens fast — slow the cadence or require early-exit triage first.
npx @cobusgreyling/loop-audit . --suggestScores 0–100 with concrete next steps. Re-run after each improvement. Paste a badge when you're proud of the score:
npx @cobusgreyling/loop-audit . --badge/loop 1d Run loop-triage. Update STATE.md. No auto-fix in week one./loop 1d Run $loop-triage. Read STATE.md. Merge findings into High Priority and Watch List. Update Last run. Do not edit code.Use the first-run command printed by loop-init (pattern-specific). Week one: triage and state updates only.
No loop-init --tool openclaw yet — copy skills/loop-triage/SKILL.md and STATE.md, then create an isolated cron job. See examples/openclaw/daily-triage.md.
No loop-init --tool cursor yet — copy skills and state from any starter, then map scheduling to editor Automations or Workflows. See the Cursor & Windsurf appendix in the primitives matrix.
Workflow examples under examples/github-actions/ are schema-complete; you wire the agent invocation (Codex API, repository_dispatch, etc.). Start with report-only outputs to a state file or issue comment.
Open STATE.md. Did the loop capture real priorities? Edit anything wrong — you're still the engineer.
Commit the scaffold + first run update so loop-audit sees activity on the next audit.
| When | Do this |
|---|---|
| End of week one | Re-run loop-audit . --suggest — aim for L1 (score ~40+) |
| Week two | Add a verifier skill; try one assisted fix in a worktree (L2) |
| Before unattended (L3) | loop-budget.md + loop-run-log.md filled, human gates in LOOP.md, proven runs |
| Unsure which pattern | pattern-picker.md · loop-design-checklist.md |
| Something broke | failure-modes.md · stories/ |
# Scaffold
npx @cobusgreyling/loop-init . --pattern daily-triage --tool grok
# Cost check
npx @cobusgreyling/loop-cost --pattern daily-triage --level L1 --cadence 1d
# Audit + suggestions
npx @cobusgreyling/loop-audit . --suggest
# Optional badge for your README
npx @cobusgreyling/loop-audit . --badge- Loop Engineering essay — concept and primitives
- Primitives matrix — Grok vs Claude vs Codex vs OpenClaw vs Cursor
- Operating loops — when to kill a loop
Questions? GitHub Discussions · Share your setup via Add Adopter