> **Stop prompting. Design the loop. Get a score.**
```bash
npx @cobusgreyling/loop-init .
```
`loop-init` scaffolds skills, state, and budget files, then prints your **Loop Ready** score and first loop command. Swap `--tool` for `claude`, `codex`, or `opencode`.
Loop engineering replaces you as the person who prompts the agent — you design the system that does it instead.
**New here?** [Quickstart (5 min)](docs/QUICKSTART.md) · [Interactive picker](https://cobusgreyling.github.io/loop-engineering/#interactive)
For developers using Grok, Claude Code, Codex, Cursor, and other AI coding agents.
## Why This Matters
Peter Steinberger:
> “You shouldn’t be prompting coding agents anymore. You should be designing loops that prompt your agents.”
Boris Cherny (Head of Claude Code at Anthropic):
> “I don’t prompt Claude anymore. I have loops running that prompt Claude and figuring out what to do. My job is to write loops.”
The leverage point has moved from crafting individual prompts to designing the control systems that orchestrate agents over time.
## The Five Building Blocks + Memory
| Primitive | Job in the Loop |
|-----------|-----------------|
| **Automations / Scheduling** | Discovery + triage on a cadence |
| **Worktrees** | Safe parallel execution |
| **Skills** | Persistent project knowledge |
| **Plugins & Connectors** | Reach into your real tools (MCP) |
| **Sub-agents** | Maker / checker split |
| **+ Memory / State** | Durable spine outside any conversation |
Full detail: [docs/primitives.md](docs/primitives.md) · Cross-tool matrix: [docs/primitives-matrix.md](docs/primitives-matrix.md)
### Visual Overview
### Anatomy of a Loop
Mermaid diagram (copy-friendly)
```mermaid
flowchart LR
A[Schedule / Automation] --> B[Triage Skill]
B --> C[Read + Write STATE / Memory]
C --> D[Isolated Worktree]
D --> E[Implementer Sub-agent]
E --> F[Verifier Sub-agent tests + gates]
F --> G[MCP / Git / Tickets]
G --> H{Human Gate?}
H -->|safe / allowlisted| I[Commit / PR / Action]
H -->|risky / ambiguous| J[Escalate to human with full context]
I --> A
J --> A
```
**This reference repo now runs its own `validate-patterns` + `audit` workflows on every push/PR** (see `.github/workflows/`). We also added `LOOP.md` describing the loops that will maintain it.
## Patterns
| Pattern | Cadence | Starter | Week 1 | Token cost |
|---------|---------|---------|--------|------------|
| [Daily Triage](patterns/daily-triage.md) | 1d–2h | [minimal-loop](starters/minimal-loop/) | **L1** report | Low |
| [PR Babysitter](patterns/pr-babysitter.md) | 5–15m | [pr-babysitter](starters/pr-babysitter/) | L1 watch | High |
| [CI Sweeper](patterns/ci-sweeper.md) | 5–15m | [ci-sweeper](starters/ci-sweeper/) | L2 cautious | Very high |
| [Dependency Sweeper](patterns/dependency-sweeper.md) | 6h–1d | [dependency-sweeper](starters/dependency-sweeper/) | L2 patch-only | Medium |
| [Changelog Drafter](patterns/changelog-drafter.md) | 1d or tag | [changelog-drafter](starters/changelog-drafter/) | **L1** draft | Low |
| [Post-Merge Cleanup](patterns/post-merge-cleanup.md) | 1d–6h | [post-merge-cleanup](starters/post-merge-cleanup/) | **L1** off-peak | Low |
| [Issue Triage](patterns/issue-triage.md) | 2h–1d | [issue-triage](starters/issue-triage/) | **L1** propose-only | Low |
Not sure which to pick? Try the [interactive picker](https://cobusgreyling.github.io/loop-engineering/#interactive) or [pattern-picker](docs/pattern-picker.md).
Machine-readable index: [patterns/registry.yaml](patterns/registry.yaml) (7 patterns)
## Getting Started (5 minutes)
```bash
# 1. Scaffold + get your Loop Ready score (printed automatically)
npx @cobusgreyling/loop-init . --pattern daily-triage --tool grok
# 2. Estimate token spend for your cadence
npx @cobusgreyling/loop-cost --pattern daily-triage --level L1
# 3. Re-audit after improvements
npx @cobusgreyling/loop-audit . --suggest
# Optional: paste Loop Ready badge into your README
npx @cobusgreyling/loop-audit . --badge
# 4. See scores climb: empty → L1 → L2
bash scripts/before-after-demo.sh
# 5. Start report-only (Grok example)
/loop 1d Run loop-triage. Update STATE.md. No auto-fix in week one.
```
All npm CLIs publish from tagged releases — see [docs/RELEASE.md](docs/RELEASE.md). No clone required.
**Develop from source** (monorepo contributors):
```bash
cd tools/loop-init && npm ci && npm test && node dist/cli.js /path/to/project --pattern daily-triage --tool grok
cd tools/loop-audit && npm ci && npm test && node dist/cli.js /path/to/project --suggest
cd tools/loop-cost && npm ci && npm test && node dist/cli.js --pattern ci-sweeper --cadence 15m
```
Phased rollout: **L1 report → L2 assisted fixes → L3 unattended** — see [loop-design-checklist](docs/loop-design-checklist.md).
