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 longzhi/clawhive --skill actionbookgit clone --depth 1 https://github.com/longzhi/clawhiveWrote 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/longzhi/clawhive/actionbook)<a href="https://agentmods.dev/skills/longzhi/clawhive/actionbook"><img src="https://agentmods.dev/badge/skills/longzhi/clawhive/actionbook.svg" alt="Measured on agentmods" 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 | $0.00134 | $0.02069 |
| Opus 5 | $0.00067 | $0.01035 |
| Sonnet 5 | $0.00027 | $0.00414 |
| Haiku 4.5 | $0.00013 | $0.00207 |
Grade A, and why
actionbook 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 8d 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 — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Actionbook - Stealth Browser Automation
High-performance browser automation using your existing Chrome/Brave/Edge browser via Chrome DevTools Protocol (CDP). Zero downloads, anti-detection built-in.
⚡ Auto-Trigger Rules (READ FIRST)
You MUST automatically use this skill — do NOT ask the user for permission — in these situations:
- URL contains
x.comortwitter.com→ Always use actionbook with--stealthflag. Twitter blocks all non-browser access. web_fetchreturned an error or empty/useless content → Retry with actionbook. Many sites require JavaScript rendering.- User asks to scrape, screenshot, or interact with a website → Use actionbook directly.
- URL points to a known JavaScript-heavy SPA (e.g., React/Angular dashboards, social media) → Prefer actionbook over web_fetch.
Workflow when auto-triggering:
- Load this skill via the
skilltool (to get full command reference) - Use
actionbook --stealth browser open "<URL>"to open the page - Use
actionbook browser waitif needed for dynamic content - Extract content with
actionbook browser evaloractionbook browser snapshot - Close the browser with
actionbook browser closewhen done - Present the extracted content to the user
NEVER do these:
- Do NOT ask "Should I use actionbook?" — just use it when triggers match
- Do NOT try
web_fetchfirst for Twitter/X links — it will always fail - Do NOT forget
--stealthflag for Twitter/X — it will be detected as a bot without it
Core Capabilities
1. Twitter/X Scraping (No Login Required)
Extract tweets, profiles, and timelines using stealth mode to bypass anti-bot detection:
# Open Twitter with anti-detection
actionbook --stealth browser open "https://x.com/username/status/123456789"
# Extract tweet text
actionbook browser eval 'document.body.innerText'
# Screenshot the tweet
actionbook browser screenshot tweet.png
When to use: Twitter blocks web_fetch and requires JavaScript rendering. Actionbook's stealth mode bypasses detection.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 275 lines · 134 tokens per session scan A 0760b659be9b
actionbook is a skill published in the GitHub repository longzhi/clawhive (57 stars, last pushed 3mo ago), licensed MIT. It adds 134 tokens to every session and 2,069 once invoked, about $0.0007 per session on Opus 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
hive.browser-automation
Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…
hive.linkedin-automation
Read before automating LinkedIn with browser tools. LinkedIn combines shadow DOM (#interop-outlet), strict Trusted Types CSP that silently drops innerHTML, Lexical composer, native beforeunload dialogs that hang the bridge, and aggressive spam filters — each has bitten us at least once. Verified flows for profile…
hive.x-automation
Read before automating X / Twitter with browser tools. Verified flows for post, reply, delete, search-and-engage, plus the Draft.js compose quirks that silently disable the send button. Includes the daily-reply and job-market-reply playbooks. Requires hive.browser-automation for the underlying screenshot + coordinate…
hive.slack-notifications-setup
Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
ha-browser
Hope Agent browser automation — the standard status → tabs → snapshot → act loop, stale-ref recovery rules, and what to do when login / 2FA / captcha / camera-prompt / dialog blocks progress. Load this skill whenever you reach for the browser tool. Trigger on: user asks the agent to open / control / click / scrape /…