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-cannygit 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-canny)<a href="https://agentmods.dev/skills/openonion/connectonion/co-canny"><img src="https://agentmods.dev/badge/skills/openonion/connectonion/co-canny/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-canny"><img src="https://agentmods.dev/badge/skills/openonion/connectonion/co-canny.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 | $0.00067 | $0.01209 |
| Opus 5.5 | $0.00027 | $0.00484 |
| Sonnet 5.5 | $0.00013 | $0.00242 |
| Haiku 4.5 | $0.00007 | $0.00121 |
Grade A, and why
co-canny 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Canny feedback with co canny
co canny --help and each command's --help are the source of truth for
syntax. This skill says which command serves which goal and what to watch for;
read the command's help before the first use of each one.
Route the request
| Goal | Start with |
|---|---|
| Is Canny connected? Who am I in Canny? | co canny check |
| Which boards exist | co canny boards |
| Most-voted open requests | co canny posts --help (filter by status, sort by score) |
| Does a request already exist | co canny search --help |
| Everything about one request: votes, comments, owner | co canny post --help |
| Move a request to planned / in progress / complete | co canny status --help |
| Reply to the people on a request | co canny comment --help |
| What has shipped, or announce something | co canny changelog --help |
Every listing row starts with the post id the next command takes. Every
command ends with one Next: line naming the command to run next; follow it.
Use --json when you will process rows yourself; the fields are the same.
Workflows
Weekly feedback digest. Read, never write. List open posts sorted by
newest and by trending, then the most-voted open ones; open the few that
matter with co canny post to read their comments. Report each item as
title, votes, status and board, with its id so the user can act on it. The
digest is about what users asked for, so quote their words from the post,
not your paraphrase.
Top-voted open requests. One co canny posts call with the open status,
score sort and the count the user asked for. Votes are Canny's score.
"Open" is one status; a team may also use "under review" for untriaged
requests — check which statuses the rows show before saying "nothing else
is waiting".
Mark a request planned and tell its voters. Run co canny status with
the new status, a short --comment that says what happens next, and
--notify, first without --yes. Show the user the preview: it names the
current status, the vote count and who will be emailed. Only after the user
approves, run the exact command the preview printed (it ends in --yes).
--notify emails the post's non-admin voters; a plain co canny comment
emails no one.
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 · 89 lines · 67 tokens per session scan A f04cac0f250d
co-canny is a skill published in the GitHub repository openonion/connectonion (1,497 stars, last pushed today), licensed Apache-2.0. It adds 67 tokens to every session and 1,209 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 2026-10-02.
Other skills, from other repositories
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.
company-hr
Run HR for a PenguinHarness organization — guarantee every employee has an enabled calendar event, hire and offboard employees (channels included), evaluate and improve them (with the default-rsi-toolkit plugin's agent-optimization skill), and keep the handbook's role conventions current.
company-mirror
Run a PenguinHarness organization that mirrors a real company — one digital twin per real colleague, each twin's desk bound to that colleague's chat bot, twins answering what the handbook already knows and relaying the rest to one another instead of hiring, scheduling and filing tickets.
company-setup
Create a company-mode organization together with the user — collect its id, name, mission, shared workspace, model and CEO budget one question at a time, confirm the whole thing in one summary, then run penguin org create and hand the user over to company mode.
agentlas-operations
A set of operating procedures for running Agentlas, a system for coordinating agents, reusable workforces, automation graphs, and shared agent resources. It covers candidate selection, graph creation, asset discovery, and memory rules.