Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audit, loop-init, loop-cost.
TypeScript agentic-aiai-agentsai-codinganthropicautomationclaudeclaude-codecodexcoding-agentsdevops-automationdevtoolsgithub-actionsgrokllmloop-engineeringmcpprompt-engineering
LOOP.md — Thin loop
- Pattern: thin-loop
- Level: L1 report-only
- Cadence:
issues/pull_requestopened + weekdays 08:00 UTC - State: none. GitHub issues and PRs are the backlog. The Actions job summary is the report.
- Writes: job summary; at most one comment per thread (
<!-- thin-loop -->). - Denylist: no code edits, no labels, no closes, no pushes.
- Kill switch: disable
.github/workflows/thin-loop.ymlor cancel the workflow.
When a queue must survive across runs (attempt counts, budgets, watch lists), graduate to Daily Triage and add STATE.md.