Agent Browser Automation
withkynam/vibecode-pro-max-kit
Drives a browser through the agent-browser CLI, using compact snapshots with element refs to keep context small in long sessions, plus video recording and cloud browsers.
Automates a Chrome or Chromium browser through the agent-browser CLI: navigate, fill forms, click, screenshot and extract data using element refs.
Install Agent Browser CLI
$ npx skills add sipeed/picoclaw --skill agent-browser -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install sipeed/picoclaw agent-browser --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/sipeed/picoclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/workspace/skills/agent-browser .claude/skills/agent-browser && rm -rf skills-srcUse ~/.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/
Install the "agent-browser" agent skill from https://github.com/sipeed/picoclaw/tree/main/workspace/skills/agent-browser into .claude/skills/agent-browser/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-browser", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/sipeed/picoclaw/tree/main/workspace/skills/agent-browserType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add sipeed/picoclaw --skill agent-browser -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install sipeed/picoclaw agent-browser --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sipeed/picoclaw.git skills-src && mkdir -p .agents/skills && cp -r skills-src/workspace/skills/agent-browser .agents/skills/agent-browser && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "agent-browser" agent skill from https://github.com/sipeed/picoclaw/tree/main/workspace/skills/agent-browser into .agents/skills/agent-browser/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-browser", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add sipeed/picoclaw --skill agent-browser -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install sipeed/picoclaw agent-browser --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sipeed/picoclaw.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/workspace/skills/agent-browser .cursor/skills/agent-browser && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "agent-browser" agent skill from https://github.com/sipeed/picoclaw/tree/main/workspace/skills/agent-browser into .cursor/skills/agent-browser/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-browser", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/sipeed/picoclaw.git --path workspace/skills/agent-browser--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add sipeed/picoclaw --skill agent-browser -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install sipeed/picoclaw agent-browser --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sipeed/picoclaw.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/workspace/skills/agent-browser .gemini/skills/agent-browser && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "agent-browser" agent skill from https://github.com/sipeed/picoclaw/tree/main/workspace/skills/agent-browser into .gemini/skills/agent-browser/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-browser", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install sipeed/picoclaw agent-browserInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add sipeed/picoclaw --skill agent-browser -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/sipeed/picoclaw.git skills-src && mkdir -p .github/skills && cp -r skills-src/workspace/skills/agent-browser .github/skills/agent-browser && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "agent-browser" agent skill from https://github.com/sipeed/picoclaw/tree/main/workspace/skills/agent-browser into .github/skills/agent-browser/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-browser", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add sipeed/picoclaw --skill agent-browser -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install sipeed/picoclaw agent-browser --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sipeed/picoclaw.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/workspace/skills/agent-browser .opencode/skills/agent-browser && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "agent-browser" agent skill from https://github.com/sipeed/picoclaw/tree/main/workspace/skills/agent-browser into .opencode/skills/agent-browser/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-browser", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
agent-browser- GitHub stars
- 30k
- Token cost
- ~1.1k tokens
- SKILL.md length
- 138 words
- Files
- 1
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- MIT
At a glance
Automates a Chrome or Chromium browser through the agent-browser CLI: navigate, fill forms, click, screenshot and extract data using element refs.
- Works in 4 steps: agent-browser open — navigate → agent-browser snapshot -i — get… → Interact using refs — click @e1, fill… → …
- Navigating a website and filling in and submitting a form
- SKILL.md covers Core Workflow, Commands, Authentication and Iframes, plus 3 more sections
- Calls npm; reaches site-a.com and site-b.com
What it does
The skill drives a browser over CDP with the agent-browser command, installed with npm i -g agent-browser and then agent-browser install. It first checks that the tool exists with which. If it is missing, the agent tells you that the CLI and Chromium are only available in the heavy container image and does not try to install anything at runtime.
The core loop is to open a URL, take an interactive snapshot that lists elements with refs such as @e1, interact by ref with click and fill, and take a new snapshot after any navigation or DOM change because refs are invalidated. Commands can be chained with &&, iframe content is inlined in snapshots so no frame switch is needed, parallel sessions are named with a session flag, and eval runs JavaScript with a stdin option for complex code. Sessions should be closed when the work is done.
For sites that need a login, auth state can be saved from your running Chrome using an auto-connect option and loaded again in later sessions with a state flag.
When your agent uses it
- Navigating a website and filling in and submitting a form
- Taking screenshots or extracting data from a web page
- Testing a web app by clicking through it
- Reusing a logged-in Chrome session for automation
Example prompts
- “Open https://example.com/form, fill in the email and password fields and tell me what the page says after submit.”
- “Take a screenshot of the pricing page and extract the plan names.”
- “Run two sessions in parallel to compare site-a.com and site-b.com.”
