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 thewolffish/wolffish-app --skill browser-extensiongit clone --depth 1 https://github.com/thewolffish/wolffish-appWrote 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/thewolffish/wolffish-app/browser-extension)<a href="https://agentmods.dev/skills/thewolffish/wolffish-app/browser-extension"><img src="https://agentmods.dev/badge/skills/thewolffish/wolffish-app/browser-extension/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/thewolffish/wolffish-app/browser-extension"><img src="https://agentmods.dev/badge/skills/thewolffish/wolffish-app/browser-extension.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 | $0.00072 | $0.11335 |
| Opus 5 | $0.00036 | $0.05667 |
| Sonnet 5 | $0.00014 | $0.02267 |
| Haiku 4.5 | $0.00007 | $0.01133 |
Grade A, and why
browser-extension 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 10d 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 — 1,115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Extension
Control the user's real browser (Chrome, Edge, Brave, Firefox, …) through the Wolffish extension. This operates in the user's actual browser — their cookies, logins, extensions, and open tabs are all available. Several browsers can be connected at the same time.
Tool Naming
All tools use the ext_ prefix. The wire protocol translates these to browser_ commands. For example ext_navigate sends browser_navigate to the extension.
Multiple browsers
The extension can be connected from several browsers at once (e.g. Chrome and Edge). Every connected browser is a fully separate world: its own tabs, tab ids, windows, cookie jars, logins, and its own debugger attachment.
- One browser connected — nothing to do; every
ext_*tool targets it automatically. - Several connected — each conversation drives exactly one browser at a time. Pick it with
ext_use_browser(the choice sticks for the rest of the conversation; call it again to switch). Until a browser is picked,ext_*tools return an error listing the connected browsers. - How to pick: if the user named a browser ("open it in Edge") or the context makes it obvious (the site is logged in only in Chrome, earlier in the conversation you were working in Brave), call
ext_use_browseryourself and briefly say which browser you're using. If there is no signal which browser the user means, ask them before acting. - Profiles: two Chrome profiles are two separate connections with separate logins.
ext_browsersreports each profile's signed-in email — use it to tell them apart ("work" vs "personal") and pass an email fragment toext_use_browserwhen the user means a specific profile. ext_browserslists what is connected (name, version, OS, profile email, selection key) — check it when unsure what's available.- Selection keys are stable while the app runs: a browser that reloads or reconnects keeps its key (chrome-2 stays the same profile). After an app restart keys may be assigned afresh — re-check
ext_browsersrather than assuming. - Never mix ids across browsers: a
tabIdfromext_tabs_listin Chrome is meaningless in Edge. After switching browsers, re-list tabs before acting on them.
What ships with it
2 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.
- 10d ago First seen · 1,115 lines · 72 tokens per session scan A 518353fb89e2
browser-extension is a skill published in the GitHub repository thewolffish/wolffish-app (5 stars, last pushed 3d ago), licensed MIT. It adds 72 tokens to every session and 11,335 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
agent-computer-use
REQUIRED for any task that involves operating a desktop application — opening apps, clicking buttons, typing into fields, pressing keys, scrolling, dragging, reading what's on screen, moving or resizing windows, or verifying state after an action. Always use the agent-cu CLI commands (open, snapshot, click, type, key…
macos-use
GUI control for macOS apps via mediar-ai's mcp-server-macos-use. Click, type, scroll, key-press, open apps — driven by accessibility tree, works in non-interactive Claude Code mode. Use this for any Sutando task that needs to drive another macOS application (Safari, Zoom, Mail, Finder, etc.).
test-ui
Test the BrowserOS app extension UI by starting the dev environment and visually verifying changes via CDP. Covers the new tab page (left sidebar — Home, Scheduled Tasks, Settings, etc.) and the right side panel (chat interface). Use after making UI changes to apps/app/.
ai-sdk
Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI…
browseros-neo
The user's dedicated browser for agents — a real browser signed into their accounts, with live logins and a persistent profile. Use it for any task that touches a website or browser (open, read, act, fill, sign in, download, verify). The user installed it precisely so agents default here unprompted — over in-app…
computer-use
A set of rules for controlling Windows desktop applications through screen observation and simulated mouse and keyboard actions. It also describes how to find and launch installed applications and verify the results.