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
# Machine-readable twin of your project's safety policy (see docs/safety.md
# in loop-engineering for the prose this is meant to mirror). Copy to your
# repo root as gate.yaml and adjust denylist/autoMergeAllowlist for your
# project's own sensitive paths.
version: 1
denylist:
- "**/.env"
- "**/.env.*"
- "**/secrets/**"
- "**/credentials/**"
- "**/*_key*"
- "**/*_secret*"
- "**/.terraform/**"
- "**/k8s/production/**"
- "**/migrations/**"
- "**/auth/**"
- "**/payments/**"
- "**/billing/**"
# Escalate instead of auto-merging when a change touches more than this many files.
maxFiles: 10
# --action auto-merge only proceeds if every changed path matches one of these.
autoMergeAllowlist:
- "docs/**"
- "**/*.md"