Agent skill

Agent Browser

by Chachamaru127 in Chachamaru127/claude-code-harness

Browser automation through the repo agent-browser CLI. An agent skill from Chachamaru127/claude-code-harness.

MITAuto-check: notesProductivity & Automation

Install Agent Browser

skills CLI
$ npx skills add Chachamaru127/claude-code-harness --skill agent-browser -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Chachamaru127/claude-code-harness agent-browser --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Chachamaru127/claude-code-harness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/agent-browser .claude/skills/agent-browser && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
agent-browser
GitHub stars
3.2k
Token cost
~1.1k tokens
SKILL.md length
198 words
Files
3 (incl. references)
Skills in repo
25
Repo updated
First seen
Licence
MIT

At a glance

Browser automation through the repo agent-browser CLI. An agent skill from Chachamaru127/claude-code-harness.

  • Works in 4 steps: agent-browser の確認 → ユーザーのリクエストを分類 → AI スナップショットワークフロー(推奨) → …
  • Tasks that involve Browser automation
  • SKILL.md covers トリガーフレーズ, 機能詳細, 実行手順 and クイックリファレンス, plus 3 more sections
  • Calls npm

What it does

Agent Browser is an agent skill from Chachamaru127/claude-code-harness. Browser automation through the repo agent-browser CLI. Explicit helper for navigation, forms, screenshots, scraping, and web-app checks. Prefer Browser Use or Playwright when available. Do NOT load for: sharing URLs, embedding links, or editing screenshot files.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/ai-snapshot-workflow.md` and `references/browser-automation.md`).

It sits in Productivity & Automation, covering Browser automation. It works with Playwright and Model Context Protocol. The repository describes itself as: Claude Code Dedicated Development Harness - Achieving High-Quality Development Through an Autonomous Plan→Work→Review Cycle. The licence is MIT.

When your agent uses it

  • Tasks that involve Browser automation

Example prompts

  • “/agent-browser”

Requirements

  • Node.js
  • Pre-approved tools (allowed-tools): Bash, Read

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. agent-browser の確認
  2. ユーザーのリクエストを分類
  3. AI スナップショットワークフロー(推奨)
  4. 結果の確認

What it can do on your machine

Read from SKILL.md and the folder at commit 2b2b748. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash
    • Read

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Agent Browser loads about 1.1k tokens when it runs, and up to ~4.4k if it reads all its reference files. Until then it costs about 69 tokens; SKILL.md has 198 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~69
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Read

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Chachamaru127/claude-code-harness at commit 2b2b748, republished under its MIT licence (© Chachamaru127). 198 words, ~1,059 tokens.

Download SKILL.mdSave it as .claude/skills/agent-browser/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
agent-browser
description
Browser automation through the repo agent-browser CLI. Explicit helper for navigation, forms, screenshots, scraping, and web-app checks. Prefer Browser Use or Playwright when available. Do NOT load for: sharing URLs, embedding links, or editing screenshot files.
allowed-tools
Bash, Read
description-en
Browser automation through the repo agent-browser CLI. Explicit helper for navigation, forms, screenshots, scraping, and web-app checks. Prefer Browser Use or…
description-ja
repo の agent-browser CLI でブラウザ操作を行う明示補助スキル。ページ遷移、フォーム、スクショ、スクレイピング、Webアプリ確認向け。利用可能なら Browser Use / Playwright を優先。URL共有、リンク埋め込み、スクショ画像編集には使わない。
user-invocable
false
disable-model-invocation
true
context
fork
argument-hint
[url] [--headless]

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

agent-browser が明示指定された時に使う補助スキル。以下は扱える操作の例であり、自動起動の条件ではない:

  • 「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
bash
# インストール確認
which agent-browser

# インストールを明示依頼され、未インストールの場合のみ
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:

bash
# 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 "user@example.com"
agent-browser fill @e4 "password123"
agent-browser click @e5           # Submit
Step 3: 結果の確認
bash
# 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 -cAI 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
ナビゲーション
コマンド説明
back戻る
forward進む
reloadリロード
情報取得
コマンド説明
get text @e1テキスト取得
get html @e1HTML 取得
get url現在の URL
get titleページタイトル
待機
コマンド説明
wait @e1要素を待機
wait 10001秒待機
デバッグ
コマンド説明
--headedブラウザを表示
consoleコンソールログ
errorsページエラー
highlight @e1要素をハイライト

