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 agentmods add skills/thewolffish/wolffish-app/browsernpx skills add thewolffish/wolffish-app --skill browsergit 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)<a href="https://agentmods.dev/skills/thewolffish/wolffish-app/browser"><img src="https://agentmods.dev/badge/skills/thewolffish/wolffish-app/browser.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.05279 |
| Opus 5 | $0.00014 | $0.02639 |
| Sonnet 5 | $0.00006 | $0.01056 |
| Haiku 4.5 | $0.00003 | $0.00528 |
Grade A, and why
browser 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 6d 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 — 739 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Automation
Interface
- Tools: 22 tools for launching, navigating, interacting, extracting, and managing browser sessions
- Engine: Playwright (Chromium by default, Firefox and WebKit also available)
- Sessions: each
browser_launchcreates an isolated session; multiple sessions can run simultaneously - Tabs: each session can have multiple tabs via
browser_multi_tab
Safety — READ BEFORE EVERY USE
Terms of Service
ALWAYS warn the user before automating any website that this may violate that site's Terms of Service. Many platforms (Google, Facebook, LinkedIn, Amazon, Twitter/X, Instagram, banking sites) explicitly prohibit automated access. Violating ToS can result in account suspension or legal action. Let the user decide whether to proceed.
Bot Detection
Browser automation is detectable by modern anti-bot systems (Cloudflare, reCAPTCHA, DataDome, PerimeterX, Akamai). Sites fingerprint automated browsers via WebDriver flags, headless detection, canvas fingerprinting, and behavioral analysis. Never promise undetectable automation.
CAPTCHAs
If a site presents a CAPTCHA, STOP and inform the user. Never attempt to solve or bypass CAPTCHAs.
Financial and Sensitive Sites
NEVER automate login to banking, financial, healthcare, or government sites unless the user explicitly acknowledges the risk after being warned. NEVER automate actions that could result in financial transactions (purchases, transfers, payments) without explicit per-action user approval.
Screenshots
When taking screenshots, warn the user if the page might contain sensitive information (banking dashboards, email inboxes, medical records).
Credential Handling — CRITICAL
Credentials must NEVER be written to any markdown file, episode, task log, memory, feedback, or conversation history.
Storing Credentials
When the user provides login credentials, immediately call browser_store_credential to store them securely. Never include raw credentials in any other tool call's arguments — always reference by credential_id.
What ships with it
3 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.
- 6d ago First seen · 739 lines · 28 tokens per session scan A 3d08faac1d91
browser is a skill published in the GitHub repository thewolffish/wolffish-app (5 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 5,279 once invoked, about $0.0001 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
Windows 桌面自动化执行规则。使用 screeninteractor 观察与操作原生桌面应用。.