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 ouro-ai-labs/ouro --skill agent-browsergit clone --depth 1 https://github.com/ouro-ai-labs/ouroWrote 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/ouro-ai-labs/ouro/agent-browser)<a href="https://agentmods.dev/skills/ouro-ai-labs/ouro/agent-browser"><img src="https://agentmods.dev/badge/skills/ouro-ai-labs/ouro/agent-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/ouro-ai-labs/ouro/agent-browser"><img src="https://agentmods.dev/badge/skills/ouro-ai-labs/ouro/agent-browser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Data Exfiltration · line 331 Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
- medium MCP Rug Pull · line 4 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Rogue Agent · line 518 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00108 | $0.04805 |
| Opus 5 | $0.00054 | $0.02403 |
| Sonnet 5 | $0.00022 | $0.00961 |
| Haiku 4.5 | $0.00011 | $0.00481 |
Grade A, and why
agent-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 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 — 553 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Automation with agent-browser
Anti-Detection (Bot Fingerprint Evasion)
When visiting sites with aggressive bot detection (e.g. xiaohongshu.com, ctrip.com, trip.com, taobao.com, jd.com), the default headless mode will be blocked. Always use --headed mode to avoid detection.
Use Headed Mode
The default headless Chromium exposes detectable fingerprints (navigator.webdriver, headless-specific WebGL/Canvas values, etc.). Using --headed launches a visible browser window that behaves like a normal user's browser.
agent-browser --headed open https://xiaohongshu.com
agent-browser snapshot -i
Login Strategy
When a site requires login, prefer these methods in order:
- SMS verification code (preferred) — fill in the user's phone number, ask the user for the verification code they receive, then complete login. This is the most reliable method and rarely triggers extra risk checks.
- QR code scanning (fallback) — switch to the QR code login tab, take a screenshot of the QR code, and send it to the user so they can scan it with their phone.
Avoid username/password login when possible — it is more likely to trigger CAPTCHAs and additional verification.
# SMS login flow
agent-browser --headed open https://xiaohongshu.com/login
agent-browser snapshot -i
# Switch to SMS login tab if needed
agent-browser click @e1
agent-browser snapshot -i
# Fill phone number (ask user for it)
agent-browser fill @e2 "13800138000"
agent-browser click @e3 # Send verification code
# Ask user for the SMS code they received, then fill it in
agent-browser fill @e4 "123456"
agent-browser click @e5 # Submit
agent-browser wait --url "**/explore" --timeout 60000
agent-browser state save xhs-auth.json
# QR code login flow (fallback)
agent-browser --headed open https://xiaohongshu.com/login
agent-browser snapshot -i
# Switch to QR code login tab
agent-browser click @e1
agent-browser wait 2000
# Capture the QR code and send to user
agent-browser screenshot qr-code.png
# Send qr-code.png to the user, then wait for them to scan
agent-browser wait --url "**/explore" --timeout 120000
agent-browser state save xhs-auth.json
What ships with it
8 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.
- references/authentication.md 4.9 KB
- references/commands.md 9.6 KB
- references/proxy-support.md 4.9 KB
- references/session-management.md 4.2 KB
- references/snapshot-refs.md 4.2 KB
- templates/authenticated-session.sh 3.3 KB runs code
- templates/capture-workflow.sh 1.8 KB runs code
- templates/form-automation.sh 1.8 KB runs code
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 · 553 lines · 108 tokens per session scan A 2aa9dd9e2f87
agent-browser is a skill published in the GitHub repository ouro-ai-labs/ouro (44 stars, last pushed 1mo ago), licensed MIT. It adds 108 tokens to every session and 4,805 once invoked, about $0.0005 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
cua-driver
Drive a native macOS app via the cua-driver CLI (default) or MCP server — snapshot its AX tree, click/type/scroll by elementindex, verify via re-snapshot. Use when the user asks you to operate, drive, automate, or perform a GUI task in a real macOS application on the host (e.g. "open a file in TextEdit", "navigate to…
control-browser
Research and inspect pages through Lime's managed browser session.
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…
dingtalk_channel_connect
Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.