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 Advai-X/advai-skills --skill advai-browsergit clone --depth 1 https://github.com/Advai-X/advai-skillsWrote 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/advai-x/advai-skills/advai-browser)<a href="https://agentmods.dev/skills/advai-x/advai-skills/advai-browser"><img src="https://agentmods.dev/badge/skills/advai-x/advai-skills/advai-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/advai-x/advai-skills/advai-browser"><img src="https://agentmods.dev/badge/skills/advai-x/advai-skills/advai-browser.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 | $0.00044 | $0.01091 |
| Opus 5.5 | $0.00018 | $0.00436 |
| Sonnet 5.5 | $0.00009 | $0.00218 |
| Haiku 4.5 | $0.00004 | $0.00109 |
Grade A, and why
advai-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 2mo 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Advai Browser
Use this skill to operate a live browser through advai browser.
When to Invoke
Invoke this skill when the user wants to:
- Open or navigate real web pages
- Click, type, fill, select, or scroll in a browser
- Read DOM content, extract structured data, or execute JavaScript
- Capture screenshots, inspect cookies, or manage tabs
- Scrape public web content or validate browser-side behavior
Do not use this skill for static codebase inspection or for platforms that already have a more specific native skill.
Preconditions
Before running browser actions:
- This skill depends on the
advaiCLI fromhttps://github.com/Advai-X/advai-cli. - Ensure
advaiis installed and available on PATH. - Ensure the
advai browsersubcommand is available in the current installation. - If
advai browseris missing, stop and guide the user to install or upgradeadvaifromhttps://github.com/Advai-X/advai-clibefore continuing. - Ensure the browser extension/runtime is installed and connected.
- Start with:
advai browser doctor
If browser support is unavailable, surface the doctor output and explain what is missing.
Core Workflow
Use a named session for each task, for example demo, zhihu, checkout, or research.
Basic flow:
advai browser open demo https://example.com
advai browser wait demo --selector "h1"
advai browser get demo
advai browser exec demo "document.title"
Reuse the current tab instead of creating a new one:
advai browser open demo https://example.com --replace
Important behavior:
opencreates a new tab by defaultopen --replacereuses the current tab when the session already has one- If the session has no active page,
open --replacefalls back to opening a new tab - Tabs are not closed automatically after the action completes
Common Commands
Open and navigate:
advai browser open <session> <url>
advai browser open <session> <url> --replace
advai browser navigate <session> <url>
advai browser state <session>
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.
- 2mo ago First seen · 147 lines · 44 tokens per session scan A b6434a90c571
advai-browser is a skill published in the GitHub repository Advai-X/advai-skills (76 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 1,091 once invoked, about $0.0002 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.
advai-browser compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| advai-browserAdvai-X/advai-skills | Skill | 76 | 2mo ago | MIT | A | 44 | Claude Code, Codex |
| interactive-loginyc-software/qm | Skill | 16k | yesterday | MIT | A | 46 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 52 | Claude Code, Codex |
| azure-messaging-webpubsub-javamicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 43 | Claude Code |
| cua-driverdavidondrej/skills | Skill | 4.3k | 3d ago | MIT | A | 68 | Claude Code, Codex |
| open-design-browsercompozy/compozy | Skill | 2.8k | yesterday | MIT | A | 56 | Claude Code, Codex |
| southwestborski/travel-hacking-toolkit | Skill | 895 | yesterday | MIT | A | 40 | Claude Code |