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/crearize/ai-dev-helm/browser-agentnpx skills add Crearize/ai-dev-helm --skill browser-agentgit clone --depth 1 https://github.com/Crearize/ai-dev-helmWhat 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 | $0.00072 | $0.01077 |
| Opus 5 | $0.00036 | $0.00539 |
| Sonnet 5 | $0.00014 | $0.00215 |
| Haiku 4.5 | $0.00007 | $0.00108 |
Grade A, and why
browser-agent 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 3d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Agent Skill - agent-browser CLIによるUI検証
前提条件
agent-browserがインストール済み（npm install -g agent-browser && agent-browser install）- フロントエンドとバックエンドが起動済み（server-startupスキル参照）
Core Workflow
open → snapshot → screenshot → 操作 → snapshot → screenshot
必ず snapshot（構造確認）と screenshot（視覚確認）の両方 を取る。
Quick Reference
# 基本操作
agent-browser open <url> # ページを開く
agent-browser snapshot # アクセシビリティツリー（ref付き）を取得
agent-browser screenshot # 現在のビューポートをキャプチャ
agent-browser screenshot --full # フルページキャプチャ
agent-browser screenshot --annotate # 要素ラベル付きキャプチャ
# 操作
agent-browser fill <sel> "text" # クリア後入力
agent-browser click <sel> # クリック
agent-browser select <sel> "option" # セレクト
agent-browser press Enter # キー入力
# 待機
agent-browser wait --load networkidle # ネットワーク安定待ち
agent-browser wait <selector> # 要素出現待ち
agent-browser wait --text "Welcome" # テキスト出現待ち
# 検査
agent-browser get text <sel> # テキスト取得
agent-browser get url # 現在のURL
agent-browser errors # エラー確認
# セマンティック検索
agent-browser find role button click --name "Submit"
agent-browser find text "Sign In" click
agent-browser find label "Email" fill "[email protected]"
# ビューポート
agent-browser set viewport 375 812 # モバイル（iPhone）
agent-browser set viewport 768 1024 # タブレット
agent-browser set viewport 1280 720 # デスクトップ
# 状態リセット
agent-browser close # ブラウザを閉じる
検証チェックリスト
1. 表示確認（必須）
agent-browser open <url>
agent-browser wait --load networkidle
agent-browser screenshot --full
agent-browser snapshot
agent-browser errors
agent-browser close # 検証完了後に必ず実行
2. インタラクション検証（フォーム/ボタンがある場合）
# 正常系
agent-browser fill '[data-testid="email-input"]' "[email protected]"
agent-browser click '[data-testid="submit-button"]'
agent-browser wait --load networkidle
agent-browser screenshot
# 異常系
agent-browser open <url>
agent-browser fill '[data-testid="email-input"]' "invalid"
agent-browser click '[data-testid="submit-button"]'
agent-browser screenshot
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.
- 3d ago First seen · 116 lines · 72 tokens per session scan A d645c703cd11
browser-agent is a skill published in the GitHub repository Crearize/ai-dev-helm (4 stars, last pushed 8d ago), licensed MIT. It adds 72 tokens to every session and 1,077 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
electron
Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include…
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.
playwright
Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via playwright-cli or the bundled wrapper script.
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.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.