## Examples by Tool
- [Grok](examples/grok/daily-triage.md)
- [Claude Code](examples/claude-code/)
- [Codex](examples/codex/)
- [OpenClaw](examples/openclaw/daily-triage.md)
- [Opencode](examples/opencode/)
- [GitHub Actions](examples/github-actions/)
## Operating & Safety
- [Failure Modes](docs/failure-modes.md) — incident-style catalog
- [Anti-Patterns](docs/anti-patterns.md) — design mistakes before production
- [Multi-Loop Coordination](docs/multi-loop.md) — when loops collide
- [Operating Loops](docs/operating-loops.md) — cost, logging, when to kill
- [Safety](docs/safety.md) — denylist, auto-merge, MCP scopes
- [Security](SECURITY.md) — reporting and unattended automation risks
- [Concepts](docs/concepts.md) — intent debt, comprehension debt, harness vs loop
- [MCP Cookbook](examples/mcp/) — connector examples by pattern
## Caveats
Loop engineering amplifies judgment — both good and bad.
- **Token costs** can explode with sub-agents and long-running loops.
- **Verification is still on you.** Unattended loops make unattended mistakes.
- **Comprehension debt** grows faster unless you read what the loop ships.
- Two people can run the same loop and get opposite results. The loop doesn't know. You do.
Addy Osmani:
> “Build the loop. But build it like someone who intends to stay the engineer, not just the person who presses go.”
## Help wanted
**First PR?** Start with the [contributor quickstart](https://github.com/cobusgreyling/loop-engineering/discussions/123) — ~10 min to ~1 hr tasks with same-day review on stories and adopters. See [CONTRIBUTORS.md](CONTRIBUTORS.md) for everyone who has shipped so far.
| Pick one | Issue |
|----------|-------|
| ~10 min | [#120 — Add your project to adopters](https://github.com/cobusgreyling/loop-engineering/issues/120) |
| ~15 min | [#118 — Daily Triage story](https://github.com/cobusgreyling/loop-engineering/issues/118) · [#119 — PR Babysitter failure story](https://github.com/cobusgreyling/loop-engineering/issues/119) |
| ~15 min | [#226 — `loop-sync` subsection in QUICKSTART](https://github.com/cobusgreyling/loop-engineering/issues/226) |
| ~20 min | [#117 — Continue.dev row in primitives matrix](https://github.com/cobusgreyling/loop-engineering/issues/117) |
| ~30 min | [#147 — Cline appendix](https://github.com/cobusgreyling/loop-engineering/issues/147) · [#220 — Cursor CI Sweeper example](https://github.com/cobusgreyling/loop-engineering/issues/220) |
| ~30 min | [#221 — Cursor Post-Merge Cleanup](https://github.com/cobusgreyling/loop-engineering/issues/221) · [#224 — Cursor Issue Triage](https://github.com/cobusgreyling/loop-engineering/issues/224) |
| ~30 min | [#195 — Roo Code appendix](https://github.com/cobusgreyling/loop-engineering/issues/195) · [#196 — GitHub Copilot appendix](https://github.com/cobusgreyling/loop-engineering/issues/196) |
| ~45 min | [#225 — Hermes PR Babysitter example](https://github.com/cobusgreyling/loop-engineering/issues/225) · [#231 — loop-init validation checklist](https://github.com/cobusgreyling/loop-engineering/issues/231) |
| ~1 hr | [#229](https://github.com/cobusgreyling/loop-engineering/issues/229) / [#230](https://github.com/cobusgreyling/loop-engineering/issues/230) — **your story** (worktree week-two, multi-loop failure) |
| ~1 hr | [#173 — Issue Triage week-one story](https://github.com/cobusgreyling/loop-engineering/issues/173) |
Comment **"I'll take this"** on any [`good first issue`](https://github.com/cobusgreyling/loop-engineering/issues?q=is%3Aissue+is%3Aopen+label%3A%22good+first+issue%22) for assignment.
## Contributing
Share production patterns, tool mappings, and failure stories. See [CONTRIBUTING.md](CONTRIBUTING.md) (contribution ladder + [`good first issue` backlog](https://github.com/cobusgreyling/loop-engineering/issues?q=is%3Aissue+is%3Aopen+label%3A%22good+first+issue%22)), [adopters](docs/adopters.md), and [GitHub Discussions](https://github.com/cobusgreyling/loop-engineering/discussions).
## Sources
- [Cobus Greyling – Loop Engineering (Substack)](https://cobusgreyling.substack.com/p/loop-engineering)
- [Addy Osmani – Loop Engineering](https://addyosmani.com/blog/loop-engineering/)
- [Attribution & further reading](resources/sources.md)
## License
MIT
---
*Practical, tool-aware reference for loop engineering, patterns you can clone, checklists you can ship against, and stories that include what broke.*
