ConnectOnion is an open-source, template-first toolkit for building, debugging, deploying, and operating AI agents. Developers use its command-line tools and Python runtime to create agents, add tools, connect services, deploy them, and make them callable by other agents, while the catalogue entries are related agents, skills, and instructions.
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/openonion/connectonion/co-browsernpx skills add openonion/connectonion --skill co-browsergit clone --depth 1 https://github.com/openonion/connectonionWrote 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/openonion/connectonion/co-browser)<a href="https://agentmods.dev/skills/openonion/connectonion/co-browser"><img src="https://agentmods.dev/badge/skills/openonion/connectonion/co-browser.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 | $0.00063 | $0.03160 |
| Opus 5 | $0.00032 | $0.01580 |
| Sonnet 5 | $0.00013 | $0.00632 |
| Haiku 4.5 | $0.00006 | $0.00316 |
Grade A, and why
co-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 6d 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.
co browser Skill
Drive one real browser from the shell. The browser stays open between commands —
cookies and logins persist until co browser close. Every terminal on the machine
talks to the same daemon: one browser, one board, no matter where you type.
Always read the output, not just the exit code. A failed action (selector not
found, browser not open) often returns exit 0 with the error text on stdout —
never chain co browser ... && next_step as your only success check.
Step 1: Identity — who are you?
The daemon attributes every tab to a caller and uses that identity to stop two
agents from silently driving the same page. Set CO_WHO explicitly — shell
state does not survive between your tool calls, so a lone export is lost.
Either prefix every command:
CO_WHO=alice co browser go_to example.com
or keep the export and the commands in the SAME shell invocation:
export CO_WHO=alice && co browser go_to example.com && co browser get_text
(Some environments — e.g. Claude Code background jobs — are auto-identified,
but setting CO_WHO is always safe and never worse.) An anonymous caller still
works but gets no contention protection.
Step 2: Check the board, then claim a tab
One task = one tab. Before touching the browser, see what's already happening:
co browser status # browser state, headless flag, last command, the board
co browser tab ls # every tab: who owns it, purpose, last command (--json for scripting)
Solo (nobody else on the board) — bare commands run on the shared main tab, no ceremony:
co browser go_to example.com # runs on 'main'
co browser get_text # still 'main'
Concurrent (another agent or a second parallel task exists) — open your own tab
and add -t <name> to EVERY command, including do. Pick an explicit literal tab
name — a NAME=$(...) capture is lost between tool calls:
CO_WHO=alice co browser tab open scrape --for "scrape pricing" --needs 10m
CO_WHO=alice co browser -t scrape go_to example.com/pricing
CO_WHO=alice co browser -t scrape do "extract every plan and its monthly price"
CO_WHO=alice co browser tab close scrape # release when done
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.
- 6d ago First seen · 275 lines · 63 tokens per session scan A 9a2d9346253e
co-browser is a skill published in the GitHub repository openonion/connectonion (1,481 stars, last pushed today), licensed Apache-2.0. It adds 63 tokens to every session and 3,160 once invoked, about $0.0003 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
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…
penguin-harness-manual-test
Use when standing PenguinHarness up to try a change by hand — launching the Web App, the desktop shell, the landing page or the docs site to click through it, screenshot it, or reproduce a report. Covers the four dev entry points and their ports, which data root each writes to, and the four ways a healthy setup looks…
firecrawl
Search the web and scrape pages into clean markdown with the Firecrawl API — query-based discovery, single-URL extraction including public PDFs, driven by curl with a vault-stored API key.
web-reader
Implement web page content extraction capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to scrape web pages, extract article content, retrieve page metadata, or build applications that process web content. Supports automatic content extraction with title, HTML, and publication time retrieval.
p5.js
Production pipeline for interactive and generative visual art using p5.js. Creates browser-based sketches, generative art, data visualizations, interactive experiences, 3D scenes, audio-reactive visuals, and motion graphics — exported as HTML, PNG, GIF, MP4, or SVG. Covers: 2D/3D rendering, noise and particle systems…
Web Read
Keeps direct URL reading and text extraction available when a specific page matters more than search results.