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 skills/adolfousier/opencrabs/browser-cdpnpx skills add adolfousier/opencrabs --skill browser-cdpgit clone --depth 1 https://github.com/adolfousier/opencrabsWrote 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/adolfousier/opencrabs/browser-cdp)<a href="https://agentmods.dev/skills/adolfousier/opencrabs/browser-cdp"><img src="https://agentmods.dev/badge/skills/adolfousier/opencrabs/browser-cdp.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 | $0.00036 | $0.00556 |
| Opus 5 | $0.00018 | $0.00278 |
| Sonnet 5 | $0.00007 | $0.00111 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
browser-cdp 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 4d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Native Browser Automation (CDP)
Built-in browser control via Chrome DevTools Protocol — no Node.js, no Playwright, pure Rust.
Tools
| Tool | Required | Optional | What |
|---|---|---|---|
browser_navigate |
url |
headless |
Navigate to URL |
browser_click |
selector |
— | Click element by CSS selector |
browser_type |
text |
selector |
Type text into input |
browser_screenshot |
— | selector |
Screenshot (returns file path) |
browser_eval |
script |
— | Execute JavaScript |
browser_content |
— | selector, text_only |
Extract text/HTML |
browser_wait |
— | selector, timeout_secs, delay_secs |
Wait for element or delay |
browser_find |
— | pattern, mode, limit |
Inventory (no pattern) or find elements |
Headless vs Headed
- Headless (default): No visible window. Fast, low resources.
- Headed: Visible Chrome window. Pass
headless: falsetobrowser_navigate.
Usage Tips
- Compose workflows: navigate → inventory/find → click → type → screenshot
- Inventory mode: call
browser_findwith NOpatternto get every visible interactive element on the page, each with a stable[data-opencrabs-match="N"]selector. Prefer this overbrowser_screenshotwhen you have just landed and do not yet know what to click — text beats pixels for deciding where to act. - Screenshots return file paths. Use
<<IMG:path>>to send to channels. - JavaScript evaluation for complex DOM manipulation and SPAs.
- No credentials stored. Navigate to login page and use click/type for auth (with user approval).
- Requires Chrome/Chromium installed. Feature-gated:
browserflag.
Chrome Launch Failures
- SingletonLock exists:
rm -f ~/.opencrabs/chrome-profile/SingletonLock ~/.opencrabs/chrome-profile/SingletonCookie ~/.opencrabs/chrome-profile/SingletonSocketthen retry. - DevTools data dir conflict:
pkill -f chromethen retry. - Channel closed: Kill Chrome, delete lock files, retry.
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.
- 4d ago First seen · 45 lines · 36 tokens per session scan A d32118502085
browser-cdp is a skill published in the GitHub repository adolfousier/opencrabs (920 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 556 once invoked, about $0.0002 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
defuddle
Plan and, with explicit network consent, use an optional external Defuddle cleaner to extract article-like HTTPS pages as Markdown. Use for defuddle, clean this URL, strip page clutter, readable Markdown from a web page, or preparing a web source for later wiki ingestion.
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…
hive.telegram-notifications-setup
Set up a Telegram notification channel (Sentinel) for a colony by driving the browser — create a bot via @BotFather in Telegram Web, store its token, detect the chat to notify, and turn Sentinel on so the colony can ping the user on Telegram and accept replies. Use when the user asks to "set up Telegram…