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 whit3rabbit/camoufox-mcp --skill camoufoxgit clone --depth 1 https://github.com/whit3rabbit/camoufox-mcpWrote 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/whit3rabbit/camoufox-mcp/camoufox)<a href="https://agentmods.dev/skills/whit3rabbit/camoufox-mcp/camoufox"><img src="https://agentmods.dev/badge/skills/whit3rabbit/camoufox-mcp/camoufox/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/whit3rabbit/camoufox-mcp/camoufox"><img src="https://agentmods.dev/badge/skills/whit3rabbit/camoufox-mcp/camoufox.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 | $0.00093 | $0.04535 |
| Opus 5 | $0.00046 | $0.02268 |
| Sonnet 5 | $0.00019 | $0.00907 |
| Haiku 4.5 | $0.00009 | $0.00453 |
Grade C, and why
camoufox scanned grade C with 1 finding 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 12d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
Native module errors such as `better-sqlite3` compiled for the wrong Node.js version (`NODE_MODULE_VERSION` mismatch) come from this server's own dependency tree: `camoufox-js` pulls in `better-sqlite3`, whose native bin How it starts
The opening of the file, as written. The whole thing — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Camoufox Browser Automation
Camoufox is a privacy-focused Firefox exposed through the camoufox-mcp-server MCP server. Reach for it when a plain HTTP fetch is not enough: JavaScript-rendered pages, bot walls, forms, multi-step flows, screenshots, or anything that benefits from a realistic browser fingerprint.
Every tool launches or reuses a real browser, so each call costs time and tokens. The whole skill is about getting the answer in the fewest, narrowest calls. Two habits do most of the work:
- Pick the narrowest tool for the question (see Choosing a Tool). A page's link list, headings, or one text match is far cheaper than its full rendered text.
- Bound every call. Set
maxChars,selector, oroutputMode: "metadata"so a giant page can't blow up your context.
This skill does not start the server. Confirm an MCP server named camoufox is available first. The installable plugin ships this config with unsafe browser options enabled so hard-site tuning can use firefox_user_prefs, args, and exclude_addons:
{
"mcpServers": {
"camoufox": {
"command": "npx",
"args": ["-y", "camoufox-mcp-server@latest"],
"env": { "CAMOUFOX_MCP_ALLOW_UNSAFE_OPTIONS": "1" }
}
}
}
Bare npx -y camoufox-mcp-server@latest remains safe by default unless the host config adds that env var.
On a fresh machine the first browse needs the Camoufox binary (~780MB), which npx installs do not prefetch. If a call returns Camoufox browser binary not installed. Run: npx -y [email protected] fetch, run that one-time command (it lands in the shared OS cache; do not omit the version pin) and retry.
Bring the Server Up (operator / local checkout)
npx camoufox-mcp-server@latest self-installs, but a local checkout or a first
run needs the browser binary fetched and a preflight before you trust it:
npm install # Node >=22 required
npm run build # compile dist/
npm run fetch:camoufox # download the Camoufox browser binary
npm run doctor # preflight: pins, cached binary, live browse smoke test
What ships with it
4 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.
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.
- 12d ago First seen · 311 lines · 93 tokens per session scan C 74410ded8768
camoufox is a skill published in the GitHub repository whit3rabbit/camoufox-mcp (46 stars, last pushed 2d ago), licensed MIT. It adds 93 tokens to every session and 4,535 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…