Borrowing it
Nothing to install: this file belongs to Chachamaru127/codex-harness. 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/Chachamaru127/codex-harness/main/.codex/skills/agent-browser/SKILL.mdgit clone --depth 1 https://github.com/Chachamaru127/codex-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/codex-harness/agent-browser)<a href="https://agentmods.dev/skills/chachamaru127/codex-harness/agent-browser"><img src="https://agentmods.dev/badge/skills/chachamaru127/codex-harness/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/chachamaru127/codex-harness/agent-browser"><img src="https://agentmods.dev/badge/skills/chachamaru127/codex-harness/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 | $0.00120 | $0.01734 |
| Opus 5.5 | $0.00048 | $0.00694 |
| Sonnet 5.5 | $0.00024 | $0.00347 |
| Haiku 4.5 | $0.00012 | $0.00173 |
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.
This is a copy
100% identical to agent-browser-chachamaru127-claude-code-harness-4 — 189 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 — 187 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
3 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.
- 1mo ago First seen · 187 lines · 120 tokens per session scan A 81fcb79558c2
agent-browser is a skill published in the GitHub repository Chachamaru127/codex-harness (2 stars, last pushed 8mo ago), licensed MIT. It adds 120 tokens to every session and 1,734 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to agent-browser-chachamaru127-claude-code-harness-4, differing in 189 lines, and is treated as a copy.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
Log a CLI in with a browser/device-code flow (aws sso, gh, glab, gcloud, …) and save the result to the keychain so later commands can request it through execute.credentials.
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.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
open-design-browser
Inspect and exercise local HTML design artifacts and library prototype previews with the existing agent-browser CLI, including screenshots, interaction checks, and rendered DOM snapshots. Use when rendered evidence helps author or review a design; excludes browser installation, remote services, and unrelated browser…