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 agentmods add skills/suge8/bao/agent-browsernpx skills add Suge8/Bao --skill agent-browsergit clone --depth 1 https://github.com/Suge8/BaoWrote 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/suge8/bao/agent-browser)<a href="https://agentmods.dev/skills/suge8/bao/agent-browser"><img src="https://agentmods.dev/badge/skills/suge8/bao/agent-browser.svg" alt="Measured on agentmods" 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 | $0.00019 | $0.03152 |
| Opus 5 | $0.00010 | $0.01576 |
| Sonnet 5 | $0.00004 | $0.00630 |
| Haiku 4.5 | $0.00002 | $0.00315 |
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 5d 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 — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Automation with agent-browser
Preferred path in Bao
If agent_browser is present in ## Available Now, use that tool instead of composing shell commands yourself.
Use this skill to understand the workflow and command vocabulary behind the tool, or to debug the underlying CLI behavior when needed.
Runtime
Bao desktop builds should prefer the bundled managed browser runtime.
Source / CLI environments can still use this workflow, but they must provide a browser runtime explicitly
for Bao to call. The recommended testing path is to point BAO_BROWSER_RUNTIME_ROOT at a prepared runtime
directory instead of assuming a global agent-browser binary on PATH.
Quick start
Preferred Bao tool call shape:
{"action":"open","args":["https://example.com"]}
{"action":"snapshot"}
{"action":"click","args":["@e1"]}
{"action":"fill","args":["@e2","hello"]}
{"action":"close"}
Underlying CLI equivalent:
agent-browser open <url> # Navigate to page
agent-browser snapshot -i # Get interactive elements with refs
agent-browser click @e1 # Click element by ref
agent-browser fill @e2 "text" # Fill input by ref
agent-browser close # Close browser
Core workflow
- Navigate to the page.
- Snapshot the page structure and interactive refs.
- Interact using refs from the latest snapshot.
- Re-snapshot after navigation or significant DOM changes.
In Bao, the same loop maps naturally to:
agent_browser(action="open", args=[url])agent_browser(action="snapshot")agent_browser(action="click"|"fill"|..., args=[...])agent_browser(action="snapshot")again when the page changed
Commands
Navigation
agent-browser open <url> # Navigate to URL (aliases: goto, navigate)
# Supports: https://, http://, file://, about:, data://
# Auto-prepends https:// if no protocol given
agent-browser back # Go back
agent-browser forward # Go forward
agent-browser reload # Reload page
agent-browser close # Close browser (aliases: quit, exit)
agent-browser connect 9222 # Connect to browser via CDP port
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 4.3 KB
- references/proxy-support.md 4.2 KB
- references/session-management.md 3.8 KB
- references/snapshot-refs.md 4.0 KB
- references/video-recording.md 3.2 KB
- templates/authenticated-session.sh 4.1 KB runs code
- templates/capture-workflow.sh 1.9 KB runs code
- templates/form-automation.sh 1.6 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.
- 5d ago First seen · 391 lines · 19 tokens per session scan A a08ad64bd5a1
agent-browser is a skill published in the GitHub repository Suge8/Bao (23 stars, last pushed 5mo ago), licensed MIT. It adds 19 tokens to every session and 3,152 once invoked, about $0.0001 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
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
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.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…