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.
git 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/commands/actionbook/actionbook/analyze)<a href="https://agentmods.dev/commands/actionbook/actionbook/analyze"><img src="https://agentmods.dev/badge/commands/actionbook/actionbook/analyze/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/commands/actionbook/actionbook/analyze"><img src="https://agentmods.dev/badge/commands/actionbook/actionbook/analyze.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.00524 |
| Opus 5.5 | $0.00000 | $0.00210 |
| Sonnet 5.5 | $0.00000 | $0.00105 |
| Haiku 4.5 | $0.00000 | $0.00052 |
Grade A, and why
analyze 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/actionbook-scraper:analyze
Analyze a webpage's structure using Actionbook's verified selectors and show available elements for scraping.
Usage
/actionbook-scraper:analyze <url>
Parameters
url(required): The full URL of the page to analyze
Examples
/actionbook-scraper:analyze https://firstround.com/companies
/actionbook-scraper:analyze https://example.com/products
Workflow
- Extract domain from the provided URL
- Search Actionbook using
search_actionswith domain and page keywords - Fetch full details using
get_action_by_idfor the best matching action - Launch structure-analyzer agent to process and format the results
- Present findings with selector table and recommendations
Agent
This command uses the structure-analyzer agent (haiku model) for processing.
Output Format
## Page Analysis: {url}
### Matched Action
- **Action ID**: {action_id}
- **Confidence**: HIGH | MEDIUM | LOW
### Available Selectors
| Element | Selector | Type | Methods |
|---------|----------|------|---------|
| Company Card | .card-container | css | click, extract |
| Card Title | .card__title | css | extract |
| Expand Button | button.expand | css | click |
### Page Structure
- **Type**: Dynamic (requires scroll)
- **Data Pattern**: Card-based with expand/collapse
- **Lazy Loading**: Yes
- **Expand/Collapse**: Yes
### Recommendations
- **Suggested Template**: playwright-js
- **Special Handling**: Scroll to load all cards, click to expand each
- **Estimated Items**: ~200 cards
Error Handling
| Error | Cause | Solution |
|---|---|---|
| "No matching actions found" | Site not indexed | Try /actionbook-scraper:list-sources to see available sites |
| "Multiple matches found" | Ambiguous search | Results will show top matches, pick most relevant |
| "Partial data available" | Incomplete indexing | Some selectors may be missing |
Notes
- Run this command before
/actionbook-scraper:generateto understand the page structure - Check the confidence level to gauge selector reliability
- Review the page type to understand what template will be suggested
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 · 76 lines · 0 tokens per session scan A dcf3460c7c48
analyze is a command published in the GitHub repository actionbook/actionbook (1,620 stars, last pushed 8d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 524 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 2026-08-30.
Other commands, from other repositories
intercept
HTTP sniffer for tandem's Chrome via CDP, all tabs: captures request+response bodies (private APIs, CSRF tokens). Subcommands: start (background), stop, status, show, clear, count.
check-browser
Use Browser Controller to check what's currently showing in my browser.
interactive-dev
Start a persistent interactive development session with natural language browser control, auto-error monitoring, and full dev tool access.
playbook
Manage Mochi playbooks (list, show, run, delete). Plays through the browser MCP tools.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.