Your CLAUDE.md doesn't scale. Version your AI standards as code.

Prath Malik, an engineer running an integration platform with dozens of small repos, developed a methodology called 'standards as code' to version and distribute AI coding agent configurations across teams. The approach uses a single Git repository as the source of truth for skills and rules, synced to user-level tool directories via git hooks, replacing the common but unscalable practice of copy-pasting CLAUDE.md files. Malik released an open template, agent-standards-kit, to help teams adopt the pattern.

Every team using AI coding agents starts the same way: someone drops a CLAUDE.md or .cursorrules , or a copilot-instructions.md into a repo. It works. So the next repo gets one too. And the next. Then you look up and you have 20 repos, 6 teammates, and 3 different AI tools — and no two of those config files are the same. Which one is right? Nobody knows. I hit this wall running an integration platform with dozens of small repos. This post is the pattern I landed on, and a small open template you can clone to do the same. A single file is perfect for one repo and one person. At team scale it fails in five predictable ways: None of these are exotic. They're just what happens when a copy-pasted file meets a growing team. awesome-cursorrules are great for inspiration, but they're copy-paste, single-tool, and have no sync or freshness. AGENTS.md The gap: nobody treats the standards themselves as code — owned, versioned, reviewed, and automatically distributed. Three moves: SKILL.md format. skills/ and rules/ into your tool's config directory. Git hooks re-run the sync on every pull / checkout / rebase . Git repo source of truth ~/.cursor/ skills/ ──────────────└ skills/ junction/symlink rules/ ──────────────┤ setup + rules/ synced .mdc └── git hooks ─────────→ every workspace, every teammate Because rules sync to the user level , they apply in every workspace automatically. Update the repo, everyone git pull s, and the whole team's standards move together — no per-repo copies. CLAUDE.md | standards-as-code | bare CLAUDE.md | | |---|---|---| | Scales across repos | Yes one source | No N copies | | Versioned + PR-reviewed | Yes | No | | Auto-distributed | Yes sync + hooks | Manual | | Freshness mechanism | Yes later in the series | No | It's the difference between a shared library and a code snippet everyone pastes. I packaged the mechanism as an open template: agent-standards-kit this post pins v0.1 . git clone https://github.com/prathakmalik/agent-standards-kit.git cd agent-standards-kit ./scripts/setup.ps1 Windows/Cursor; no admin needed Restart Cursor and your sample skills + rules are live. Swap in your own — the repo ships templates and a de-identified worked example. This is not another skills manager — that niche is crowded. It's a methodology plus a starter template , proven on a real multi-repo platform. Its value is the boring, durable stuff: team+repo scoping via plain git, review of changes, and coming in this series a loop that keeps the standards from rotting. If you're one dev on one repo, a single file is genuinely fine. The moment there's a team , treat your AI standards like code. Coming up next v0.2 : One source of truth is great — but your team doesn't all use the same AI tool. Next post: making the same skills and rules work across Cursor, Claude Code, and GitHub Copilot , with cross-platform setup bash and PowerShell . Star the repo to follow along. If you found this useful, a ⭐ on the repo helps more than you'd think.