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
Constraints — Claude Code
Add rules your loop must never break. The loop-constraints skill reads loop-constraints.md at the start of every run.
Quick start
# Add a constraint (appends to loop-constraints.md)
/constraints Don't push before telling me. Never edit auth/. Always run tests first.
Before every loop run
# The loop-constraints skill runs first — it reads loop-constraints.md and bakes
# every rule into the agent's context BEFORE triage or any action skill runs.
/loop 1d Run $loop-constraints, then $loop-triage. Update STATE.md. No auto-fix in week one.
How it works
/constraints <rule>appends your rule toloop-constraints.md- The
loop-constraintsskill (fromtemplates/SKILL.md.loop-constraints) must be installed in.claude/skills/loop-constraints/SKILL.md - Every loop run starts with
$loop-constraints— it reads the file, loads rules, enforces them
Scaffold automatically
npx @cobusgreyling/loop-init . --pattern daily-triage --tool claude