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/chachamaru127/claude-code-harness/agent-browsernpx skills add Chachamaru127/claude-code-harness --skill agent-browsergit clone --depth 1 https://github.com/Chachamaru127/claude-code-harnessWrote 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/chachamaru127/claude-code-harness/agent-browser)<a href="https://agentmods.dev/skills/chachamaru127/claude-code-harness/agent-browser"><img src="https://agentmods.dev/badge/skills/chachamaru127/claude-code-harness/agent-browser.svg" alt="Measured on agentmods" 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 | $0.00053 | $0.01592 |
| Opus 5 | $0.00026 | $0.00796 |
| Sonnet 5 | $0.00011 | $0.00318 |
| Haiku 4.5 | $0.00005 | $0.00159 |
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 4d 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Browser Skill
ブラウザ自動化を行うスキル。agent-browser CLI を使用して、UI デバッグ・検証・自動操作を実行します。
トリガーフレーズ
このスキルは以下のフレーズで自動起動します：
- 「ページを開いて」「URLを確認して」
- 「クリックして」「入力して」「フォームに」
- 「スクリーンショットを撮って」
- 「UIを確認して」「画面をテストして」
- "open this page", "click on", "fill the form", "screenshot"
機能詳細
| 機能 | 詳細 |
|---|---|
| ブラウザ自動化 | See references/browser-automation.md |
| AI スナップショットワークフロー | See references/ai-snapshot-workflow.md |
実行手順
Step 0: agent-browser の確認
# インストール確認
which agent-browser
# 未インストールの場合
npm install -g agent-browser
agent-browser install
Step 1: ユーザーのリクエストを分類
| リクエストタイプ | 対応アクション |
|---|---|
| URL を開く | agent-browser open <url> |
| 要素をクリック | スナップショット → agent-browser click @ref |
| フォーム入力 | スナップショット → agent-browser fill @ref "text" |
| 状態確認 | agent-browser snapshot -i -c |
| スクリーンショット | agent-browser screenshot <path> |
| デバッグ | agent-browser --headed open <url> |
Step 2: AI スナップショットワークフロー（推奨）
ほとんどの操作で、まずスナップショットを取得してから要素参照で操作します：
# 1. ページを開く
agent-browser open https://example.com
# 2. スナップショット取得（AI 向け、インタラクティブ要素のみ）
agent-browser snapshot -i -c
# 出力例:
# - link "Home" [ref=e1]
# - button "Login" [ref=e2]
# - input "Email" [ref=e3]
# - input "Password" [ref=e4]
# - button "Submit" [ref=e5]
# 3. 要素参照で操作
agent-browser click @e2 # Login ボタンをクリック
agent-browser fill @e3 "[email protected]"
agent-browser fill @e4 "password123"
agent-browser click @e5 # Submit
Step 3: 結果の確認
# 現在の状態をスナップショットで確認
agent-browser snapshot -i -c
# または URL を確認
agent-browser get url
# スクリーンショットを取得
agent-browser screenshot result.png
クイックリファレンス
基本操作
| コマンド | 説明 |
|---|---|
open <url> |
URL を開く |
snapshot -i -c |
AI 向けスナップショット |
click @e1 |
要素をクリック |
fill @e1 "text" |
フォームに入力 |
type @e1 "text" |
テキストを入力 |
press Enter |
キーを押す |
screenshot [path] |
スクリーンショット |
close |
ブラウザを閉じる |
What ships with it
2 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.
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.
- 4d ago First seen · 188 lines · 53 tokens per session scan A 3414853814ba
agent-browser is a skill published in the GitHub repository Chachamaru127/claude-code-harness (3,082 stars, last pushed 3d ago), licensed MIT. It adds 53 tokens to every session and 1,592 once invoked, about $0.0003 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
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.
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
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.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…
web-browser
Automate and interact with web pages through Chrome or Chromium using the Chrome DevTools Protocol (CDP): navigate, click, fill forms, inspect content, take screenshots, and debug console or network activity. Use when an agent needs a real browser. Prefer headless Chrome unless visible browser interaction is required.