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 skills add openonion/connectonion --skill co-tiktokgit 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-tiktok)<a href="https://agentmods.dev/skills/openonion/connectonion/co-tiktok"><img src="https://agentmods.dev/badge/skills/openonion/connectonion/co-tiktok/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/openonion/connectonion/co-tiktok"><img src="https://agentmods.dev/badge/skills/openonion/connectonion/co-tiktok.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 | $0.00048 | $0.01224 |
| Opus 5.5 | $0.00019 | $0.00490 |
| Sonnet 5 | $0.00010 | $0.00245 |
| Haiku 4.5 | $0.00005 | $0.00122 |
Grade A, and why
co-tiktok 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 today.
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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TikTok
Always read the output, not just the exit code. A direct co browser
primitive can fail with exit 0. Never use && alone to decide whether to continue.
Required tool: the shell for co commands. This skill grants no tool permissions.
YouTube is not here: it uses the official API through the Google login, see
co youtube --help and the co-google skill.
| Intent | Command | Boundary |
|---|---|---|
| Prepare a TikTok post | co tiktok post clip.mp4 --caption Demo --account @creator |
Local plan; no TikTok draft or upload |
| Check TikTok browser state | co tiktok inspect --tab creator-tiktok |
Login or unknown surface is an error, never “ready” |
Both leaves support --json: stdout is one JSON object with ok, mode on
success, next_command, and next_tip. Otherwise the final stdout line is one
literal next command, including under | cat. Usage errors (exit 2) print the
cause and a recovery tip on stderr.
The local plan
post previews by default; --dry-run makes that explicit. The plan carries
plan.confirmation, a SHA-256 digest of the exact file bytes, the caption and
the intended @handle. The @handle is what the user said, not proof of login.
--confirm <plan.confirmation> checks the digest, then refuses submission
with exit 1 and code: submit_unavailable. As of 2026-09-05 the real Studio URL
redirected to login. The upload form, account identity, caption editor, privacy
choices, upload-complete state and final publish control have not been observed,
so no submission adapter is shipped. Local plan acceptance is not publication
approval. The post preview points to co browser tab ls so the agent can find
its owned tab without guessing a name.
Browser evidence workflow
Use the co-browser ownership rules: set CO_WHO on every call, inspect the tab
board, use one named tab per task, and never move someone else's tab. Browser
inspection operates on an existing tab and never navigates, clicks, types,
uploads, or submits. Open only the intended URL with generic primitives:
What ships with it
2 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.
- today First seen · 102 lines · 48 tokens per session scan A 9ff1ad615bd4
co-tiktok is a skill published in the GitHub repository openonion/connectonion (1,479 stars, last pushed yesterday), licensed Apache-2.0. It adds 48 tokens to every session and 1,224 once invoked, about $0.0002 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 2026-09-25.
Other skills, from other repositories
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.
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…
agentlas-browser
Use when the user types /agentlas-browser , /agentlas browser, or /hep-browser for browser-required tasks, rendering pages, form flows, or visual evidence.
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.