CLAUDE.md Generator from Repo

claudemd-generator is an Apify Actor that generates a high-quality draft CLAUDE.md for any public GitHub repo in under 30 seconds by auto-detecting stack, commands, conventions, and structure. It replaces the 30-minute manual chore of writing CLAUDE.md from scratch with a one-click ~70% complete draft you only need to lightly edit.

Best for / Not for

✓ Best for	✗ Not for
Onboarding Claude Code to a new repo or codebase you just joined	Repos using obscure stacks (PHP, Ruby, Elixir — stack section blank)
Standardizing every repo in your org with a baseline CLAUDE.md	Replacing thoughtful project-specific conventions and gotchas
OSS maintainers shipping CLAUDE.md so contributors using Claude Code stay on-rails	Private repos (anonymous GitHub API only in the public version)

Example input → output

Input:

{
  "githubRepo": "vercel/next.js"
}

Output (dataset summary, truncated):

{
  "repo": "vercel/next.js",
  "stars": 128000,
  "primary_language": "JavaScript",
  "detected_stack": {
    "languages": ["JavaScript/TypeScript"],
    "frameworks": ["Next.js", "React"],
    "testCommands": ["npm test  # or: jest"],
    "buildCommands": ["npm run build  # next build"]
  },
  "existing_claudemd": false,
  "draft_size_bytes": 2148
}

The generated CLAUDE.md (Markdown, ~1–3 KB) is written to the run's Key-Value Store with sections for project overview, tech stack, commands, structure, conventions, and a sensible "what NOT to do" baseline.

FAQ

Does this work with Claude Code?

Yes — the output is purpose-built for Claude Code. Drop the generated CLAUDE.md at the root of your local copy of the repo, commit it, and the next time you launch Claude Code in that directory the agent picks it up automatically.

Is it free?

There's no upfront free tier — the Actor uses Apify's pay-per-event model at $0.05 per generated draft. A $5 bulk plan covers 200 drafts (enough for a full org-wide audit in one batch).

Does it scan private repos?

Not in the public version. The Actor uses anonymous GitHub API. For private-repo support, contact for a custom version that accepts a GitHub token via Apify secrets.

Can I run it in CI?

Yes. Trigger the Actor from a GitHub Action whenever a new repo is created in your org. Pipe the generated CLAUDE.md to a PR, get a maintainer to lightly edit, merge. End result: no repo in your org ships without one.

Output format?

Markdown file (CLAUDE.md) in the run's Key-Value Store, plus a JSON dataset row summarizing detected stack, repo stats, and whether an existing CLAUDE.md was found. Downloadable from Apify Console or REST API.

Rate limits?

The Actor uses ~6 GitHub anonymous API calls per run (well under the 60 req/hour anonymous ceiling). For org-wide audits run in batches or upgrade to Apify proxy.

What if the repo uses a stack I haven't listed?

The Actor detects JS/TS, Python, Rust, and Go. If your repo uses another language (PHP, Ruby, Elixir, etc.), the stack section will be blank and you'll need to fill it in. PRs to the source repo welcome.

Is the generated CLAUDE.md good enough to commit as-is?

No — it's a draft. Plan for 5–10 minutes of editing per repo: fill in the conventions, gotchas, and "what NOT to do" sections specific to your codebase. The Actor does the boring 70%; you do the high-value 30%.

How does this compare to writing CLAUDE.md from scratch?

Same final quality if you spend the same time editing. The difference is the floor — without this Actor, most repos end up with no CLAUDE.md at all because the activation energy is too high. With this Actor, every repo gets at least a baseline.

Why use this Actor?

• Onboard Claude Code to any repo in seconds, not hours
• Standardize team conventions: run this on every project so every CLAUDE.md has the same structure
• Audit your existing repos: see at a glance which projects lack a CLAUDE.md
• Faster contractor / open-source contribution: drop into a new codebase and immediately have the AI agent oriented
• Open-source maintainers: ship a great CLAUDE.md so contributors using Claude Code don't ask repeated "how do I run tests?" questions

How to use

1. Enter a public GitHub repo in the form owner/repo (e.g. vercel/next.js)
2. Click Start
3. Wait ~10–30 seconds (depending on repo size)
4. Open the Storage tab → Key-value store → download CLAUDE.md
5. Drop it into the root of your local copy of the repo, edit lightly, and commit

Input

• githubRepo (required) — A public GitHub repository in the form owner/repo. Examples: vercel/next.js, fastapi/fastapi, tokio-rs/tokio.

Output

The Actor saves two outputs per run:

1. Key-value store: CLAUDE.md

The generated draft (Markdown, ~1–3 KB). Sections include:

• Project overview (derived from repo description + README)
• Tech stack (auto-detected)
• Common commands (npm test, cargo build, pytest, etc.)
• Repository structure (top-level dirs)
• Conventions and gotchas (placeholders to fill in)
• What NOT to do (sensible defaults: no npm install without confirming, no commit to main, no claims of "tests pass" without running them)
• Recommended hooks (e.g. verify-before-stop for blocking false-completion regressions)

2. Dataset summary

A JSON row with detected stack, stars, primary language, and whether an existing CLAUDE.md was found (so you merge instead of overwrite).

Pricing

Pay-per-event model:

• Per-repo generation: $0.05 per draft (~6 GitHub API calls per run — well under the anonymous rate limit)
• Bulk plan: $5 for 200 drafts (run on every repo in your org in one batch)
• Custom: contact for white-label / on-prem versions

Tips

• The Actor uses anonymous GitHub API (60 req/hour ceiling). For high-throughput org-wide audits, run in small batches or upgrade Apify proxy.
• Generated drafts are a starting point, not a final spec. Review before committing — especially the "conventions and gotchas" section, which is mostly placeholders.
• For repos with an existing CLAUDE.md, the Actor flags it in the output. Merge selectively rather than overwriting.
• For repos missing manifest files, the stack detection falls back to the repo's primary_language field — less precise but still useful.

Support

Issues / feature requests: open in the Issues tab on the Apify console.

Built by Ian Mu — github.com/ianymu — author of verify-before-stop, the Stop hook that blocks Claude Code session-end if files changed but no verification log exists.