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 yutori-ai/yutori-mcp --skill 03-browsegit clone --depth 1 https://github.com/yutori-ai/yutori-mcpWrote 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/yutori-ai/yutori-mcp/03-browse)<a href="https://agentmods.dev/skills/yutori-ai/yutori-mcp/03-browse"><img src="https://agentmods.dev/badge/skills/yutori-ai/yutori-mcp/03-browse/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/yutori-ai/yutori-mcp/03-browse"><img src="https://agentmods.dev/badge/skills/yutori-ai/yutori-mcp/03-browse.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00041 | $0.00437 |
| Opus 5 | $0.00020 | $0.00218 |
| Sonnet 5 | $0.00008 | $0.00087 |
| Haiku 4.5 | $0.00004 | $0.00044 |
Grade A, and why
yutori-browse 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 12d 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 Automation
Help the user automate browser-based tasks using Yutori's Navigator agent.
Process
-
Understand the task
- What website needs to be automated?
- What actions are required? (clicking, typing, extracting data)
- Does it require login or authentication?
-
Define the task clearly
- Break complex workflows into clear steps
- Specify what data to extract if applicable
- Note any buttons or elements to interact with
-
Start the browsing task Use
run_browsing_taskwith:task: Clear natural language instructionsstart_url: The URL to begin browsingmax_steps: 25 (default) to 100 for complex flowsrequire_auth: true: For login forms or other authenticated workflowsbrowser: "local": When the task should run through Yutori Local with the user's desktop sessionoutput_fields: For structured data extraction (e.g., ["name", "price", "url"])webhook_url: HTTPS URL for completion notificationwebhook_format:scout(default),slack, orzapier
-
Poll for results
- Browsing typically takes 30-120 seconds depending on complexity
- Use
get_browsing_task_resultto check status - Poll every 10-15 seconds until complete
-
Review and validate
- Check the extracted data or confirmation
- Verify the task completed as expected
Task Writing Tips
- Be specific about UI elements: "Click the blue 'Submit' button"
- Reference visible text when possible
- For forms, specify which fields get which values
$ARGUMENTS
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.
- 12d ago First seen · 50 lines · 41 tokens per session scan A 601e1dd63f61
yutori-browse is a skill published in the GitHub repository yutori-ai/yutori-mcp (24 stars, last pushed today), licensed Apache-2.0. It adds 41 tokens to every session and 437 once invoked, about $0.0002 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
site-audit
Use when user asks to audit a website, review all pages, check for broken links, capture full site state, or do a comprehensive product review.
kaboom
Use when user asks to check browser state, debug page errors, inspect network traffic, take screenshots, automate clicks or form fills, run accessibility or security audits, measure performance, generate tests, or record browser sessions. Trigger phrases: "check my browser", "debug this page", "take a screenshot"…
automate
Use when user asks to automate browser actions, click buttons, fill forms, navigate pages, run a sequence of browser steps, or build a repeatable workflow.
tutti-workspace-app-factory
Create, convert, or repair one Tutti workspace app as either a self-contained publishable package under package/ or a Chrome-style local debug app under .tutti/dev-app/. Use for mention://workspace-app-factory/create handoffs, mention://workspace-app-factory handoffs, standalone app generation, adapting existing…
h5i
Browse or automate web pages, perform authorized web security testing on captured HTTP traffic, or run untrusted development work inside disposable confined boxes with auditable evidence and reviewed export.
moai-platform-chrome-extension
Chrome Extension Manifest V3 development specialist covering service workers, content scripts, message passing, chrome. APIs, side panel, declarativeNetRequest, and Chrome Web Store publishing. Use when building browser extensions.