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 fanfan-de/anybox --skill chromegit clone --depth 1 https://github.com/fanfan-de/anyboxWrote 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/fanfan-de/anybox/chrome)<a href="https://agentmods.dev/skills/fanfan-de/anybox/chrome"><img src="https://agentmods.dev/badge/skills/fanfan-de/anybox/chrome.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 32 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00052 | $0.03639 |
| Opus 5 | $0.00026 | $0.01819 |
| Sonnet 5 | $0.00010 | $0.00728 |
| Haiku 4.5 | $0.00005 | $0.00364 |
Grade A, and why
Chrome 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 8d 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 — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chrome
Stop: choose the right surface before browser action
Explicit Chrome intent wins. If the user names Chrome or this plugin, asks to open or navigate to a page in Chrome, wants the page's visual or interactive state inspected, or requests UI interaction, continue with this skill and do not silently substitute another browser.
Otherwise, treat a URL or open tab as context rather than browser intent. Before each semantic operation on a linked resource, inspect available tools and use tool discovery when available to find an applicable connector, API, or CLI. Prefer that purpose-built surface when it can complete the operation. Use Chrome when no such surface exists, it lacks the required capability, existing Chrome state matters, or UI work remains.
Use this skill for navigating, inspecting visible page state, testing local web apps, clicking, filling, typing, scrolling, waiting for page changes, and taking screenshots.
Use only the Anybox Node REPL
Control Chrome only through the general-purpose Anybox Node REPL js tool. Its full Anybox tool ID normally resembles mcp__anybox_node_repl__js. Do not use per-action browser_* MCP tools, Computer Use, standalone Playwright, or another browser-control plugin for this Chrome surface.
The js_reset tool terminates and replaces the Node kernel, including globals, module cache, timers, and descendants. The kernel is also replaced when the Anybox session changes. The js_add_node_module_dir tool only changes CommonJS module resolution. Do not call either helper while trying to expose js.
Keep setup details internal. Unless the user asks about implementation, describe progress naturally as connecting to Chrome, inspecting the page, or retrying the connection.
The Browser Client sends only operations advertised by Browser Contract v4 to the plugin-owned Browser Host over authenticated local IPC. The client performs an early schema and capability check, and the Browser Host authoritatively validates every command again before it can reach Chrome. The general-purpose Node environment does not provide a browser host-service API; do not call or expect nodeRepl.requestHost(...).
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.
- 8d ago First seen · 286 lines · 52 tokens per session scan A fb038d610eed
Chrome is a skill published in the GitHub repository fanfan-de/anybox (57 stars, last pushed 25d ago), licensed MIT. It adds 52 tokens to every session and 3,639 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
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.
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…
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…