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 web-searchgit 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/web-search)<a href="https://agentmods.dev/skills/thewolffish/wolffish-app/web-search"><img src="https://agentmods.dev/badge/skills/thewolffish/wolffish-app/web-search/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/web-search"><img src="https://agentmods.dev/badge/skills/thewolffish/wolffish-app/web-search.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 | $0.00020 | $0.01699 |
| Opus 5 | $0.00010 | $0.00849 |
| Sonnet 5 | $0.00004 | $0.00340 |
| Haiku 4.5 | $0.00002 | $0.00170 |
Grade A, and why
web-search 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 9d 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Search
Tools
web_search— search the web, returns titles + snippets + URLsweb_fetch— fetch and read full page content from a URL
Search is one of three routes — pick deliberately
These two tools are not the only way to reach the web, and often not the best one. The third is the browser extension (tool_activate("browser-extension")), which drives the user's real browser.
| reaches | costs | |
|---|---|---|
web_search |
an index — snippets, never a page | real money per query; very fast |
web_fetch |
whatever a server returns to a bare GET | free, instant; blind to JS, paywalls, logins, bot checks |
| browser extension | essentially any page the user can open, and can click/scroll/fill | more tokens, more seconds; needs a connected browser |
Lean toward the browser whenever the task names a specific site, needs a logged-in or paid-for page, needs interaction, spans more than a page or two, or when a fetch came back thin. Two failed fetches cost more than opening the browser would have. Nothing here is a rule — weigh it yourself; these are the trade-offs to weigh.
When to use web_search
Use web_search when the user:
- Asks about current events, recent news, or anything time-sensitive
- Needs documentation or reference material
- Asks "what is X", "who is X", or "how to do X" and you aren't confident in your answer
- Wants to look something up, find a link, or research a topic
- Asks about something you don't have reliable knowledge about
- Needs live data (prices, weather, scores, stock info)
When to use web_fetch
Use web_fetch after web_search when:
- The snippets from search results aren't enough to fully answer the question
- You need to read an article, documentation page, or reference in detail
- The user explicitly asks you to read or visit a specific URL
Fetch the most relevant 1–2 URLs, not all of them. Never fetch more than 3 pages in one conversation turn.
Read what comes back before trusting it. A page that returns a few hundred characters, a cookie banner, "enable JavaScript", a login form, or a subscribe wall did not actually load — it just failed quietly with a 200. Don't re-fetch it and don't answer from the fragment: that page is a job for the browser extension, which renders it as the user's own browser would. The same goes for any site you already know is JS-rendered or gated.
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.
- 9d ago First seen · 208 lines · 20 tokens per session scan A f82ef3071259
web-search is a skill published in the GitHub repository thewolffish/wolffish-app (5 stars, last pushed 3d ago), licensed MIT. It adds 20 tokens to every session and 1,699 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
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.