セッション管理

複数のタブ/セッションを並列管理:

bash
# セッションを指定
agent-browser --session admin open https://admin.example.com
agent-browser --session user open https://example.com

# セッション一覧
agent-browser session list

# 特定セッションで操作
agent-browser --session admin snapshot -i -c

MCP ブラウザツールとの使い分け

ツール推奨度用途
agent-browser★★★明示指定された CLI によるスナップショット操作
chrome-devtools MCP★★☆Chrome が既に開いている場合
playwright MCP★★☆複雑な E2E テスト

原則: ユーザー指定のブラウザ経路を優先する。指定がなければ利用可能な Browser Use / Playwright 等の経路を使い、agent-browser の導入を前提にしない。


注意事項

  • agent-browser はヘッドレスモードがデフォルト
  • --headed オプションでブラウザを表示可能
  • セッションは明示的に close するまで維持される
  • 認証が必要なサイトはセッションを活用

© Chachamaru127, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in skills/agent-browser of Chachamaru127/claude-code-harness.

  • SKILL.md
  • references/ai-snapshot-workflow.md
  • references/browser-automation.md

Open the folder on GitHubat commit 2b2b748

Compare with similar skills

Agent Browser next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Agent Browser compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agent Browser this skillChachamaru127/claude-code-harness3.2k—~1.1kAutomated safety check: NotesMIT
Zerotoken OpenclawAMOS144/ZeroToken4551 repos~2.9kAutomated safety check: PassMIT
Browser MCP Agentantibrow/anti-detect-browser-skills9321 repos~4.2kAutomated safety check: WarnMIT
Browser AgentOyadotAI/oya-browser348—~2kAutomated safety check: PassCustom licence
Oya BrowserOyadotAI/oya-browser348—~2.1kAutomated safety check: PassCustom licence
Skillredf0x1/camofox-mcp117—~3.1kAutomated safety check: PassMIT

Similar skills

  • Zerotoken Openclaw

    AMOS144/ZeroToken

    A skill your agent uses when using ZeroToken MCP via OpenClaw for browser automation, trajectory recording and low-token replay, especially for recurring or scheduled browser tasks.

    455 GitHub starsUsed in 1 repo~2.9k tokens
    Productivity & AutomationAuto-check passed
  • Browser MCP Agent

    antibrow/anti-detect-browser-skills

    Give an AI agent its own real browser over MCP tool calls - launch, navigate, click, fill, screenshot, extract text, run JS - with a kernel-level real-device fingerprint and a persistent profile, so…

    932 GitHub starsUsed in 1 repo~4.2k tokens
    Productivity & AutomationAuto-check: warnings
  • Browser Agent

    OyadotAI/oya-browser

    Control a real browser via Oya Browser MCP tools. An agent skill from OyadotAI/oya-browser.

    348 GitHub stars~2k tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Oya Browser

    OyadotAI/oya-browser

    Drive real Chrome browsers through Oya Browser. An agent skill from OyadotAI/oya-browser.

    348 GitHub stars~2.1k tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Skill

    redf0x1/camofox-mcp

    Anti-detection browser automation MCP skill for OpenClaw agents with 47 tools for navigation, interaction, observation, extraction, downloads, profiles, sessions, and stealth web search.

    117 GitHub stars~3.1k tokensUpdated 1 mo ago
    Productivity & AutomationAuto-check passed
  • Vrbo

    borski/travel-hacking-toolkit

    Search VRBO (Vrbo / Expedia Group) vacation rentals including entire homes, condos, and cabins via Patchright browser automation.

    688 GitHub stars~1.7k tokensUpdated 3 days ago
    Productivity & AutomationAuto-check passed

More from Chachamaru127/claude-code-harness

All 25 skills in this repo
  • CI Failure Triage and Repair

    Chachamaru127/claude-code-harness

    Diagnoses failing CI pipelines and tests, deciding first whether the test or the implementation is at fault, and hands hard cases to a dedicated fixer subagent.

