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 rem-owner-pagegit 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/rem-owner-page)<a href="https://agentmods.dev/skills/openonion/connectonion/rem-owner-page"><img src="https://agentmods.dev/badge/skills/openonion/connectonion/rem-owner-page/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-owner-page"><img src="https://agentmods.dev/badge/skills/openonion/connectonion/rem-owner-page.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 | $0.00013 | $0.00770 |
| Opus 5.5 | $0.00005 | $0.00308 |
| Sonnet 5.5 | $0.00003 | $0.00154 |
| Haiku 4.5 | $0.00001 | $0.00077 |
Grade A, and why
rem-owner-page 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 14d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your own page
Write the user's page from their messages. