Actionbook is an AI agent that works inside a browser to read information behind logins, operate websites, and produce completed outputs such as reports, CSV files, and drafts. It is intended for people who want agents to automate authenticated web workflows, using direct requests when possible and browser interaction when necessary. The catalogue add-ons provide workflows and instructions for operating Actionbook.
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 skills add actionbook/actionbook --skill agent-browsergit clone --depth 1 https://github.com/actionbook/actionbookWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/actionbook/actionbook/agent-browser)<a href="https://agentmods.dev/skills/actionbook/actionbook/agent-browser"><img src="https://agentmods.dev/badge/skills/actionbook/actionbook/agent-browser/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/actionbook/actionbook/agent-browser"><img src="https://agentmods.dev/badge/skills/actionbook/actionbook/agent-browser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Memory Poisoning · line 14 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
What 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 5.1 | $0.00028 | $0.00637 |
| Opus 5.5 | $0.00011 | $0.00255 |
| Sonnet 5.5 | $0.00006 | $0.00127 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
agent-browser 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 1mo 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Automation with agent-browser
Quick start
agent-browser open <url> # Navigate to page
agent-browser snapshot -i # Get interactive elements with refs
agent-browser click @e1 # Click element by ref
agent-browser fill @e2 "text" # Fill input by ref
agent-browser close # Close browser
Core workflow
- Navigate:
agent-browser open <url> - Snapshot:
agent-browser snapshot -i(returns elements with refs like@e1,@e2) - Interact using refs from the snapshot
- Re-snapshot after navigation or significant DOM changes
- Always close:
agent-browser close
Commands
Navigation
agent-browser open <url> # Navigate to URL
agent-browser close # Close browser (ALWAYS do this)
Snapshot (page analysis)
agent-browser snapshot # Full accessibility tree
agent-browser snapshot -i # Interactive elements only (recommended)
Interactions (use @refs from snapshot)
agent-browser click @e1 # Click
agent-browser fill @e2 "text" # Clear and type
agent-browser type @e2 "text" # Type without clearing
agent-browser press Enter # Press key
agent-browser scroll down 500 # Scroll page
Get information
agent-browser get text @e1 # Get element text
agent-browser get title # Get page title
agent-browser get url # Get current URL
Wait
agent-browser wait @e1 # Wait for element
agent-browser wait 2000 # Wait milliseconds
agent-browser wait --load networkidle # Wait for network idle
Example: Form submission (request-website)
# Open Actionbook request page
agent-browser open "https://actionbook.app/request-website"
# Get form elements
agent-browser snapshot -i
# Output shows: textbox "Site URL" [ref=e1], textbox "Email" [ref=e2], textbox "Use Case" [ref=e3], button "Submit" [ref=e4]
# Fill form
agent-browser fill @e1 "https://example.com/products"
agent-browser fill @e2 "[email protected]"
agent-browser fill @e3 "Scraping product catalog"
# Submit
agent-browser click @e4
agent-browser wait --load networkidle
# Verify submission
agent-browser snapshot -i
# Close browser
agent-browser close
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.
- 1mo ago First seen · 103 lines · 28 tokens per session scan A 61f6f46d7f4a
agent-browser is a skill published in the GitHub repository actionbook/actionbook (1,616 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 28 tokens to every session and 637 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
skill-body
Call help() or help("page.click") to print signatures and uncommon options of APIs named below; it prints by itself, so do not wrap it in console.log. For installation or connection problems, read references/install.md in the ego-browser Skill directory.
moli-webfetch
Fetch, inspect, crawl, and capture live, JavaScript-rendered websites with Moli. Use when Codex needs current web content, web research, fact lookup, link following, a bounded crawl, client-rendered or response-gated content, network diagnostics, or a standalone HTML, Markdown, JSON, semantic-tree, viewport or…
moli-websearch
Search the web by keyword or reverse-search images with Moli to find subjects, sources, exact matches, or similar images—even when Moli is not named. For fetching a known URL, use moli-webfetch.
moli-cdp-server
Start Moli's CDP server and connect Playwright, Puppeteer, or raw CDP clients. Use to run a headless-browser CDP endpoint, replace a Chromium process, attach over CDP, enable real layout and screenshot surfaces, or diagnose CDP discovery, connection, and target startup—even when Moli is not named.
ego-browser
When you need a browser, read this Skill by default. Use it to open and operate websites, fill forms, click buttons, take screenshots, extract page data, sign in, and perform other browser automation tasks, as well as web app testing, dogfooding, QA, bug investigation, and app-quality review. ego-browser (ego-lite) is…
ego-lite-simplify
Find and implement evidence-backed simplifications in the ego-lite repository. Use when reviewing the codebase for dead code, duplicated state or APIs, speculative abstractions, unnecessary compatibility layers, hand-written infrastructure, excessive tests or documentation, or when the user asks to reduce code size or…