Borrowing it
Nothing to install: this file belongs to ton-to-ton/real-browser-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/ton-to-ton/real-browser-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/ton-to-ton/real-browser-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/ton-to-ton/real-browser-mcp/agents-md)<a href="https://agentmods.dev/instructions/ton-to-ton/real-browser-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/ton-to-ton/real-browser-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/ton-to-ton/real-browser-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/ton-to-ton/real-browser-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.03154 | $0.03154 |
| Opus 5 | $0.01577 | $0.01577 |
| Sonnet 5 | $0.00631 | $0.00631 |
| Haiku 4.5 | $0.00315 | $0.00315 |
Grade A, and why
real-browser-mcp AGENTS.md scanned grade A with 1 finding 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 9d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
p = subprocess.Popen( How it starts
The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - Real Browser MCP
Overview
Real Browser MCP is an MCP-facing fork of the upstream browser bridge.
Architecture:
MCP Server <-> Local Broker <-> Native Host <-> Chrome Extension
Core files:
bin/mcp-server.js: stdio MCP entrypoint for MCP clientsbin/cli.js: installer, status, tool runner, and MCP launch wrapperbin/broker.cjs: local broker with per-session tab ownershipbin/native-host.cjs: Chrome Native Messaging hostextension/background.js: browser-side tool executiondist/plugin.js: bundled tool layer reused from the upstream implementation
Current State
- MCP startup works with Codex CLI
0.114.0. - The MCP server accepts Codex's JSONL-style
initialize/tools/*messages. - The MCP server also serves text
resources/*and prompt runbooks over the same stdio transport. - Native host, broker, and Chrome extension have been verified end-to-end up to
browser_statusreportinghostConnected: true. browser_screenshotexposesfullPage.- Download flows are verified for direct URL, selector-triggered,
wait=true, and competing-download association cases. browser_extractandbrowser_taskare implemented in the bundled tool layer and covered by self-test.rpa_run,rpa_runs_list,rpa_run_get,rpa_run_cancel, andrpa_templates_listnow expose a native-first browser RPA layer abovebrowser_task.browser_routenow supports both block and mock actions on the profile backend.- Both backends now expose
browser_context_*,browser_trace_*,browser_har_*, andbrowser_video_*. - On the native backend, isolated contexts are backed by split incognito windows and require Chrome's "Allow in Incognito" toggle.
- Backend selection now supports
native,agent, andauto, withnativeas the default andautoavailable only when explicitly requested. - MCP exposes
resources/list,resources/read,resources/templates/list,prompts/list, andprompts/get. - The fixed unpacked extension ID derived from the manifest key is
hcghacpnkedkkbelmhapbobekbdfmppi. - The broker's
ensureSessionTabnow receives the caller'spreferredHostIdso that auto-tab creation works when multiple browser hosts (regular + incognito) are connected.
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.
- 9d ago First seen · 150 lines · 3,154 tokens per session scan A 010311fe8abe
real-browser-mcp AGENTS.md is an instructions file published in the GitHub repository ton-to-ton/real-browser-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 3,154 tokens to every session, about $0.0158 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.