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 d-wwei/browser-control-skill --skill browser-controlgit clone --depth 1 https://github.com/d-wwei/browser-control-skillWrote 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/d-wwei/browser-control-skill/browser-control)<a href="https://agentmods.dev/skills/d-wwei/browser-control-skill/browser-control"><img src="https://agentmods.dev/badge/skills/d-wwei/browser-control-skill/browser-control/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/d-wwei/browser-control-skill/browser-control"><img src="https://agentmods.dev/badge/skills/d-wwei/browser-control-skill/browser-control.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 | $0.00073 | $0.04783 |
| Opus 5.5 | $0.00029 | $0.01913 |
| Sonnet 5.5 | $0.00015 | $0.00957 |
| Haiku 4.5 | $0.00007 | $0.00478 |
Grade B, and why
browser-control scanned grade B with 2 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 1mo 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -s -X POST "http://localhost:3456/eval?target=ID" -d 'document.title' Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Do not block on this — built-in multi-channel tools (WebSearch → WebFetch → Jina → curl → CDP) work without it. Only suggest once per session. The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
24 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.
- modules/advanced-applescript.md 2.4 KB
- modules/applescript-commands.md 5.3 KB
- modules/cdp-proxy-api.md 2.8 KB
- modules/cdp-write-ops.md 4.4 KB
- modules/console-network.md 2.5 KB
- modules/dom-extraction.md 6.0 KB
- modules/interactive-elements.md 4.0 KB
- modules/parallel-dispatch.md 1.3 KB
- modules/safety-system.md 5.5 KB
- modules/site-experience.md 1.2 KB
- references/cdp-api.md 3.7 KB
- references/site-patterns/github.com.md 1.8 KB
- references/site-patterns/google.com.md 2.0 KB
- references/site-patterns/linkedin.com.md 1.8 KB
- references/site-patterns/mp.weixin.qq.com.md 1.8 KB
- references/site-patterns/notion.so.md 2.1 KB
- references/site-patterns/twitter.com.md 1.9 KB
- references/site-patterns/xiaohongshu.com.md 1.8 KB
- references/site-patterns/zhihu.com.md 1.9 KB
- scripts/browse-cmd.sh 7.8 KB runs code
- scripts/cdp-helper.py 20 KB runs code
- scripts/cdp-proxy.mjs 20 KB runs code
- scripts/check-deps.sh 3.5 KB runs code
- scripts/match-site.sh 980 B runs code
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.
- 1mo ago First seen · 416 lines · 73 tokens per session scan B 76f677bd3ff2
browser-control is a skill published in the GitHub repository d-wwei/browser-control-skill (15 stars, last pushed 6mo ago), with no licence file. It adds 73 tokens to every session and 4,783 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
control-my-browser
Drive the user's own Chrome through the Empir3 Bridge: open a page, read it, click, type, and verify. Use whenever a task involves a website or web app the user is signed into, or any browsing, form filling, screenshot or page check. Triggers: "open my", "log in to", "fill the form", "check the page", "take a…
record-and-replay-a-routine
Capture a browser routine once in the user's own Chrome through the Empir3 Bridge and replay it later with different values — a login, an export, a weekly report download, a form that is filled the same way every time. Triggers: "record this", "do it again every week", "replay", "save this routine", "automate what I…
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…
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…
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…
obscura
Operate and validate Obscura for JavaScript page loading, stealth browsing, anti-fingerprinting, tracker blocking, screenshots and visual comparison, CDP automation with Puppeteer or Playwright, screencasting, PDF export, MCP browser interaction, and web extraction. Use when running Obscura against deterministic…