Agent Browser
CLI cheat-sheet for scripted Playwright browser automation: navigate, fill, screenshot, extract
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 10, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · e366c49
Its snapshot workflow is built to return one targeted element instead of a 65KB accessibility-tree dump, but the sandbox blocked running the actual npm package, so that win could only be inferred, not confirmed.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 7/10
- Docs & honesty 4/5
What Agent Browser does
Documents the `agent-browser` CLI (open/snapshot/click/fill/screenshot/extract commands, refs, auth vault, cloud providers) for driving a real browser from the command line. Triggers when the user needs to navigate sites, fill forms, test a web app end-to-end, take screenshots, or scrape page data.
How to install Agent Browser
git clone https://github.com/code-yeongyu/oh-my-openagent
cd oh-my-openagent
mkdir -p ~/.claude/skills
cp -r packages/omo-opencode/src/features/builtin-skills/agent-browser ~/.claude/skills/agent-browser
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Agent Browser
-
/agent-browserCLI cheat-sheet for scripted Playwright browser automation: navigate, fill, screenshot, extract
It also activates on plain-language prompts like these:
-
Use the agent-browser CLI to fill out and submit this signup form -
Script a Playwright flow that logs in and screenshots the dashboard -
Extract all product prices from this page via agent-browser
Frequently asked questions
- Is the Agent Browser skill free?
- Yes. The skill itself is free from code-yeongyu/oh-my-openagent. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Agent Browser work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 10, 2026. Verdict: Tested · Works. Its snapshot workflow is built to return one targeted element instead of a 65KB accessibility-tree dump, but the sandbox blocked running the actual npm package, so that win could only be inferred, not confirmed.
- What is the Agent Browser SkillProof Score?
- 8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 4/5.
- How do I install Agent Browser?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Agent Browser with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.