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/escapewu/chrome-agent-bridge/chrome-agent-controlnpx skills add escapeWu/chrome-agent-bridge --skill chrome-agent-controlgit clone --depth 1 https://github.com/escapeWu/chrome-agent-bridgeWrote 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/skills/escapewu/chrome-agent-bridge/chrome-agent-control)<a href="https://agentmods.dev/skills/escapewu/chrome-agent-bridge/chrome-agent-control"><img src="https://agentmods.dev/badge/skills/escapewu/chrome-agent-bridge/chrome-agent-control.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 | $0.00086 | $0.00769 |
| Opus 5 | $0.00043 | $0.00385 |
| Sonnet 5 | $0.00017 | $0.00154 |
| Haiku 4.5 | $0.00009 | $0.00077 |
Grade A, and why
chrome-agent-control 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 5d 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chrome Agent Control
Use chrome-agent-bridge when a task depends on the user's existing Chrome tabs or signed-in session. Prefer a dedicated connector or API when it can perform the semantic operation directly.
Start
- For supplied code, payloads, source-map text, or WASM files, load the matching local-analysis reference; no browser connection is required.
- Before a browser operation, call
browser_status. On failure, read connection-and-recovery.md. - Call
browser_list_tabsand select a current tab before any tab-scoped operation. Never guess a tab ID. - Load only the reference required by the task:
- Navigation, snapshots, screenshots, clicks, fills, or tab events: read page-control.md.
- Sanitized request lifecycle monitoring: read network-monitoring.md.
- Arbitrary CDP commands or original CDP events: read raw-cdp.md.
- Collected scripts, breakpoints, scopes, watches, or Webpack modules: read script-debugging.md, then follow its Raw CDP prerequisite.
- Source-map discovery, lookup, coverage, reconstruction, or diffing: read source-maps.md.
- CPU/heap/coverage/trace or unsanitized response bodies, HAR, auth, and interception: read performance-and-deep-network.md, then follow its Raw CDP prerequisite.
- Supplied JavaScript analysis or transformation: read code-analysis.md.
- Supplied binary, Protobuf, HTTP/2, gRPC, protocol, or WASM data: read protocol-and-wasm.md.
- Raw commands plus a sanitized network projection: read
network-monitoring.mdandraw-cdp.md; do not load the other references.
Do not read the entire references/ directory preemptively.
Treat the selected references as the authoritative Agent-facing tool contract. Do not inspect MCP source, repository README files, or installation docs during normal browser work; read installation docs only for setup or upgrade tasks.
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 289 B
- references/code-analysis.md 1.6 KB
- references/connection-and-recovery.md 1.5 KB
- references/network-monitoring.md 2.2 KB
- references/page-control.md 3.3 KB
- references/performance-and-deep-network.md 1.5 KB
- references/protocol-and-wasm.md 1.5 KB
- references/raw-cdp.md 1.9 KB
- references/script-debugging.md 1.4 KB
- references/source-maps.md 1.3 KB
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.
- 5d ago First seen · 40 lines · 86 tokens per session scan A c056b8c13066
chrome-agent-control is a skill published in the GitHub repository escapeWu/chrome-agent-bridge (3 stars, last pushed 24d ago), licensed MIT. It adds 86 tokens to every session and 769 once invoked, about $0.0004 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 skills, from other repositories
chrome-bridge
Recipes for the user's real, logged-in Chrome through the chrome-bridge MCP tools and the zero-token chrome-bridge CLI. Use whenever the user wants to test, debug, audit, compare or automate something in a browser — a form "until the email arrives", a checkout with a test card, a pixel/GTM check, a cookie-banner…
debug-codex-chrome-mcp
Diagnose ChromeWire MCP connection problems between MCP clients, the bridge, Chrome, and the official Codex Chrome Extension.
opencli-autofix
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.
moli-webfetch
Fetch, inspect, crawl, and capture live, JavaScript-rendered websites with Moli. Use when Codex needs current web content, web research, fact lookup, link following, a bounded crawl, client-rendered or response-gated content, network diagnostics, or a standalone HTML, Markdown, JSON, semantic-tree, viewport or…
moli-cdp-server
Start Moli's CDP server and connect Playwright, Puppeteer, or raw CDP clients. Use to run a headless-browser CDP endpoint, replace a Chromium process, attach over CDP, enable real layout and screenshot surfaces, or diagnose CDP discovery, connection, and target startup—even when Moli is not named.
aipex-browser
AI-powered browser automation using the AIPex Chrome Extension via MCP bridge. Use this skill when the agent needs to control a Chrome browser — navigating pages, clicking elements, filling forms, capturing screenshots, managing tabs, or downloading content — by connecting to the AIPex MCP bridge.