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 skills/deliciousbuding/codex-browser-bridge/codex-browsernpx skills add DeliciousBuding/codex-browser-bridge --skill codex-browsergit clone --depth 1 https://github.com/DeliciousBuding/codex-browser-bridgeWhat 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 | $0.00050 | $0.02894 |
| Opus 5 | $0.00025 | $0.01447 |
| Sonnet 5 | $0.00010 | $0.00579 |
| Haiku 4.5 | $0.00005 | $0.00289 |
Grade A, and why
codex-browser 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 3d 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.
This is a copy
89% identical to codex-browser — 39 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Browser Bridge
You are an agent controlling a real Chrome or Edge browser through the codex-browser MCP server. This skill covers all 52 tools and their effective use.
Quick Check
Call codex_doctor first. If healthy is true, browser pipes are ready. If install.mcp_spawn_ready is false, ask the user to update the MCP config with install.suggested_mcp_config; this is separate from browser pipe health.
Tool Groups
Tabs (5 tools)
| Tool | What it does |
|---|---|
codex_list_tabs |
Tabs owned by this session |
codex_create_tab |
New blank tab (navigate after) |
codex_close_tab |
Close a tab |
codex_user_tabs |
All browser tabs, including unclaimed |
codex_claim_tab |
Take ownership of an existing tab |
Navigation (8 tools)
| Tool | What it does |
|---|---|
codex_navigate |
Go to URL. Only http:// and https:// URLs are accepted. |
codex_reload |
Reload current page |
codex_navigate_back |
Back |
codex_navigate_forward |
Forward |
codex_wait_for_load |
Poll document.readyState until complete or timeout (default 10s) |
codex_nav_and_wait |
Navigate and wait for load in one call. Prefer this over navigate + wait_for_load. |
codex_wait_for_element |
Poll a CSS selector until it matches. Use on SPAs where wait_for_load returns immediately but content renders async. |
codex_wait_for_url |
Poll until location.href contains a substring (SPA route change). |
DOM & Accessibility (5 tools)
| Tool | What it does |
|---|---|
codex_dom_snapshot |
Full AX tree with node IDs for codex_dom_click |
codex_dom_get_visible |
Human-readable DOM (no node IDs) |
codex_dom_click |
Click by AX node ID from snapshot |
codex_find_element |
Search by ARIA role and/or name. Returns node IDs. |
codex_click_element |
Click a result from codex_find_element. Uses CDP mouse events — no JS injection. |
Page inspection (7 tools)
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.
- 3d ago First seen · 235 lines · 50 tokens per session scan A d2f29595f5b3
codex-browser is a skill published in the GitHub repository DeliciousBuding/codex-browser-bridge (15 stars, last pushed 14d ago), licensed MIT. It adds 50 tokens to every session and 2,894 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to codex-browser, differing in 39 lines, and is treated as a copy.
Other skills, from other repositories
owb
Open Web Bridge (OWB) — drive the user's own real browser with the owb command. Read pages behind their existing logins, gather and cross-check information, fill forms, walk multi-step flows, debug their site, audit responsive/accessibility behavior, and capture or reverse-engineer network traffic. Use this whenever…
nekoro-browser
浏览器自动化——打开网页、搜索、点击、截图、执行 JS、填表、上传文件、处理对话框。通过 Chrome 扩展的 chrome.debugger API 操控用户日常浏览器，保留登录态，不开调试端口。触发词："浏览器"、"打开网页"、"搜索"、"截图"、"点击"、"填表"、"上传文件"、"自动化操作"。.
codex-control-chrome-mcp
Use Codex Control Chrome MCP to control the user's normal Chrome profile through the Codex Chrome extension. Use when a task needs existing Chrome tabs, cookies, logged-in sessions, installed extensions, CDP commands, page inspection, navigation, screenshots, network/console events, or browser automation from an MCP…
browser-automation
Use browser automation to inspect or interact with websites, test rendered interfaces, capture screenshots, and diagnose console or network behavior.
control-chrome-bridge
Drive the user's real Chrome browser — their own profile, tabs, cookies and logged-in sessions — through the chrome-bridge MCP server. Use for tasks that need existing browser state: reading a page behind a login, filling a form on a site the user is signed into, testing a local app in a real browser, or inspecting…
setup
Guide users through Chrome extension setup for browser control. Use when user asks about setup, installing the extension, connecting Chrome, or when browsercontrol tools return "No browser connected".