Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/full-stack-skills/agent-skills/basic-commandsgit clone --depth 1 https://github.com/full-stack-skills/agent-skillsWhat 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 | $0.00000 | $0.00587 |
| Opus 5 | $0.00000 | $0.00293 |
| Sonnet 5 | $0.00000 | $0.00117 |
| Haiku 4.5 | $0.00000 | $0.00059 |
Grade A, and why
basic-commands 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Basic Commands | 基础命令
官方文档: https://github.com/vercel-labs/agent-browser/blob/main/README.md
Instructions
This example demonstrates how to use basic agent-browser commands.
Key Concepts
- Navigation commands
- Interaction commands
- Input commands
- Form commands
- Mouse commands
Example: Navigation
# Open a URL (aliases: goto, navigate)
agent-browser open https://example.com
# Open with session
agent-browser open https://example.com --session my-session
Example: Clicking Elements
# Click an element using ref
agent-browser click @e1
# Click using CSS selector
agent-browser click button.submit
# Click using XPath
agent-browser click "//button[@type='submit']"
# Double-click
agent-browser dblclick @e2
# Right-click
agent-browser click @e3 --button right
Example: Typing and Filling
# Type text into an element
agent-browser type @e1 "Hello World"
# Fill an input field
agent-browser fill @e2 "[email protected]"
# Press a key
agent-browser press @e1 Enter
# Key down
agent-browser keydown @e1 Control
# Key up
agent-browser keyup @e1 Control
Example: Form Interactions
# Focus an element
agent-browser focus @e1
# Select an option
agent-browser select @e1 "Option 1"
# Check a checkbox
agent-browser check @e1
# Uncheck a checkbox
agent-browser uncheck @e1
Example: Mouse Actions
# Hover over an element
agent-browser hover @e1
# Scroll
agent-browser scroll @e1
# Scroll to element
agent-browser scroll @e1 --to
Example: Getting Element Information
# Get text content
agent-browser get text @e1
# Get attribute
agent-browser get attribute @e1 href
# Get property
agent-browser get property @e1 value
Example: Command Chaining
# Open page, then click
agent-browser open https://example.com && agent-browser click @e1
# Using session for state
agent-browser open https://example.com --session test
agent-browser click @e1 --session test
agent-browser fill @e2 "text" --session test
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.
- 2d ago First seen · 128 lines · 0 tokens per session scan A b14393218b30
basic-commands is a command published in the GitHub repository full-stack-skills/agent-skills (2 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 587 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
auto-browse
Auto-browse — learn, optimize, and graduate browser operations or web data-mining workflows.
research-perplexity
Run a deep research query using Perplexity's /research mode via Playwright browser automation. This is an alternative to /export-to-council that uses Perplexity's dedicated research mode instead of multi-model council.
review
Compare a reference design against an implementation. Accepts Figma URL, image file, or browser URL as reference.
graphify
Turn your vault into a clustered knowledge graph with HTML and JSON outputs.
laravel-playwright
E2E Playwright patterns; use the laravel:e2e-playwright skill exactly as written.
qa
Smoke or browser-walk a running app. Report only. Do not implement. Do not merge.