Borrowing it
Nothing to install: this file belongs to 23blocks-OS/ai-maestro. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/23blocks-OS/ai-maestro/main/.agents/skills/agent-browser/SKILL.mdgit clone --depth 1 https://github.com/23blocks-OS/ai-maestroWrote 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/23blocks-os/ai-maestro/agent-browser)<a href="https://agentmods.dev/skills/23blocks-os/ai-maestro/agent-browser"><img src="https://agentmods.dev/badge/skills/23blocks-os/ai-maestro/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/23blocks-os/ai-maestro/agent-browser"><img src="https://agentmods.dev/badge/skills/23blocks-os/ai-maestro/agent-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 | $0.00200 | $0.00864 |
| Opus 5.5 | $0.00080 | $0.00346 |
| Sonnet 5.5 | $0.00040 | $0.00173 |
| Haiku 4.5 | $0.00020 | $0.00086 |
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 18d 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.
This is a copy
100% identical to agent-browser — 9 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agent-browser
Fast browser automation CLI for AI agents. Chrome/Chromium via CDP with accessibility-tree snapshots and compact @eN element refs.
Install: npm i -g agent-browser && agent-browser install
Start here
This file is a discovery stub, not the usage guide. Before running any agent-browser command, load the actual workflow content from the CLI:
agent-browser skills get core # start here — workflows, common patterns, troubleshooting
agent-browser skills get core --full # include full command reference and templates
The CLI serves skill content that always matches the installed version, so instructions never go stale. The content in this stub cannot change between releases, which is why it just points at skills get core.
Always close your session
agent-browser leaves a Chrome process and a 50-500 MB temp profile behind when a session is not closed (or its daemon dies). On a host with many agents this fills the disk.
- Run
agent-browser closewhen you finish, including after an error. Do not leave a session open "for later". - Set a short idle timeout so a forgotten session ends by itself:
export AGENT_BROWSER_IDLE_TIMEOUT_MS=300000(5 minutes; the default is 1 hour, and0disables it). - Leftovers from crashed sessions are cleaned by
scripts/cleanup-agent-browser.shin the AI Maestro repo (dry run by default,--applyto act).
Specialized skills
Load a specialized skill when the task falls outside browser web pages:
agent-browser skills get electron # Electron desktop apps (VS Code, Slack, Discord, Figma, ...)
agent-browser skills get slack # Slack workspace automation
agent-browser skills get dogfood # Exploratory testing / QA / bug hunts
agent-browser skills get derive-client # Record a HAR, derive a standalone API client for a site
agent-browser skills get vercel-sandbox # agent-browser inside Vercel Sandbox microVMs
agent-browser skills get protected-vercel-deployments # Access protected Vercel deployments
agent-browser skills get agentcore # AWS Bedrock AgentCore cloud browsers
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.
- 18d ago Changed · +8 lines e830da36176b
- 26d ago Changed · -3 lines 3a7520e64de2
- 1mo ago First seen · 56 lines · 200 tokens per session scan A 00709861067d
agent-browser is a skill published in the GitHub repository 23blocks-OS/ai-maestro (836 stars, last pushed yesterday), licensed MIT. It adds 200 tokens to every session and 864 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to agent-browser, differing in 9 lines, and is treated as a copy.
Other skills, from other repositories
agent-browser
Drive a real browser to inspect or interact with a web page or app — navigate, take screenshots, read console and network, fill simple forms — for verification tasks, not unattended automation.
browser
Interactive browser automation via playwright-cli. Use when you need to navigate a site, click elements, fill forms, take snapshots, or triage a live app.
ui-visual-self-review
Use when you are about to hand off any UI change - the four-width check and the screenshot checklist that decide whether the screen is really done.
frontend-explorer
An exploratory browser test that uses a real browser and a first-time-user perspective to find where people get stuck or do not understand a web product. Each finding includes the text seen on screen and screenshot evidence, ordered by how much it blocks progress.
browser-use
Drives web pages with the browseruse tool through one checked pipeline - pick the right web tool, open the page in the chat's own tab, write down how the result will be checked, find elements by ref, act in small steps, read the page back, fix what differs, report only what the page shows. Explains which browser a…
eric-task-master
Run durable local Chrome automation with the installed Task Master CLI. Use when an Agent needs to create and execute a one-off browser task, follow its progress, or manage its Chrome Profile.