VercelCLAUDE.mdagent-browser / eve
vercel-labs/agent-browser/examples/eve/CLAUDE.md
No summary in the file. Open it to read it.
152 projects use a version of this
CLAUDE.md examples from real projects
How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Worked for most · soon
VercelCLAUDE.mdVercelCLAUDE.mddeepsec
vercel-labs/deepsec/CLAUDE.md
Pointer file for Claude Code working in this repo. User-facing docs are in README.md; contributor docs in CONTRIBUTING.md. Read those first. Always use the technical-writer skill (.agents/skills/technical-writer/SKILL.md) when you write or edit prose for this repo, including docs, READMEs, commit messages, PR titles and descriptions, and issues. - Plugin contracts live in packages/core/src/plugin.ts. Internals route through getRegistry() from deepsec/config rather than calling organization-specific code directly. - The CLI auto-loads deepsec.config.{ts,mjs,js,cjs} from cwd upward (via packages/deepsec/src/load-config.ts, jiti). - New matchers go…
VercelCLAUDE.mdopen-agents
vercel-labs/open-agents/CLAUDE.md
No summary in the file. Open it to read it.
169 projects use a version of this
VercelCLAUDE.mdopenreview
vercel-labs/openreview/.claude/CLAUDE.md
This project uses Ultracite, a zero-config preset that enforces strict code quality standards through automated formatting and linting. Oxlint + Oxfmt (the underlying engine) provides robust linting and formatting. Most…
3 projects use a version of this
VercelCLAUDE.mdnext-skills
vercel-labs/next-skills/CLAUDE.md
The skills here have moved to https://github.com/vercel/next.js/tree/canary/skills See AGENTS.md.
VercelCLAUDE.mdbash-tool
vercel-labs/bash-tool/CLAUDE.md
This file provides guidance for Claude Code when working on this project. bash-tool is a generic bash tool for AI agents, compatible with AI SDK (https://ai-sdk.dev/). It provides bash, readFile, and writeFile tools that work with a sandboxed environment. Tests are co-located with source files (*.test.ts). Tests are included in TypeScript compilation for type checking. AI SDK tool execute calls require ToolExecutionOptions with toolCallId and messages.
VercelCLAUDE.mdfx0 / design-md
vercel-labs/fx0/lib/design-md/claude.md
A warm-canvas editorial interface for Anthropic's Claude product. The system anchors on a tinted cream canvas with serif display headlines, warm coral CTAs, and dark navy product surfaces (code editor mockups, model showcase cards). Brand voltage comes from the cream/coral pairing — deliberately warm and humanist where most AI brands use cool blue + slate. Type voice runs a slab-serif display ("Copernicus" / Tiempos Headline) for h1/h2 and a humanist sans for body. The signature Anthropic black-radial-spike mark anchors the wordmark.
VercelReads credentialsCLAUDE.mdagent-eval
vercel-labs/agent-eval/CLAUDE.md
Configuration should be done through the experiment config file, not environment variables. When adding a new agent to the framework, follow this checklist:
VercelCLAUDE.mdgithub-tools
vercel-labs/github-tools/CLAUDE.md
No summary in the file. Open it to read it.
188 projects use a version of this
VercelCLAUDE.mdmarkdown-sanitizers
vercel-labs/markdown-sanitizers/CLAUDE.md
This is a monorepo containing two related security-focused npm packages for hardening markdown against data exfiltration attacks through LLM prompt injection: Both packages use pnpm (not npm) as the package manager. Both packages share the tests based on markdown-to-markdown-sanitizer/tests/bypass-attempts/\*.md. Adding more examples hardens both packages Both packages are designed for defensive security use only:
VercelCLAUDE.mdmarkdown-sanitizers / markdown-to-markdown-sanitizer
vercel-labs/markdown-sanitizers/markdown-to-markdown-sanitizer/CLAUDE.md
This is a robust markdown sanitizer that filters URLs in markdown links and images against prefix allow-lists, with comprehensive HTML sanitization. The sanitizer uses a sophisticated markdown-to-HTML-to-markdown pipeline to ensure security while preserving markdown structure. The sanitizer follows this flow: Always use pnpm, not npm. The codebase includes extensive security testing with 111 bypass attempt files that test various attack vectors: Tests use Vitest and run against multiple markdown parsers (remark, marked, markdown-it, showdown, commonmark) to ensure comprehensive coverage. The…
VercelCLAUDE.mdspecli
vercel-labs/specli/CLAUDE.md
Specli turns an OpenAPI 3.x spec (URL or file) into a CLI. There are two ways to use it: This file is guidance for agents working in this repo. Install…
VercelCLAUDE.mdmcp-to-ai-sdk
vercel-labs/mcp-to-ai-sdk/CLAUDE.md
This is mcp-to-ai-sdk, a CLI tool that generates Vercel AI SDK wrappers for Model Context Protocol (MCP) tools. It connects to MCP servers, discovers their tools, and generates type-safe TypeScript wrappers that can be used with the Vercel AI SDK. Main CLI File (mcp-tools-cli.ts) Generated Code Architecture The CLI generates a directory structure like mcps/mcp.grep.app/ with: Tool Factory Pattern: Tools are generated as factory functions that accept a client getter, enabling both default shared client usage and custom client injection.
VercelCLAUDE.mdphase
vercel-labs/phase/CLAUDE.md
See AGENTS.md for repository instructions and its package-specific instruction pointers.
VercelCLAUDE.mdnpm.bet
vercel-labs/npm.bet/.claude/CLAUDE.md
This project uses Ultracite, a zero-config Biome preset that enforces strict code quality standards through automated formatting and linting. Biome (the underlying engine) provides extremely fast Rust-based linting and formatting.…
VercelCLAUDE.mdnode-vfs-polyfill
vercel-labs/node-vfs-polyfill/CLAUDE.md
User-land implementation of the Node.js Virtual File System (VFS) based on nodejs/node#61478. This library allows mounting an in-memory filesystem that intercepts standard fs module calls through monkey-patching. Run a single test: We do not modify vendor/vfs-upstream/. The vendor directory contains code based on the upstream Node.js VFS PR. All extensions are layered on top via src/ and index.js. See UPSTREAM.md for details on our extensions.
VercelCLAUDE.mdfast-webstreams
vercel-labs/fast-webstreams/CLAUDE.md
WHATWG ReadableStream/WritableStream/TransformStream backed by Node.js streams for zero-promise piping. Run all three checks before committing — unit tests, WPT, lint/knip: Or all at once: IMPORTANT: Always run pnpm run test:unit…
VercelCLAUDE.mdoss-gtm-feedback / www
vercel-labs/oss-gtm-feedback/apps/www/CLAUDE.md
This is a Next.js 16 application for GTM feedback collection and reporting. It uses: This project uses next-safe-action v8 for type-safe server actions with a sophisticated middleware pipeline. Located in src/lib/actions/clients/, we have three main action clients:
VercelCLAUDE.mdnext-docs-agentic-rag
vercel-labs/next-docs-agentic-rag/CLAUDE.md
No summary in the file. Open it to read it.
VercelReads credentialsCLAUDE.mdworkflow-campaign-demos
vercel-labs/workflow-campaign-demos/CLAUDE.md
A git subtree organizer for the "30 Days of Workflow DevKit" demo collection. Each subdirectory is a complete standalone Next.js app that also lives in its own repo under vercel-labs/…
About CLAUDE.md
What is CLAUDE.md?
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
Where does it go?
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
What should it contain?
Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.
CLAUDE.md or AGENTS.md?
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.