Requirements
- The agent-browser CLI and Chromium, installed with npm i -g agent-browser and agent-browser install
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- agent-browser open — navigate
- agent-browser snapshot -i — get interactive elements with refs (@e1, @e2, ...)
- Interact using refs — click @e1, fill @e2 "text"
- Re-snapshot after any navigation or DOM change — refs are invalidated
What it can do on your machine
Read from SKILL.md and the folder at commit bbf6893. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
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
Hosts in commands or code, which the agent is likely to contact:
site-a.comsite-b.com
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 CLI loads about 1.1k tokens when it runs. Until then it costs about 45 tokens; SKILL.md has 138 words of instructions outside code blocks.
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 passed
The automated check found no risky patterns in SKILL.md.
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 sipeed/picoclaw at commit bbf6893, republished under its MIT licence (© sipeed). 138 words, ~1,059 tokens.
Download SKILL.mdSave it as
.claude/skills/agent-browser/SKILL.md (or your agent's skills folder).- name
- agent-browser
- description
- Browser automation via agent-browser CLI. Use when the user needs to navigate websites, fill forms, click buttons, take screenshots, extract data, or test web apps.
Agent Browser
CLI browser automation via Chrome/Chromium CDP. Install: npm i -g agent-browser && agent-browser install.
Before using this skill, verify the tool is available by running which agent-browser. If the command is not found, tell the user that browser automation requires the agent-browser CLI and Chromium, which are only available in the heavy container image. Do not attempt to install it at runtime.
Core Workflow
agent-browser open <url>— navigateagent-browser snapshot -i— get interactive elements with refs (@e1,@e2, ...)- Interact using refs —
click @e1,fill @e2 "text" - Re-snapshot after any navigation or DOM change — refs are invalidated
agent-browser open https://example.com/form
agent-browser snapshot -i
# @e1 [input] "Email", @e2 [input] "Password", @e3 [button] "Submit"
agent-browser fill @e1 "user@example.com"
agent-browser fill @e2 "secret"
agent-browser click @e3
agent-browser wait --load networkidle
agent-browser snapshot -iChain commands with && when you don't need intermediate output:
agent-browser open https://example.com && agent-browser wait --load networkidle && agent-browser snapshot -iCommands
# Navigation
agent-browser open <url>
agent-browser close
# Snapshot
agent-browser snapshot -i # Interactive elements with refs
agent-browser snapshot -s "#selector" # Scope to CSS selector
# Interaction (use @refs from snapshot)
agent-browser click @e1
agent-browser fill @e2 "text" # Clear + type
agent-browser type @e2 "text" # Type without clearing
agent-browser select @e1 "option"
agent-browser check @e1
agent-browser press Enter
agent-browser scroll down 500
# Get info
agent-browser get text @e1
agent-browser get url
agent-browser get title
# Wait
agent-browser wait @e1 # Wait for element
agent-browser wait --load networkidle # Wait for network idle
agent-browser wait --url "**/dashboard" # Wait for URL pattern
agent-browser wait --text "Welcome" # Wait for text
agent-browser wait 2000 # Wait ms
# Capture
agent-browser screenshot # Screenshot to temp dir
agent-browser screenshot --full # Full page
agent-browser screenshot --annotate # With numbered element labels ([N] -> @eN)
agent-browser pdf output.pdf
# Semantic locators (when refs unavailable)
agent-browser find text "Sign In" click
agent-browser find label "Email" fill "user@test.com"
agent-browser find role button click --name "Submit"Authentication
# Option 1: Import from user's running Chrome
agent-browser --auto-connect state save ./auth.json
agent-browser --state ./auth.json open https://app.example.com
# Option 2: Persistent profile
agent-browser --profile ~/.myapp open https://app.example.com/login
# ... login once, all future runs are authenticated
# Option 3: Session name (auto-save/restore)
agent-browser --session-name myapp open https://app.example.com/login
# ... login, close, next run state is restored
# Option 4: State file
agent-browser state save auth.json
agent-browser state load auth.jsonIframes
Iframe content is inlined in snapshots. Interact with iframe refs directly — no frame switch needed.
Parallel Sessions
agent-browser --session s1 open https://site-a.com
agent-browser --session s2 open https://site-b.com
agent-browser session listJavaScript Eval
agent-browser eval 'document.title'
# Complex JS — use --stdin to avoid shell quoting issues
agent-browser eval --stdin <<'EVALEOF'
JSON.stringify(Array.from(document.querySelectorAll("a")).map(a => a.href))
EVALEOFCleanup
Always close sessions when done:
agent-browser close
agent-browser --session s1 close© sipeed, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in workspace/skills/agent-browser of sipeed/picoclaw.
