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 IceWhaleTech/ZimaOS-Blue --skill browsergit clone --depth 1 https://github.com/IceWhaleTech/ZimaOS-BlueWrote 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/icewhaletech/zimaos-blue/browser)<a href="https://agentmods.dev/skills/icewhaletech/zimaos-blue/browser"><img src="https://agentmods.dev/badge/skills/icewhaletech/zimaos-blue/browser/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/icewhaletech/zimaos-blue/browser"><img src="https://agentmods.dev/badge/skills/icewhaletech/zimaos-blue/browser.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 | $0.00036 | $0.00512 |
| Opus 5.5 | $0.00014 | $0.00205 |
| Sonnet 5.5 | $0.00007 | $0.00102 |
| Haiku 4.5 | $0.00004 | $0.00051 |
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 1mo 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.
What it actually says
Browser
Use browser when the job requires a live browser tab instead of ordinary fetch/read.
Routing Guide
| Need | Action |
|---|---|
| Public links, docs, or readable page content without interaction | Prefer web_query first |
| Logged-in readable page and existing session state is already available | Try authenticated read/fetch with Cookie, Authorization, or browser_target_id before full browser automation |
| Real interaction: click, type, scroll, login, form submit, screenshot, or challenge handling | Use blue browser ... |
| Existing Chrome session should be reused | Prefer relay/local Chrome or an existing browser target instead of a fresh anonymous tab |
Command Usage
blue browser navigate url=https://example.com
blue browser screenshot url=https://example.com full_page=true
blue browser click browser_target_id=tab_123 selector="text=Sign in"
blue browser type browser_target_id=tab_123 selector="input[type=email]" text="[email protected]"
blue browser scroll browser_target_id=tab_123 y=1200
Common parameters vary by action, but typical fields include:
urlfor opening a pagebrowser_target_idfor reusing an existing tab/sessionselectoror target metadata for click/type operationstextfor typed inputfull_pagefor screenshots
Notes
browseris the canonical interactive web skill.- Prefer
web_queryfor discovery or straightforward readable content; escalate tobrowseronly when a live session or interaction is truly required. - If
web_queryreportslogin_wall,challenge,browser_required, orretry_browser, first retry with session/auth reuse when possible and then switch tobrowser.
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.
- 1mo ago First seen · 54 lines · 36 tokens per session scan A 143684fba499
browser is a skill published in the GitHub repository IceWhaleTech/ZimaOS-Blue (28 stars, last pushed 2d ago), licensed MIT. It adds 36 tokens to every session and 512 once invoked, about $0.0001 per session on Opus 5.5. 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
defuddle
Extract clean Markdown from HTML pages with Defuddle CLI.
transcriptapi
Use when YouTube is or could be relevant — even if not mentioned: pasted video/channel/playlist links, video IDs, @handles, creator lookups, video summaries, quotes, translations, topic research, tutorials, talks, lectures, expert discussions, product reviews, how-to guides, new product announcements, or anything…
youtube-playlist
Use when a YouTube playlist is involved: pasted playlist links or IDs, requests to list playlist videos, browse playlist contents, or work through a playlist for transcripts or research. Also use when the user wants all videos from a series, course, or collection. Not for creating playlists or account management.
nearby-places-skill
Search for nearby places like restaurants, cafes, stores, and services using Google Places API. Find places by type and location.
browser-skill
Use a real web browser - read pages through their accessibility tree, click and type by reference, call the tools a site offers (WebMCP), and hand the page to the owner for logins, CAPTCHAs and final confirmations.
unbrowse
Search and call websites through Unbrowse's hosted API or remote MCP, reuse indexed site tools, read pages, and learn missing routes in its cloud browser. Use for structured website tasks, and authenticated site access with Unbrowse.