Steel CLI + Skill

Overview

@steel-dev/cli lets you run full browser workflows from the terminal, end-to-end. You can start a browser session, navigate pages, click/fill/type, extract content, and stop the session without wiring custom browser infrastructure.

What it enables:

• Run browser automation in cloud mode (default) or self-hosted/local mode
• Drive pages with terminal-first browser commands (open, snapshot, fill, click, etc.)
• Use API tools for scrape, screenshot, and pdf
• Bootstrap projects quickly with forge and run templates instantly with run

Under the hood, steel browser is directly integrated with the agent-browser runtime. That means Steel adds session lifecycle, auth, and endpoint routing while preserving familiar browser command behavior.

• GitHub: steel-dev/cli
• Package: npmjs.com/package/@steel-dev/cli

Documentation Index (for Agents)

If you are using an AI agent and want a complete docs index before exploring pages:

• https://docs.steel.dev/llms-full.txt

This returns a flattened, agent-friendly text map of the docs site.

Installation

Requirements:

• Node.js >=18

Install globally:

npm i -g @steel-dev/cli

Or run without global install:

npx @steel-dev/cli --help

Quick Start

Cloud Mode (Default)

steel login
steel browser start --session my-job
steel browser open https://example.com --session my-job
steel browser snapshot -i --session my-job
steel browser stop --session my-job

Self-Hosted Endpoint

steel browser start --api-url https://steel.your-domain.dev/v1 --session my-job
steel browser open https://example.com --api-url https://steel.your-domain.dev/v1 --session my-job

Local Runtime (localhost) Flow

steel dev install
steel dev start
steel browser start --local --session local-job
steel browser open https://example.com --session local-job
steel browser stop --session local-job
steel dev stop

Skills for Coding Agents

Steel ships a dedicated skill package for browser workflows:

• skills/steel-browser

This is designed for coding agents, including:

• Codex
• OpenCode
• OpenClaw
• Claude Code

Install from GitHub:

npx skills add github:steel-dev/cli/skills/steel-browser

Or from a local checkout:

npx skills add ./skills/steel-browser

After installation, restart your agent client so it can discover newly installed skills.

What this skill gives agents:

• Mode-aware command planning (cloud vs self-hosted)
• Named-session lifecycle discipline (start -> work -> stop)
• Reliable command patterns for steel browser passthrough actions
• Migration guidance from agent-browser
• Troubleshooting playbooks for auth/session/CAPTCHA failures

Typical Agent Skill Workflow

Most agent loops follow this pattern:

1. 1Start or attach a named session.
2. 2Open a page and inspect interactable elements (snapshot -i).
3. 3Perform actions (fill, select, check, click).
4. 4Wait for the post-action state and verify output.
5. 5Stop the session when done.

SESSION="signup-demo-$(date +%s)"
steel browser start --session "$SESSION"
steel browser open https://example.com/signup --session "$SESSION"
steel browser snapshot -i --session "$SESSION"
steel browser fill @e1 "Jane Doe" --session "$SESSION"
steel browser fill @e2 "jane@example.com" --session "$SESSION"
steel browser select @e3 "California" --session "$SESSION"
steel browser check @e4 --session "$SESSION"
steel browser click @e5 --session "$SESSION"
steel browser wait --load networkidle --session "$SESSION"
steel browser stop --session "$SESSION"

If you already know upstream agent-browser, the behavior is typically command-prefix only:

agent-browser open https://example.com/signup
agent-browser snapshot -i
agent-browser fill @e1 "Jane Doe"
agent-browser fill @e2 "jane@example.com"
agent-browser select @e3 "California"
agent-browser check @e4
agent-browser click @e5
agent-browser wait --load networkidle

Command Model

Steel-Owned Browser Lifecycle Commands

• steel browser start
• steel browser stop
• steel browser sessions
• steel browser live
• steel browser captcha solve

Inherited Browser Commands (Passthrough)

All non-lifecycle steel browser <command> calls are routed through the vendored agent-browser runtime.

Migration is usually command-prefix only:

• Before: agent-browser <command> ...
• After: steel browser <command> ...

Essential Inherited Commands

These are the most common inherited commands agents use:

• Page navigation: open, back, forward, reload
• Page understanding: snapshot, snapshot -i
• Interaction: click, fill, type, select, check, press, hover
• Data retrieval: get text, get html, get title, get url
• Synchronization: wait, wait --load networkidle, wait --text
• Debugging: screenshot, errors, console

Use command help directly when needed:

steel browser --help
steel browser click --help
steel browser wait --help

For full command references:

• Steel browser commands reference
• Steel browser session lifecycle reference

Command Overview

Common Workflows

1. Named Session Lifecycle

SESSION="job-$(date +%s)"
steel browser start --session "$SESSION"
steel browser open https://example.com --session "$SESSION"
steel browser snapshot -i --session "$SESSION"
steel browser get title --session "$SESSION"
steel browser stop --session "$SESSION"

2. CAPTCHA-Aware Sessions

# Manual solve mode
steel browser start --session my-job --session-solve-captcha
steel browser captcha solve --session my-job

# Auto solve mode (stealth preset)
steel browser start --session my-job --stealth

3. agent-browser Migration

# Before
agent-browser open https://example.com
agent-browser snapshot -i
agent-browser click @e3

# After
steel browser open https://example.com
steel browser snapshot -i
steel browser click @e3

4. API Tool Commands

# Scrape (markdown-first output by default)
steel scrape https://example.com

# Screenshot
steel screenshot https://example.com --full-page

# PDF
steel pdf https://example.com

forge and run (Templates)

Use forge to scaffold a project and run to execute templates instantly.

# Scaffold a project
steel forge playwright --name my-bot

# Run an instant task-oriented template flow
steel run browser-use --task "Research the latest browser automation libraries"

List all templates and flags:

steel forge --help
steel run --help

Endpoint Resolution

For browser lifecycle, passthrough bootstrap, and API tools (scrape, screenshot, pdf), endpoint selection is deterministic.

Self-hosted precedence:

1. 1--api-url <url>
2. 2STEEL_BROWSER_API_URL
3. 3STEEL_LOCAL_API_URL
4. 4browser.apiUrl in ~/.config/steel/config.json
5. 5http://localhost:3000/v1

Cloud precedence:

1. 1STEEL_API_URL
2. 2https://api.steel.dev/v1

Attach-flag override:

• If --cdp or --auto-connect is provided, Steel skips bootstrap injection and forwards passthrough arguments unchanged.

Auth, Config, and Updates

steel login
steel config
steel logout
steel settings
steel cache --clean
steel update
steel update --check
steel update --force

Disable auto-update checks (24-hour cache window):

steel run --no-update-check
STEEL_CLI_SKIP_UPDATE_CHECK=true steel run
CI=true steel run
NODE_ENV=test steel run

Runtime and Output Notes

• steel scrape defaults to markdown-first output; use --raw for full JSON payload.
• steel browser start and steel browser sessions return display-safe connect_url values with sensitive query parameters redacted.
• Browser command paths bypass auto-update checks to reduce interactive latency.

Troubleshooting

• Missing browser auth...: run steel login or set STEEL_API_KEY.
• Failed to reach Steel session API ...: confirm mode and endpoint settings (--local, --api-url, env vars).
• Session reuse issues: use a consistent --session <name> across every step.
• Local runtime issues: run steel dev install once, then steel dev start.
• Stale state: run steel browser stop --all and start a fresh named session.

References

• Steel CLI README
• Generated CLI Reference
• Steel Browser Reference
• Migration Guide (agent-browser -> steel browser)
• Steel Browser Skill Package