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-inboxgit 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-inbox)<a href="https://agentmods.dev/skills/openonion/connectonion/co-inbox"><img src="https://agentmods.dev/badge/skills/openonion/connectonion/co-inbox/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-inbox"><img src="https://agentmods.dev/badge/skills/openonion/connectonion/co-inbox.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 | $0.00072 | $0.04597 |
| Opus 5.5 | $0.00029 | $0.01839 |
| Sonnet 5.5 | $0.00014 | $0.00919 |
| Haiku 4.5 | $0.00007 | $0.00460 |
Grade A, and why
co-inbox 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 — 384 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The inbox
A Feishu or Lark bot, as a directory. One process writes messages into it; you read them. Nothing here knows what an agent is.
Always read the output, not just the exit code. listen prints nothing on
a clean hour, and consume runs commands whose own failures it reports on
stderr while continuing.
co discord … takes the same verbs for a Discord bot (DISCORD_BOT_TOKEN,
Message Content intent on). Its ids are Discord's message ids and its chat is
the channel id. See docs/cli/discord.md.
co slack … (experimental) takes the same verbs for a Slack app over Socket
Mode (SLACK_APP_TOKEN xapp- and SLACK_BOT_TOKEN xoxb-). Its ids are
<channel>:<ts>, its chat is the channel id, and reply answers in the
message's thread. co auth slack sets it up; co slack channels | history | thread | search read the workspace directly (the co-slack skill). See
docs/cli/slack.md.
Which command
| you want to | run |
|---|---|
| set it up, from nothing | co auth feishu |
| set it up, reusing a bot you already have | co auth feishu --app-id cli_… |
| check it is configured | co feishu check |
| take the next message and act on it yourself | co feishu receive |
| run a program for every message, forever | co feishu consume -- <command> |
| answer a message you took | co feishu reply <id> "text" |
| decide not to answer one | co feishu done <id> |
| send without being asked | co feishu send <chat> "text" |
| fix something you already said | co feishu edit <id> "text" |
| take back something you said | co feishu delete <id> |
| acknowledge a message without a reply | co feishu react <id> 👍 |
| start a group with people (WhatsApp) | co whatsapp group create "<name>" <phone>… |
| see what is waiting | co feishu ls |
| find out which conversations exist | co feishu chats |
| read one conversation back | co feishu log --chat <id> |
| watch it work | co feishu log -f |
| hold the connection yourself | co feishu listen |
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 Changed · +2 lines b76a3b4c771a
- 18d ago Changed · +5 lines 81d525fd42ad
- 21d ago Changed · +3 lines f7171979d3d6
- 22d ago Changed · +56 lines 0bd7ce2f49a6
- 27d ago Changed · +46 lines b387eca19904
- 28d ago Changed · +122 lines 574954d77db1
- 1mo ago Changed · +8 lines c1bc9a56d0d0
- 1mo ago First seen · 142 lines · 72 tokens per session scan A 13237f1c4b18
co-inbox is a skill published in the GitHub repository openonion/connectonion (1,497 stars, last pushed today), licensed Apache-2.0. It adds 72 tokens to every session and 4,597 once invoked, about $0.0003 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 2026-09-13.
Other skills, from other repositories
agentscope-java
Expert Java developer skill for AgentScope Java framework - a reactive, message-driven multi-agent system built on Project Reactor. Use when working with reactive programming, LLM integration, agent orchestration, multi-agent systems, or when the user mentions AgentScope, ReActAgent, Mono/Flux, Project Reactor, or…
apply-patch
Apply multi-file or tricky edits atomically with git apply instead of many fragile editfile calls. Use when changing several files at once or when editfile fails to match.
git-checkpoint
Use git as a safety net - create a checkpoint commit before risky or large changes and roll back cleanly if a change makes things worse. Use before multi-file refactors.
pptagent
Create and revise editable PowerPoint presentations from a brief using HTML slide sources, rendering, and visual review. Use when the requested deliverable is a PPTX deck. The host authors the slides; text-only hosts can use an external visual reviewer.
company-employee
The protocol every employee of a PenguinHarness organization follows — read the handbook first, act on [orgtrigger] work runs, schedule tickets from the desk session and do the work in ticket sessions, block instead of idling, ask the board in the all-hands channel before anything heavy, costly, irreversible or…
company-ceo
Run a PenguinHarness organization as its CEO — turn the mission into a ticket tree, hire HR and finance first, partition the shared workspace, schedule the calendar, open a channel per stream, review tickets and report to the board in the all-hands channel.