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 S3YED/appie-kit --skill agent-browsergit clone --depth 1 https://github.com/S3YED/appie-kitWrote 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/s3yed/appie-kit/agent-browser)<a href="https://agentmods.dev/skills/s3yed/appie-kit/agent-browser"><img src="https://agentmods.dev/badge/skills/s3yed/appie-kit/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/s3yed/appie-kit/agent-browser"><img src="https://agentmods.dev/badge/skills/s3yed/appie-kit/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 | $0.00069 | $0.00543 |
| Opus 5.5 | $0.00028 | $0.00217 |
| Sonnet 5.5 | $0.00014 | $0.00109 |
| Haiku 4.5 | $0.00007 | $0.00054 |
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 1mo 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agent-browser - fleet default for browser automation
A native-Rust browser-automation CLI designed for AI agents. Compact text output minimises context usage. Use it instead of heavier browser stacks for shell-driven web tasks.
Install
npm install -g agent-browser # all platforms
# or: brew install agent-browser # macOS
agent-browser install # download Chrome (first run only)
# try without installing:
npx agent-browser open example.com
Core loop (ref-based)
agent-browser open example.com
agent-browser snapshot -i # accessibility tree with refs: heading "..." [ref=e1], link "..." [ref=e2]
agent-browser click @e2 # act on a ref from the snapshot
agent-browser screenshot page.png
agent-browser close
Why refs (the context win)
snapshot returns a compact accessibility tree where each element has a ref (@e1, @e2):
- Context-efficient: ~200-400 tokens vs ~3000-5000 for full DOM.
- Deterministic: a ref points to the exact element from the snapshot (no fragile selectors).
- Fast: no DOM re-query. AI-friendly: text output parses naturally.
What it covers (50+ commands)
Navigation, forms, screenshots, network control, storage/cookies/auth-state, file upload/download, tabs, frames, debugging. Built-in: video recording, streaming, profiler, diffing. First-class docs for React/Web Vitals, init scripts, and Next.js + Vercel. Stateful: sessions, profiles, proxy, security controls - good for long-running agents.
Architecture
Client-daemon: a Rust CLI talks to a native Rust daemon that drives Chrome over CDP. The daemon starts automatically and persists between commands.
When to use vs other tools
- Default for shell-driven browser work (cheapest context, deterministic).
- Use Playwright/Stagehand only when you need their specific ecosystem features.
- Cross-platform: macOS (arm64/x64), Linux (arm64/x64), Windows (x64).
Works with: Claude Code, Cursor, Copilot, Codex, Gemini, opencode, and any agent that runs shell commands.
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.
- 1mo ago First seen · 46 lines · 69 tokens per session scan A a07edc80f057
agent-browser is a skill published in the GitHub repository S3YED/appie-kit (12 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 543 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
geo-review-html
Render an interactive, self-contained HTML companion for a GEO content brief (04-content-brief) or a publish-ready draft (05-production), so a NON-technical client reviewer (founder, organizer staff, the domain expert filling slots) can fill REQUIRED-FILL slots, leave section-level comments, and approve/return work in…
browser-app-delivery
Deliver a runnable local browser app so the user can operate it on the first handoff. This delivery skill does not choose whether a requested local system should be a browser app. On a current turn that explicitly says to implement a brand-new browser project now, load bundled:greenfield-project-scaffolding before…
hive.browser-automation
Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…
hive.slack-notifications-setup
Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…
ha-browser
Hope Agent browser automation — the standard status → tabs → snapshot → act loop, stale-ref recovery rules, and what to do when login / 2FA / captcha / camera-prompt / dialog blocks progress. Load this skill whenever you reach for the browser tool. Trigger on: user asks the agent to open / control / click / scrape /…
stealth-browser-mcp
Use this skill when operating stealth-browser-mcp from an AI agent or MCP client for browser automation, page inspection, element interaction, screenshots, file uploads, CDP commands, network debugging, cookies/storage, stealth setup, or reliable multi-step browser workflows. It provides the correct tool order, state…