bb-browser: Instructions file for Codex

AGENTS.md

bb-browser AGENTS.md is an instructions file for Codex, OpenCode from epiral/bb-browser. It costs 2,522 tokens per session, scanned A, original, MIT.

Development instructions for bb-browser, an agent-controlled browser system with a command line tool, background service, and optional remote hub.

In plain words
What is it for?
Use them when developing the CLI, daemon, browser controls, Chrome DevTools connections, remote hub mode, or live video and user-input streaming.
Why use it?
They give coding agents the architecture and connection rules needed to change browser control, streaming, and remote operation safely.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is epiral/bb-browser's own configuration. It tells Codex and OpenCode how to work on bb-browser itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything bb-browser configures →

About the project

bb-browser is a command-line tool and MCP server that lets AI agents control a user's real Chrome browser and its existing login sessions. Agents use it to interact with websites across 36 platforms through the browser interface rather than separate APIs or extracted credentials. The catalogue skills configure or expose bb-browser for agent workflows.

epiral/bb-browser · 6,260 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to epiral/bb-browser. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/epiral/bb-browser/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/epiral/bb-browser

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for bb-browser AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/epiral/bb-browser/agents-md/github.svg)](https://agentmods.dev/instructions/epiral/bb-browser/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/epiral/bb-browser/agents-md"><img src="https://agentmods.dev/badge/instructions/epiral/bb-browser/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.

agentmods 80×15 button for bb-browser AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/epiral/bb-browser/agents-md"><img src="https://agentmods.dev/badge/instructions/epiral/bb-browser/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,522 This file is loaded in full into every session.
When invoked 2,522 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02522 $0.02522
Opus 5.5 $0.01009 $0.01009
Sonnet 5.5 $0.00504 $0.00504
Haiku 4.5 $0.00252 $0.00252

Measured 2mo ago against content hash 67667ad433d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

bb-browser 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 2mo 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.

AGENTS.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

bb-browser Agent 开发规范

架构

CLI ──HTTP──▶ Daemon ──controlConn CDP──▶ Chrome
                │
                │ --hub 模式 (可选)
                ├── Hub ProviderStream ──▶ Pinix Hub
                │
                │ Protocol 2
                └── Streamer (bb-viewer) ──captureConn + inputConn CDP──▶ Chrome
                         │
                         └── WebRTC video + DataChannel ──▶ Clip Web UI

三根 CDP 连接到同一个 Chrome:

连接 Owner 职责
controlConn daemon Agent 操作:tab/nav/site/DOM/click-by-ref
inputConn streamer Human 实时输入:鼠标/键盘/IME (DataChannel → CDP)
captureConn streamer 视频流:screencast → VP8 → WebRTC

组件:

组件 位置 职责
CLI packages/cli/ 命令行入口,HTTP 调 daemon
Daemon packages/daemon/ 控制中心:CDP controlConn、HTTP API、Hub 连接、site 执行、streamer 管理
Shared packages/shared/ 统一命令定义 (commands.ts)、协议类型 (protocol.ts)
Streamer bb-viewer repo 纯视频 + 实时输入(Go binary,daemon 子进程)

Daemon 两种模式

# 本地模式:Agent 用 CLI 操作浏览器
bb-browser daemon start

# Hub 模式:注册到 Pinix Hub,远程可用
bb-browser daemon start --hub https://hub.pinixai.com --hub-token xxx

协议

Protocol 1: CLI ↔ daemon (POST /command)

请求:{"method": "snap", "params": {"tab": "3ef9"}} 成功:{"result": {"tab": "3ef9", "title": "Google", "snapshot": "..."}} 失败:{"error": {"message": "Missing --tab", "hint": "Run 'bb-browser tab list'"}}

Protocol 2: daemon ↔ streamer (POST /command)

Method Params 说明
connect {cdpUrl, ice?} 连接 CDP,创建 WebRTC peer
answer {answer_sdp, candidates} 完成 WebRTC 信令
switch {cdpUrl} 切到新 tab(peer 不变)
stop {} 停止

统一命令定义

packages/shared/src/commands.ts 是所有命令的单一定义源。每个命令包含 method、group、description、requiresTab、params。CLI 解析、daemon dispatch、Hub 注册都从这里读取。

添加新命令:

  1. commands.ts — 添加 CommandDef
  2. protocol.ts — 添加 ActionType
  3. command-dispatch.ts — 添加处理分支
  4. packages/cli/src/commands/<name>.ts + index.ts — CLI 命令

Read the full file on GitHub · 208 lines

Changes

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.

  1. 2mo ago First seen · 208 lines · 2,522 tokens per session scan A 67667ad433d6

Subscribe to this mod's changes

bb-browser AGENTS.md is an instructions file published in the GitHub repository epiral/bb-browser (6,260 stars, last pushed 5mo ago), licensed MIT. It adds 2,522 tokens to every session, about $0.0101 per session on Opus 5.5. 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.

Related

bb-browser AGENTS.md compared with instructions from other repositories

bb-browser AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
bb-browser AGENTS.mdepiral/bb-browserInstructions file6.3k5mo agoMITA2,522Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode