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 xuiltul/animaworks --skill agent-browsergit clone --depth 1 https://github.com/xuiltul/animaworksWrote 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/xuiltul/animaworks/agent-browser)<a href="https://agentmods.dev/skills/xuiltul/animaworks/agent-browser"><img src="https://agentmods.dev/badge/skills/xuiltul/animaworks/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/xuiltul/animaworks/agent-browser"><img src="https://agentmods.dev/badge/skills/xuiltul/animaworks/agent-browser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Rogue Agent · line 126 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00055 | $0.01099 |
| Opus 5.5 | $0.00022 | $0.00440 |
| Sonnet 5.5 | $0.00011 | $0.00220 |
| Haiku 4.5 | $0.00006 | $0.00110 |
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 20d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agent-browser — Browser Operation CLI
A headless browser automation tool from Vercel Labs. Can open web pages to interact, extract information, and take screenshots.
Installation
If not installed, run the following:
npm install -g agent-browser && agent-browser install
npm install -g agent-browser: Install the CLI itselfagent-browser install: Download Chrome for Testing (first time only; on Linux, add--with-deps)
Verify installation:
agent-browser --help
Basic Workflow
1. open <url> → ページを開く
2. snapshot -i → インタラクティブ要素のスナップショット取得（@e1, @e2 等のref付き）
3. click/fill/scroll → refを使って操作
4. snapshot -i → 操作後の状態を再確認
5. screenshot → 必要に応じてスクリーンショット保存
Important: Always obtain a ref via snapshot -i before any operation.
Command List
Navigation
agent-browser open <url>
agent-browser back
agent-browser forward
agent-browser reload
agent-browser close
Snapshot (Retrieve Page Structure)
agent-browser snapshot # 全体
agent-browser snapshot -i # インタラクティブ要素のみ（推奨）
agent-browser snapshot -c # コンパクト表示
agent-browser snapshot -d 3 # 深さ制限
Element Operations
agent-browser click @e1
agent-browser dblclick @e1
agent-browser fill @e2 "入力テキスト" # 既存テキストをクリアして入力
agent-browser type @e2 "追記テキスト" # 既存テキストに追記
agent-browser hover @e1
agent-browser check @e1 # チェックボックスON
agent-browser uncheck @e1 # チェックボックスOFF
agent-browser select @e1 "value" # プルダウン選択
agent-browser press Enter # キー入力
agent-browser scroll down 500 # スクロール
agent-browser scrollintoview @e1 # 要素が見えるまでスクロール
Waiting
agent-browser wait 1500 # ミリ秒待機
agent-browser wait @e1 # 要素が表示されるまで待機
agent-browser wait --text "成功" # テキストが出現するまで待機
agent-browser wait --load networkidle # ネットワーク待機
Information Retrieval
agent-browser get title # ページタイトル
agent-browser get url # 現在のURL
agent-browser get text @e1 # 要素のテキスト
agent-browser get value @e1 # 入力要素の値
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.
- 20d ago Changed · +1 lines · +14 tokens per session dcb5dd5aab02
- 1mo ago First seen · 145 lines · 41 tokens per session scan A 7b322d14daab
agent-browser is a skill published in the GitHub repository xuiltul/animaworks (267 stars, last pushed yesterday), licensed Apache-2.0. It adds 55 tokens to every session and 1,099 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.
Other skills, from other repositories
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.linkedin-automation
Read before automating LinkedIn with browser tools. LinkedIn combines shadow DOM (#interop-outlet), strict Trusted Types CSP that silently drops innerHTML, Lexical composer, native beforeunload dialogs that hang the bridge, and aggressive spam filters — each has bitten us at least once. Verified flows for profile…
hive.x-automation
Read before automating X / Twitter with browser tools. Verified flows for post, reply, delete, search-and-engage, plus the Draft.js compose quirks that silently disable the send button. Includes the daily-reply and job-market-reply playbooks. Requires hive.browser-automation for the underlying screenshot + coordinate…
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…
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
browser-automation
Playwright-based browser automation patterns for autonomous web interaction.