Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/swimmwatch/cloakbrowser-mcp/agents-mdgit clone --depth 1 https://github.com/swimmwatch/cloakbrowser-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/swimmwatch/cloakbrowser-mcp/agents-md)<a href="https://agentmods.dev/instructions/swimmwatch/cloakbrowser-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/swimmwatch/cloakbrowser-mcp/agents-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 | $0.02582 | $0.02582 |
| Opus 5 | $0.01291 | $0.01291 |
| Sonnet 5 | $0.00516 | $0.00516 |
| Haiku 4.5 | $0.00258 | $0.00258 |
Grade A, and why
cloakbrowser-mcp AGENTS.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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Operating manual for AI coding agents working in this repository.
About The Project
cloakbrowser-mcp is a stdio MCP bridge for upstream @playwright/mcp. It starts upstream Playwright MCP as a child process, injects the CloakBrowser Chromium executable through a generated Playwright MCP config, forwards upstream tools unchanged, and adds only two local introspection tools.
- Runtime: Node.js
^22.13.0 || >=24.0.0, ES modules, TypeScriptstrictwithNodeNext. - Public surface: CLI package only,
bin: cloakbrowser-mcp. - Docker base: pinned official Playwright MCP image from
Dockerfile.
Golden Rules
- Write the simplest possible code. Do only what was requested.
- Use the
context7MCP tool whenever you need up-to-date documentation or API references for external libraries. - Everything in this repository is written in English.
- AI-agent reasoning and code-agent reasoning for this repository must be in English.
- Do not copy, rewrite, or mutate upstream Playwright MCP browser tool contracts.
Project Layout
src/
cli.ts CLI entry point
server.ts outer MCP proxy server
index.ts metadata export only
bridge/ config generation, env parsing, upstream path resolution, local tools
cli/ option handling, diagnostics, singleton cleanup
http/ Streamable HTTP server and session lifecycle
logging/ stderr/file logging
protocol/ shared protocol constants
runtime/ console fallback source strings
project/ project metadata
tests/
unit/ env/config/local tool tests
integration/ fake-upstream MCP proxy tests
fixtures/ fake upstream MCP server
Daily Commands
npm run dev
npm test
npm run test:unit
npm run test:integration
npm run typecheck
npm run lint
npm run format
npm run format:check
npm run build
npm run package:verify
npm run docker:build
npm run docker:smoke
npm run bridge:compare
npm run check
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 · 216 lines · 2,582 tokens per session scan A 06c9c7ec3f1a
cloakbrowser-mcp AGENTS.md is an instructions file published in the GitHub repository swimmwatch/cloakbrowser-mcp (56 stars, last pushed yesterday), licensed MIT. It adds 2,582 tokens to every session, about $0.0129 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 2026-08-30.
Other instructions, from other repositories
browser-use AGENTS.md
AGENTS.md instructions for browser-use/browser-use, covering agents.md version 2, development rules, quickstart, 1. installing browser-use and on windows use .venv\scripts\activate.
browser-use CLAUDE.md
Claude Code instructions for browser-use/browser-use, covering claude.md, high-level architecture, core components, event-driven browser management and cdp integration.
stealth-browser-mcp AGENTS.md
Instructions for vibheksoni/stealth-browser-mcp, covering agent instructions, start here, recommended proxy services, environment and validation.
mcp-stealth-chrome AGENTS.md
Instructions for RobithYusuf/mcp-stealth-chrome, covering mcp-stealth-chrome — agent guide, product and repository map, hard constraints, working defaults and architecture invariants.
AgenticCrawler AGENTS.md
Instructions for Mingye-Lu/AgenticCrawler, covering agents.md, project, commands, non-interactive provider setup (agent/ci use) and exit codes: 0=ok 1=error 2=usage/config 3=not-configured.
browser-mcp AGENTS.md
AGENTS.md instructions for drisplabs/browser-mcp, covering snapshot & interaction pipeline — audit results, critical (agent can't complete tasks), major (agent works around it poorly), m2. batch vs. fallback coordinate space mismatch and m3. wrapping hidden inputs dropped from snapshot.