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-slackgit 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-slack)<a href="https://agentmods.dev/skills/openonion/connectonion/co-slack"><img src="https://agentmods.dev/badge/skills/openonion/connectonion/co-slack/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-slack"><img src="https://agentmods.dev/badge/skills/openonion/connectonion/co-slack.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 | $0.00041 | $0.00811 |
| Opus 5.5 | $0.00016 | $0.00324 |
| Sonnet 5.5 | $0.00008 | $0.00162 |
| Haiku 4.5 | $0.00004 | $0.00081 |
Grade A, and why
co-slack 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 15d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slack
co slack is the user's own Slack app. Read verbs ask Slack directly (Web API);
inbox verbs (listen, receive, reply) only see what arrived while a
listener ran. It is experimental: not yet run on a live workspace.
Read the help before the first command, and read every output, not just the exit code:
co slack --help # every verb; the "Read the workspace" panel is channels, history, thread, search
co slack <verb> --help # flags and an example for that verb
Which command
| the user wants | run |
|---|---|
| set it up, or fix a token | co auth slack |
| know whether it works | co slack check |
| which channels exist (ids, names) | co slack channels |
| what a channel said | co slack history ops -n 50 |
| a whole conversation under a message | co slack thread <channel>:<ts> |
| find a message by its words | co slack search "words" --in ops --from alice |
| answer in a message's thread | co slack send <channel> "text" --reply-to <channel>:<ts> |
Add --json to any read verb for one object per line: id, chat, thread,
at (UTC), sender, sender_name, text, and replies (history and thread).
"What did #ops say today?"
co slack history ops -n 100 --json(a name, or'#ops'quoted: an unquoted#is a shell comment).- Keep the messages whose
atfalls on today in the user's timezone; the plain view already prints local time. - For any message with
replies> 0 that matters,co slack thread <id>. - Answer from what was said, citing who said it. Do not post anything.
"Find the message about X and reply in its thread"
co slack search "X" -n 10(narrow with--in/--from). WithoutSLACK_USER_TOKENit exits 1 and says so: fall back toco slack history <channel>on the likely channel, or tell the user to runco auth slackand paste the User OAuth Token.- Read the thread before answering:
co slack thread <id>. - Show the user the reply and get their yes. Then
co slack send <channel> "reply" --reply-to <id>, using that message'schatandid. It prints the new message's id.
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.
- 15d ago First seen · 64 lines · 41 tokens per session scan A 6983e87c33e1
co-slack is a skill published in the GitHub repository openonion/connectonion (1,497 stars, last pushed today), licensed Apache-2.0. It adds 41 tokens to every session and 811 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 2026-10-02.
Other skills, from other repositories
agent-initialization
Initialize or extend an Agent from a user requirement - write AGENTS.md, set identity metadata, and create, install or import Skills and hook packages (scripts the harness runs on every prompt, before tool calls, or after a task). For an Agent with an in-app workbench, pair with penguin-plugin; for a standalone…
computer-history
Answer questions about what the user recently did on their computer — who contacted them, what they were working on, where they left off — by reading the local Computer History summaries and raw event streams.
cron
Schedule reminders and recurring tasks.
AgentMail
Give the agent its own dedicated email inbox via AgentMail. Send, receive, and manage email autonomously using agent-owned email addresses (e.g. [email protected]).
Apple Notes
Open Notes.app and create or update iCloud notes on macOS using memo when possible and AppleScript when direct app automation is more reliable.
Himalaya Email
Work with IMAP email from the terminal using Himalaya for inbox reads, draft review, and carefully confirmed outbound sends.