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 ruizrica/agent-pi --skill agent-browsergit clone --depth 1 https://github.com/ruizrica/agent-piWrote 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/ruizrica/agent-pi/agent-browser)<a href="https://agentmods.dev/skills/ruizrica/agent-pi/agent-browser"><img src="https://agentmods.dev/badge/skills/ruizrica/agent-pi/agent-browser.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 155 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.
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 | $0.00137 | $0.02143 |
| Opus 5 | $0.00068 | $0.01071 |
| Sonnet 5 | $0.00027 | $0.00429 |
| Haiku 4.5 | $0.00014 | $0.00214 |
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 8d 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Automation with agent-browser
When to Use This Skill (IMPORTANT)
agent-browser is a LOCAL browser — it runs directly on this machine using a real Chromium instance. It can access:
- localhost / 127.0.0.1 (local dev servers, local APIs)
- Local network IPs (192.168.x.x, 10.x.x.x, etc.)
- Any remote URL (https://example.com, etc.)
- Local files (file:///path/to/file.html)
DO NOT use web_remote for localhost testing
The web_remote tool (formerly web_test) is a remote service powered by Cloudflare Browser Rendering. It runs on Cloudflare's servers and CANNOT reach localhost, 127.0.0.1, or any local network address. It will fail silently or error on local URLs.
| Scenario | Use This | NOT This |
|---|---|---|
| Test localhost:3000 | agent-browser |
|
| Test 127.0.0.1:8080 | agent-browser |
|
| Test local network device | agent-browser |
|
| Fill forms, click buttons | agent-browser |
|
| Multi-step browser workflow | agent-browser |
|
| Screenshot a public site (quick, no interaction) | agent-browser or web_remote |
— |
| Accessibility audit of public site | agent-browser or web_remote |
— |
Rule of thumb: Always prefer agent-browser. Use web_remote only when you need a quick remote screenshot/a11y audit and don't need any interaction.
Core Workflow
Every browser automation follows this pattern:
- Navigate:
agent-browser open <url> - Snapshot:
agent-browser snapshot -i(get element refs like@e1,@e2) - Interact: Use refs to click, fill, select
- Re-snapshot: After navigation or DOM changes, get fresh refs
agent-browser open https://example.com/form
agent-browser snapshot -i
# Output: @e1 [input type="email"], @e2 [input type="password"], @e3 [button] "Submit"
agent-browser fill @e1 "[email protected]"
agent-browser fill @e2 "password123"
agent-browser click @e3
agent-browser wait --load networkidle
agent-browser snapshot -i # Check result
What ships with it
10 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 9.3 KB
- references/proxy-support.md 4.6 KB
- references/session-management.md 4.2 KB
- references/snapshot-refs.md 4.2 KB
- references/video-recording.md 3.5 KB
- references/web-search.md 3.9 KB
- templates/authenticated-session.sh 3.2 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.
- 8d ago First seen · 244 lines · 137 tokens per session scan A 74a7ef64ab04
agent-browser is a skill published in the GitHub repository ruizrica/agent-pi (267 stars, last pushed 1mo ago), licensed MIT. It adds 137 tokens to every session and 2,143 once invoked, about $0.0007 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
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
playwright-cli
A command-line tool for controlling Chromium, Firefox, and WebKit browsers, including navigation, page interaction, screenshots, PDFs, and recorded actions.
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.
create-verification-skill
Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…