agentleFS
IgorGanapolskyIgorGanapolsky/mac-yolo-safeguards/.agents/skills/ai-native-sdlc/SKILL.md

ai-native-sdlc

Skill3 starsChanged 4 days agoMITView on GitHub

High-ROI steal of Anthropic's AI-native SDLC playbook: committed artifact chain (intent.md → spec.md → plan.md → tests/diff → PR/REVIEW.md → incident draft), plan mode before code, fix-code-not-test, humans-only production gate. Maps onto AGENTS.md / plan.md / skills / worktrees. Never clone Claude Code evals, MDM, auto-quarantine, or Continuity. Slash: /ai-native-sdlc.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

AI-native SDLC (mechanics, not Claude Code)

Source: https://claude.com/blog/the-ai-native-sdlc-playbook (Louis Claxton, 2026-08-21)

node tools/ai-native-sdlc.js --health --json
node tools/ai-native-sdlc.js --catalog --json
node tools/ai-native-sdlc.js --audit --json
node tools/ai-native-sdlc.js --chain --json
node tools/ai-native-sdlc.js --gate --env production --command "wrangler deploy --env production" --json
node tools/ai-native-sdlc.js --fix-code-not-test --task bugfix --path tests/foo.js --json
node tests/test-ai-native-sdlc.js
NEVERALWAYS
Clone Claude Code evals YAML / Anthropic API CIUse existing node tests/*.js
MDM managed settings / Claude TagSkip those plays
Western Electric auto-quarantine SKUIncident → intent.md draft only
Dual-edit .intent/contract.yamlAGENT-407 owns Tieline contract
Hero Continuity / Mac-pair / RUN ONHosted VPS product lock
Claim production gate is wiredproductionGateWired: false until a real hook exists
Weaken tests to make a fix pass--fix-code-not-test

Artifact chain: intent/ → spec/ → plan.md → tests/diff → REVIEW.md + GitHub PR → incident draft back to intent/. AGENTS.md is the CLAUDE.md analog (CLAUDE.md is a pointer).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.