Open the folder on GitHubat commit bbf6893
Compare with similar skills
Agent Browser CLI 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Agent Browser CLI this skillsipeed/picoclaw | 30k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Agent Browser Automationwithkynam/vibecode-pro-max-kit | 1.1k | — | ~2.6k | Automated safety check: Pass | Apache-2.0 | |
| Electron Devtools Testingankitvgupta/exo | 496 | — | ~2.4k | Automated safety check: Pass | Custom licence | |
| Chrome Devtoolseinverne/dotfiles | 121 | 2 repos | ~1.6k | Automated safety check: Notes | Apache-2.0 | |
| Anti Detect Browserantibrow/anti-detect-browser-skills | 932 | — | ~9.8k | Automated safety check: Warn | MIT | |
| Reverse Browser Automationsickn33/agentic-awesome-skills | 47k | 1 repos | ~1.3k | Automated safety check: Pass | MIT |
Similar skills
Electron Devtools Testing
ankitvgupta/exo
Test the Electron app interactively using Chrome DevTools Protocol.
Chrome Devtools
einverne/dotfiles
Browser automation, debugging, and performance analysis using Puppeteer CLI scripts.
Anti Detect Browser
antibrow/anti-detect-browser-skills
Drive Chromium from standard Playwright APIs with a real-device fingerprint applied in the kernel, one persistent isolated profile per identity, and a per-profile proxy whose exit IP sets timezone…
Reverse Browser Automation
sickn33/agentic-awesome-skills
Automate browsers (Playwright) and Windows desktop applications (UI automation) for reverse-engineering evidence collection, UI-driven workflows, and network observation during analysis.
UI Preview
tingly-dev/tingly-box
Capture headless-Chrome screenshots of the tingly-box frontend (running locally in mock mode) so frontend changes can be visually verified in environments without a real browser.
More from sipeed/picoclaw
Picoclaw Skill Creator
sipeed/picoclaw
Guidance for creating, updating and reviewing Picoclaw skills, from the SKILL.md structure to organizing bundled scripts, references and assets.
Sipeed I2C and SPI Hardware Control
sipeed/picoclaw
Reads and controls I2C and SPI peripherals on Sipeed boards such as LicheeRV Nano, MaixCAM and NanoKVM through the i2c and spi tools.
PicoClaw Agent
sipeed/picoclaw
Answers questions about running and changing PicoClaw, from onboarding and model selection to MCP server setup, skill loading and scheduled jobs.
Weather Lookup
sipeed/picoclaw
Looks up current weather and forecasts with curl and verified location matching, using wttr.in for city names and Open-Meteo for structured data.
Related
Works with
Categories
Questions about Agent Browser CLI
What does Agent Browser CLI do?
Automates a Chrome or Chromium browser through the agent-browser CLI: navigate, fill forms, click, screenshot and extract data using element refs. The skill drives a browser over CDP with the agent-browser command, installed with npm i -g agent-browser and then agent-browser install. It first checks that the tool exists with which.
When should I use Agent Browser CLI?
Agent Browser CLI fits situations like: navigating a website and filling in and submitting a form; taking screenshots or extracting data from a web page; testing a web app by clicking through it; reusing a logged-in Chrome session for automation.
How do I install Agent Browser CLI in Claude Code?
Run `npx skills add sipeed/picoclaw --skill agent-browser -a claude-code`. Or copy the skill folder (workspace/skills/agent-browser in sipeed/picoclaw) into .claude/skills/agent-browser in your project. Claude Code loads it when a task matches its description.
How do I install Agent Browser CLI in Codex?
Run `npx skills add sipeed/picoclaw --skill agent-browser -a codex`. Or copy the skill folder (workspace/skills/agent-browser in sipeed/picoclaw) into .agents/skills/agent-browser in your project. Codex loads it when a task matches its description.
Can I use Agent Browser CLI 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 sipeed/picoclaw --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 CLI need to run?
Going by SKILL.md and its folder, Agent Browser CLI needs the command-line tools its instructions call (npm). Our summary lists: The agent-browser CLI and Chromium, installed with npm i -g agent-browser and agent-browser install.
Does Agent Browser CLI access the network?
SKILL.md names 2 domains. In commands or code: site-a.com and site-b.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.
Is Agent Browser CLI safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Agent Browser CLI use?
Agent Browser CLI 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 CLI 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.
What are the alternatives to Agent Browser CLI?
Skills that share tags, products or a category with Agent Browser CLI: Agent Browser Automation (withkynam/vibecode-pro-max-kit, 1.1k stars), Electron Devtools Testing (ankitvgupta/exo, 496 stars), Chrome Devtools (einverne/dotfiles, 121 stars) and Anti Detect Browser (antibrow/anti-detect-browser-skills, 932 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Agent Browser CLI?
sipeed (a GitHub organization) maintains it in sipeed/picoclaw, which has 30,010 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on September 24, 2026.
Source: sipeed/picoclaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.