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 skills add leeguooooo/chrome-use --skill networkgit clone --depth 1 https://github.com/leeguooooo/chrome-useWrote 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/leeguooooo/chrome-use/network)<a href="https://agentmods.dev/skills/leeguooooo/chrome-use/network"><img src="https://agentmods.dev/badge/skills/leeguooooo/chrome-use/network/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/skills/leeguooooo/chrome-use/network"><img src="https://agentmods.dev/badge/skills/leeguooooo/chrome-use/network.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 | $0.00062 | $0.00760 |
| Opus 5.5 | $0.00025 | $0.00304 |
| Sonnet 5.5 | $0.00012 | $0.00152 |
| Haiku 4.5 | $0.00006 | $0.00076 |
Grade A, and why
network 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
chrome-use — Network Interception
Intercept, mock, rewrite, block, and record network traffic on the page you're driving — all via the CDP Fetch domain (no proxy, no extra extension permission).
Mock responses & rewrite requests
network route intercepts matching requests via the CDP Fetch domain (no proxy,
no extension permission). Three modes, verbs/fields mirror Playwright:
# Mock the RESPONSE (fulfill — the request never leaves the browser)
chrome-use network route "**/api/users" --body '{"users":[]}' --status 200 --content-type application/json
chrome-use network route "**/api/me" --body '{"vip":true}' --header X-From=mock
# Rewrite the outgoing REQUEST (continue with overrides — real response returns)
chrome-use network route "**/api/save" --method POST --set-header Authorization="Bearer test"
chrome-use network route "**/api/save" --set-body '{"x":1}' # replace the request body
chrome-use network route "**/v1/*" --rewrite-url https://staging.example.com/v1/thing
# Edit the REAL response (request goes out, response comes back, then tweak it)
chrome-use network route "**/api/me" --edit-status 503 # override status
chrome-use network route "**/api/me" --edit-header X-Env=test # add/override a response header
chrome-use network route "**/api/me" --replace 'prod=>staging' # substring-replace in the real body (repeatable)
# Block entirely
chrome-use network route "**/analytics" --abort
# Scope any rule to resource types, and inspect / record traffic
chrome-use network route "**/*.json" --abort --resource-type xhr,fetch
chrome-use network requests --clear # start capturing fresh
chrome-use network requests # inspect what fired
chrome-use network har start # record all traffic
# ... perform actions ...
chrome-use network har stop /tmp/trace.har
chrome-use network unroute # drop all routes
Three modes, distinguished by which flags you pass:
- Mock (
--body/--status/--header/--content-type): fulfill a fake response, short-circuit the request (never hits the network). - Rewrite request (
--method/--set-body/--set-header/--rewrite-url): change the outgoing request, then let the real response come back. - Edit real response (
--edit-status/--edit-header/--replace 'from=>to'): let the request go out, then tweak the real response before the page sees it. Great for forcing an error state or patching a field without a mock server.
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 Changed e754057a1526
- 1mo ago First seen · 58 lines · 62 tokens per session scan A 4686855af33a
network is a skill published in the GitHub repository leeguooooo/chrome-use (202 stars, last pushed today), licensed Apache-2.0. It adds 62 tokens to every session and 760 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It comes from a forked repository.
Other skills, from other repositories
surf
Control Chrome browser via CLI for testing, automation, and debugging. Use when the user needs browser automation, screenshots, form filling, page inspection, network/CPU emulation, DevTools streaming, or AI queries via ChatGPT/Gemini/Perplexity/Grok/AI Studio.
Agent Browser Automation
Fast Rust-based headless browser automation CLI with Node.js fallback for AI agents, featuring navigation, clicking, typing, snapshots, and structured commands optimized for agent workflows.
Browser-Use Automation
CLI tool for persistent browser automation with multi-session support, featuring Chromium/Real/Remote browser modes, cookie management, JavaScript execution, and long-running automation workflows.
cursor-browser
Drive Cursor IDE's built-in Browser Tab via cursor-browser-cli. Navigate, ref snapshots, click/type/fill/scroll/select-option by ref, wait-for, lock, screenshot, console/network/inspect. For Grok Build, Claude Code, Codex in Cursor terminal. Triggers: Cursor browser, Browser Tab, /cursor-browser, snapshot, under the…
wbrowser
Use when a task needs a browser that is already signed in — reading a dashboard, checking a web app, filling a form, taking a screenshot of a real page, or debugging a site's console. Drives a real Chrome window the user signed into by hand, so no re-login and no API keys. Do not guess selectors; run wb read first and…
ultimate-playwright
Browser automation via ultimate-playwright-mcp. Use when the agent needs to control a shared Chrome browser — open tabs, navigate, click, type, fill forms, take snapshots. Handles multi-user tab group isolation so multiple sessions can share one browser without interference. Use for web browsing, scraping, form…