agentleFS

Find the best CLAUDE.md, AGENTS.md and Claude skills

One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.

Worked for most · soon
VercelCursor rule

ai-chatbot / rules

vercel/ai-chatbot/.cursor/rules/ultracite.mdc

Ultracite Rules - AI-Ready Formatter and Linter

14 projects use a version of this

21k14mo agoReviewMountCreate a free account to mount
VercelAGENTS.md

vercel

vercel/vercel/AGENTS.md

Guidelines for AI agents working on the Vercel monorepo. This is a pnpm monorepo containing 44+ packages for the Vercel CLI and runtimes: Run tests for a specific package: Always create a changeset for all PRs. A changeset is a markdown file in .changeset/ with YAML frontmatter listing affected packages and their bump type (patch/minor/major). Example changeset for a package change: Example changeset for an internal package (the public packages that bundle it are added at version time): Example changeset…

16k18d agoReviewMountCreate a free account to mount
VercelAGENTS.md

vercel / cli

vercel/vercel/packages/cli/AGENTS.md

Always-loaded guidance for work inside packages/cli. Keep this file small. The CLI UX design system lives in packages/cli/.agents/skills/cli-ux/ and should be loaded only when the task or code review touches user-facing CLI behavior. Common shared areas:

16k18d agoReviewMountCreate a free account to mount
VercelSkill

cli-ux

vercel/vercel/packages/cli/.agents/skills/cli-ux/SKILL.md

Vercel CLI design system, the north-star standard for command names, options, help, prompts, output, copy, errors, JSON, exit codes, and agent/CI behavior in packages/cli. Use when designing, implementing, or reviewing any user-facing CLI surface. Skip implementation-only refactors that leave the CLI surface unchanged.

16k18d agoReviewMountCreate a free account to mount
VercelAGENTS.md

vercel / python

vercel/vercel/python/AGENTS.md

- Dependencies: PEP 440 compatible release clauses (rich ~= 14.0), avoid pinning patch releases (rich ~= 14.0.0). - Only add code that is actually used. No speculative APIs or exports. - _internal/ is private — no backwards compatibility needed when refactoring. - uv: uv sync, uv run <cmd>, uv add <pkg> - ruff: uv run ruff check . (lint), uv run ruff format . (format) - pytest: uv run pytest, uv run pytest tests/test_foo.py, uv run pytest -k test_name. Tests…

16k18d agoReviewMountCreate a free account to mount
VercelSkill

vercel-cli

vercel/vercel/skills/vercel-cli/SKILL.md

Guides deployment, configuration, and troubleshooting with the Vercel CLI. Use when operating Vercel projects or resources through the CLI, especially for workflows spanning multiple commands, including deployments, CI, build failures, logs, metrics, Speed Insights, traces, environment variables, domains and DNS, firewall and WAF rules, Global Config (Edge Config), feature flags, storage and Blob, Container Registry (VCR), microfrontends, Sandbox, and `vercel api` fallback.

16k18d agoReviewMountCreate a free account to mount
VercelPipes a download into a shellSkill

fix-vi-flaky-test

vercel/vercel/.vc/automations/workflows/flaky-tests/skills/fix-vi-flaky-test/SKILL.md

Set up the Factory sandbox for vercel-internal's tests, then reproduce and fix one flaky test that the flaky-tests workflow found, or add diagnostics for a shard hang.

16k18d agoReviewMountCreate a free account to mount
VercelSkill

author-labels

vercel/vercel/.vc/automations/workflows/melkey-label/skills/author-labels/SKILL.md

Decide which author label, if any, a pull request gets. Load before labeling a pull request.

16k18d agoReviewMountCreate a free account to mount
CLAUDE.md vs AGENTS.md

Agent instruction files

What are agent instruction files?

Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.

CLAUDE.md or AGENTS.md?

CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.

What is a skill?

A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.

Can I search my own team's files too?

Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.