Borrowing it
Nothing to install: this file belongs to meshbrow-dev/meshbrow-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/meshbrow-dev/meshbrow-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/meshbrow-dev/meshbrow-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/meshbrow-dev/meshbrow-mcp/claude-md)<a href="https://agentmods.dev/instructions/meshbrow-dev/meshbrow-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/meshbrow-dev/meshbrow-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00696 | $0.00696 |
| Opus 5 | $0.00348 | $0.00348 |
| Sonnet 5 | $0.00139 | $0.00139 |
| Haiku 4.5 | $0.00070 | $0.00070 |
Grade A, and why
meshbrow-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meshbrow MCP Server
You are working in meshbrow-dev/meshbrow-mcp — the standalone MCP (Model Context Protocol) server, released via GoReleaser + Homebrew (meshbrow-dev/homebrew-tap). This repo is not yet listed in meshbrow-dev/workspace's own CLAUDE.md app table; it is assumed to live at apps/mcp/ there — verify and correct this hook's path-prefix assumption if the team places it elsewhere.
See .claude/skills/go-backend/SKILL.md (Go conventions), .claude/skills/mcp-protocol/SKILL.md (tool definitions and safety rules), and .claude/skills/deployment/SKILL.md (Open-Source Tool Releases section) for conventions.
Shared Claude Code Config
.claude/skills/ and .claude/agents/ in this repo are synced automatically from meshbrow-dev/workspace by the SessionStart hook (.claude/hooks/session-start.sh) whenever this repo is opened directly (e.g. Claude Code on the web) rather than checked out inside the workspace repo. Don't hand-edit files under .claude/skills/ or .claude/agents/ here — edit them in meshbrow-dev/workspace instead, they'll be overwritten on the next session start.
Critical Rules (ALL code changes)
NEVER
- Return raw error messages to API clients — use structured error responses
- Log sensitive fields: apiKey, proxyCredentials, fingerprint configs
- Call Docker/Chromium directly — always go through the
Runtimeinterface - Skip input validation on API handlers
- Use
anytype in Go — always define concrete types - Commit secrets, .env files, or proxy provider credentials
- Ship without tests for the changed code
- Ship without updating relevant docs
- Expose fingerprint internals in API responses (detection vectors)
- Store proxy passwords unencrypted
- Allow cross-session network traffic (namespace leak = critical bug)
- Ship implementation without running tests and confirming they pass
- Consider a feature "done" with less than 80% test coverage on changed code
ALWAYS
- Use structured logging (slog in Go, structured JSON)
- Validate at system boundaries (API handlers, webhook receivers)
- Use context.Context for cancellation and deadlines
- Write tests alongside implementation (same commit or immediately after)
- Run tests after implementation and confirm they pass before marking complete
- Target ≥ 80% coverage on all changed/new code
- Use conventional commits: feat:, fix:, docs:, refactor:, test:, chore:
- Add OpenTelemetry spans for cross-service calls
- Use database transactions for multi-row operations
- Clean up network namespaces on session destroy
- Rotate proxy credentials when sessions end
- Verify anti-detection on every Chromium update
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 54 lines · 696 tokens per session scan A da9d2de84033
meshbrow-mcp CLAUDE.md is an instructions file published in the GitHub repository meshbrow-dev/meshbrow-mcp (0 stars, last pushed 17d ago), licensed MIT. It adds 696 tokens to every session, about $0.0035 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.