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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/openonion/connectonionnpx agentmods add skills/openonion/connectonion/rem-page-orgWrote 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/rem-page-org)<a href="https://agentmods.dev/skills/openonion/connectonion/rem-page-org"><img src="https://agentmods.dev/badge/skills/openonion/connectonion/rem-page-org/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/rem-page-org"><img src="https://agentmods.dev/badge/skills/openonion/connectonion/rem-page-org.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 | $0.00063 | $0.01298 |
| Opus 5.5 | $0.00025 | $0.00519 |
| Sonnet 5.5 | $0.00013 | $0.00260 |
| Haiku 4.5 | $0.00006 | $0.00130 |
Grade A, and why
rem-page-org 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 5d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
An organisation's page
Facts of the entity (programme, agreement, fees, legal entity, who the user deals with) go here, not on the sender's page.
When an organisation earns a page
Create one only when either is true:
- Two or more people write from the same work domain.
- Something is agreed with the entity rather than the person: a signed contract, recurring money, a programme or account that outlives this contact. A one-person client who signed earns a page; a one-person vendor who sent a quote does not.
Otherwise the company stays a Company: field on the person's page. A mailbox
provider (gmail.com) is never an organisation.
co rem scan orgs --days 180 proposes domains passing the first test; you
judge. Its two_way (people who wrote to the user and were answered)
separates a counterparty from a vendor; read it against the names.
- Brand names that only ever send are a vendor, whatever the headcount
(
Apple Developer,Xero Support); so are event platforms and newsletters. Their mail goes on the page of what it is about (the project using it). two_wayof zero does not settle it: a reply from the user's other mailbox leaves it at zero. Human names and subjects about the user's own work outweigh it; a brand name does not.- The user's own domain is not a counterparty. Pass every own address to the
scan with
--mine. - One domain can be two tenants (staff and students, a shared agency
address). Choose one page or two from the mail and say which in
Uncertainties.
The shape
Every section is always present, in this order; a section the evidence does
not support says Unknown. Every factual sentence carries a claim number
[n] into Sources.
# ExampleCo
## Domains
- example.test [1]
## Facts
- What they do: Unknown
- Website: Unknown
- Location: Unknown
- Legal entity: Unknown
- Your contacts: [Alex](../people/alex.md) [1]
- First contact: 2026-07-10 [1]
- Last contact: 2026-07-24 [2]
## Who they are
The named programme contact writes from example.test; legal identity is unknown. [1]
## Our relationship
The user requested one team; the programme has a two-team minimum. An exception
is not confirmed in the reviewed replies. [1][2]
## People here
- [Alex](../people/alex.md) — programme contact [1]
## Terms
- Two-team minimum; the one-team request is not accepted terms. [1][2]
## Open threads
Unknown — historical requests alone do not establish a current obligation. [2]
## Uncertainties
- Whether the exception was later accepted. [2]
## Sources
- [1] outlook:123456789abc — observed 2026-07-10
- [2] outlook:abcdef123456 — observed 2026-07-24
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.
- 5d ago Changed · +1 lines 6e693bb8b419
- 13d ago Changed · -6 lines 2c739d826e30
- 14d ago Changed · +10 lines 8d38c74fd04d
- 16d ago First seen · 115 lines · 63 tokens per session scan A 26550e515dae
rem-page-org is a skill published in the GitHub repository openonion/connectonion (1,497 stars, last pushed today), licensed Apache-2.0. It adds 63 tokens to every session and 1,298 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 2026-09-30.
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.
awm-rsi-toolkit
Run AWM (Agent Workflow Memory, Wang et al. 2024) on an agent - induce reusable workflows from its successful trajectories, online over a training stream or offline from supplied experiences, then freeze the workflow memory and measure it on a published Benchmark.
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.