    3.2k GitHub starsUsed in 1 repo~1.1k tokens
    Auto-check: notes
  • Cursor Composer Task Delegate

    Chachamaru127/claude-code-harness

    Hands one implementation task to Cursor Composer in an isolated git worktree, then reviews its diff and cherry-picks the result into the main branch.

    3.2k GitHub stars~4.4k tokensUpdated 3 days ago
    Auto-check: notes
  • Acceptance Demo Generator

    Chachamaru127/claude-code-harness

    Renders a single HTML page showing each acceptance criterion as verified or not, with a ship, wait, or reject recommendation for non-engineers.

    3.2k GitHub stars~3.4k tokensUpdated 3 days ago
    Auto-check: notes
  • Harness Long-Running Task Loop

    Chachamaru127/claude-code-harness

    Repeats a long task as a series of scheduled wake-ups, each re-entering with fresh context and calling harness-work for one task per cycle.

    3.2k GitHub stars~2.3k tokensUpdated 3 days ago
    Auto-check: notes
  • Harness Plan

    Chachamaru127/claude-code-harness

    Creates and maintains Plans.md task plans with a spec delta, updates task markers and syncs plan progress with the implementation.

    3.2k GitHub stars~3.7k tokensUpdated 3 days ago
    Auto-check: notes
  • Harness Release

    Chachamaru127/claude-code-harness

    Runs a release for any project that keeps a Keep a Changelog file on GitHub, from version bump to merge, tag and GitHub Release after a single approval.

    3.2k GitHub stars~4.4k tokensUpdated 3 days ago
    Auto-check: notes

Questions about Agent Browser

What does Agent Browser do?

Browser automation through the repo agent-browser CLI. An agent skill from Chachamaru127/claude-code-harness. Agent Browser is an agent skill from Chachamaru127/claude-code-harness. Browser automation through the repo agent-browser CLI.

When should I use Agent Browser?

Agent Browser fits situations like: tasks that involve Browser automation.

How do I install Agent Browser in Claude Code?

Run `npx skills add Chachamaru127/claude-code-harness --skill agent-browser -a claude-code`. Or copy the skill folder (skills/agent-browser in Chachamaru127/claude-code-harness) into .claude/skills/agent-browser in your project. Claude Code loads it when a task matches its description.

How do I install Agent Browser in Codex?

Run `npx skills add Chachamaru127/claude-code-harness --skill agent-browser -a codex`. Or copy the skill folder (skills/agent-browser in Chachamaru127/claude-code-harness) into .agents/skills/agent-browser in your project. Codex loads it when a task matches its description.

Can I use Agent Browser in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Chachamaru127/claude-code-harness --skill agent-browser -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-browser, .gemini/skills/agent-browser, .github/skills/agent-browser and .opencode/skills/agent-browser in your project.

What does Agent Browser need to run?

Going by SKILL.md and its folder, Agent Browser needs the command-line tools its instructions call (npm). Our summary lists: Node.js. Its frontmatter pre-approves these tools: Bash, Read.

Does Agent Browser access the network?

SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Agent Browser safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Agent Browser use?

Agent Browser is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Agent Browser use?

About 1.1k tokens (SKILL.md is roughly 4.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.3k tokens, read only when the agent opens those files.

What are the alternatives to Agent Browser?

Skills that share tags, products or a category with Agent Browser: Zerotoken Openclaw (AMOS144/ZeroToken, 455 stars), Browser MCP Agent (antibrow/anti-detect-browser-skills, 932 stars), Browser Agent (OyadotAI/oya-browser, 348 stars) and Oya Browser (OyadotAI/oya-browser, 348 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agent Browser?

Chachamaru127 (a GitHub user) maintains it in Chachamaru127/claude-code-harness, which has 3,154 GitHub stars. The repository holds 25 skills in this directory. The repository was last updated on October 5, 2026.

Source: Chachamaru127/claude-code-harness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.