Released cARL v0.4.0 today: š—°š—”š—„š—Ÿ š—¶š˜€ š—§š—µš—² š—„š—²š—®š—¹ š—¦š—µš—¶š—ŗ š—¦š—µš—®š—±š˜†.
(Yes, I used an Eminem reference. No, I’m not sorry!)

This release introduces adapter shims for cARL, my repo-native governance model for coding agents.
Different tools expect instructions in different places:
• GitHub Copilot: .github/copilot-instructions.md
• Claude Code: CLAUDE.md
• Codex: AGENTS.md
• Cursor: .cursor/rules/carl.mdc
• Antigravity: .agents/rules/carl.md

Rather than duplicating the full governance model into every file, v0.4.0 makes .github/copilot-instructions.md the shared cARL loader.
Every other harness gets a tiny shim that points back to it.
Same law. Different doorbells.

Tiny grumpy senior engineer as code continues.
https://github.com/goldjg/cARL/releases/tag/v0.4.0
#AI #AgenticAI #DevSecOps #GitHubCopilot #ClaudeCode