I checked 13 top open-source repos. 9 have zero AI agent config.

Alexandru Cioc — Tue, 07 Apr 2026 23:49:47 +0000

Django. Angular. Vue. Svelte. Tokio. Remix. Cal.com. Airflow. Tauri.

None of them have a CLAUDE.md. No .cursorrules. No AGENTS.md. No copilot-instructions.md. Nothing.

These are projects with hundreds of contributors. If they don't have AI agent config, your project almost certainly doesn't either.

The problem is worse than "no config"

The 4 projects that DO have AI configs?

Grafana has a CLAUDE.md. It's literally one line: @AGENTS.md. Their hand-written AGENTS.md has 157 lines, but it misses quality gates from their CI.

Prisma has a 166-line AGENTS.md that says:

"Your training data contains a lot of outdated information that doesn't apply to Prisma 7. Always analyze this codebase like you would analyze a project you are not familiar with."

If Prisma's own maintainers don't trust AI training data, why do you?

Supabase has three separate AI configs — one for Claude, one for Copilot, one for Cursor. Three tools, three configs, zero overlap.

What this means for your code

When you use Cursor, Claude, Copilot, or any AI coding agent, it needs to know:

What quality gates CI enforces (lint, test, build, typecheck)
Your architecture and key directories
Anti-patterns to avoid
Code style conventions

Without this, your AI is working off stale training data. It writes code that breaks in CI.

One command

I built crag to solve this.

npx @whitehatd/crag

It reads your project — CI workflows, package manifests, configs, directory structure — and generates a single governance.md that compiles to every AI tool's native format.

One file in, twelve files out:

Target	File	Consumer
agents-md	`AGENTS.md`	Codex, Aider, Gemini CLI
cursor	`.cursor/rules/`	Cursor
copilot	`copilot-instructions.md`	GitHub Copilot
claude	`CLAUDE.md`	Claude Code
gemini	`GEMINI.md`	Gemini
cline	`.clinerules`	Cline
continue	`.continuerules`	Continue
windsurf	`.windsurf/rules/`	Windsurf
zed	`.rules`	Zed
amazonq	`.amazonq/rules/`	Amazon Q
github	`gates.yml`	GitHub Actions
husky	`.husky/pre-commit`	husky

Change a rule in governance.md, run crag compile, all 12 update.

The benchmark

We tested on 50 of the most important open-source projects:

1,809 gates inferred across 50 repos
96.4% accuracy — 187/194 gates verified against codebase
20 languages, 7 CI systems, 0 crashes

Repo	Stack	Gates	Finding
grafana/grafana	Go + React + Docker	67	CLAUDE.md: 1 line
supabase/supabase	TS + React + Docker	43	3 configs, fragmented
prisma/prisma	TypeScript + Rust	40	"data outdated"
django/django	Python	38	No config
angular/angular	TypeScript	38	No config

How it works

Analyze. Reads CI workflows (GitHub Actions, GitLab, Jenkins, etc.), package manifests, tool configs. 25+ language detectors, 11 CI extractors.
Generate. Writes governance.md with quality gates, architecture, testing profile, code style, anti-patterns, framework conventions.
Compile. Converts to each tool's native format — MDC frontmatter for Cursor, numbered steps for AGENTS.md, YAML triggers for Windsurf.
Audit. Detects stale configs, missing tools, drift.
Hook. Pre-commit auto-recompile. Optional drift gate blocks commits.

No LLM. No network. No API key. 500ms. Deterministic.

Try it

npx @whitehatd/crag

Node.js 18+. Zero dependencies. MIT.

GitHub: WhitehatD/crag

I stopped copy-pasting my lint rules into 12 different config files

Alexandru Cioc — Mon, 06 Apr 2026 00:29:44 +0000

Every project I work on has the same problem: my lint/test/build rules exist in my CI workflow, my pre-commit hook, my .cursorrules, my AGENTS.md, my GEMINI.md, and 7 more files. When I change a rule in one place, the others drift.

I built crag to fix this.

What it does

You write one ~20-line governance.md. crag compiles it to 12 downstream files atomically:

.github/workflows/gates.yml (GitHub Actions)
.husky/pre-commit
.pre-commit-config.yaml
AGENTS.md (Codex, Aider, Factory)
.cursor/rules/governance.mdc
GEMINI.md
.github/copilot-instructions.md
.clinerules, .continuerules, .windsurfrules
.zed/rules.md
.sourcegraph/cody-instructions.md

Change one line, regenerate everything.

Try it in 3 seconds

npx @whitehatd/crag demo

No install. No config. No network. No LLM. ~500ms to a verified
12-target pipeline with a determinism SHA printed inline.

What backs it up

512 tests passing across Ubuntu + macOS + Windows × Node 18/20/22
Stress-tested on 101 OSS repos (4,400 invocations, 0 crashes)
Reference benchmark: 40/40 Grade A on ship-ready governance
Deterministic: same input → byte-identical output, SHA-verified on every CI push across 9 runners
Zero runtime dependencies

GitHub: https://github.com/WhitehatD/crag
npm: https://www.npmjs.com/package/@whitehatd/crag

MIT licensed. If you use more than one AI coding tool alongside CI,
this is for you.

Tags: devtools, opensource, javascript, ai

Forem: Alexandru Cioc