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 yqi96/warranted --skill browsergit clone --depth 1 https://github.com/yqi96/warrantedWrote 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/yqi96/warranted/browser)<a href="https://agentmods.dev/skills/yqi96/warranted/browser"><img src="https://agentmods.dev/badge/skills/yqi96/warranted/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/yqi96/warranted/browser"><img src="https://agentmods.dev/badge/skills/yqi96/warranted/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 | $0.00028 | $0.01331 |
| Opus 5.5 | $0.00011 | $0.00532 |
| Sonnet 5.5 | $0.00006 | $0.00266 |
| Haiku 4.5 | $0.00003 | $0.00133 |
Grade A, and why
browser scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Prefer `wget`/`curl` once you've discovered the real file URL from the page, network activity, or page state. Only fall back to clicking a download button/link when the URL can't be recovered directly — click-driven down How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Skill
You are operating a real Chrome browser via the mcp__plugin_warranted_browser__* tools. Follow these rules strictly.
CRITICAL:
mcp__plugin_warranted_browser__*are MCP tools, NOT bash commands. Never usewhich,command -v, or any shell check to test their availability. Call them directly.
Core Workflow
0. Opening the browser
You MUST call mcp__plugin_warranted_browser__browser_open before any other tool. Each call spawns its own isolated chrome-devtools-mcp process (its own Chrome, its own temp profile) and returns a session_id. You MUST pass this session_id as _browser_session to every subsequent browser tool call — sessions are process-isolated, so one session crashing or navigating away never affects another.
mcp__plugin_warranted_browser__browser_open()
→ "Browser opened. Session: <uuid>"
Then use the returned session ID for all subsequent calls:
mcp__plugin_warranted_browser__navigate_page(type="url", url="https://example.com", _browser_session="<uuid>")
mcp__plugin_warranted_browser__take_screenshot(_browser_session="<uuid>")
Close the session when done — this kills that session's Chrome process:
mcp__plugin_warranted_browser__browser_close(session_id="<uuid>")
Navigating to a known URL
mcp__plugin_warranted_browser__navigate_page(type="url", url="https://example.com", _browser_session="<uuid>")
Clicking a link or button
Never fabricate or guess URLs. Always:
- Call
mcp__plugin_warranted_browser__take_snapshotto get the accessibility tree. - Find the element's
uidin snapshot output (uid=X_Y). - Call
mcp__plugin_warranted_browser__click(uid="X_Y", _browser_session="<uuid>").
Reading page content
- Visual check:
take_screenshot(preferred for multimodal reasoning) - Structure and links:
take_snapshot - Console/network state:
list_console_messages,list_network_requests
Filling forms
take_snapshotto find input uid.fill(uid="X_Y", value="text", _browser_session="<uuid>")press_key(key="Enter", _browser_session="<uuid>")or click submit.
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 · 117 lines · 28 tokens per session scan A 9477daf9d040
browser is a skill published in the GitHub repository yqi96/warranted (2 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 1,331 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-20.
Other skills, from other repositories
argument-mapping
Use this Skill to extract and visualize argument structure: Toulmin reconstruction, support/attack graph, circularity detection, argument scheme classification, and NLP-based premise extraction.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
lean-formalize
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific…
specification-writing
A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.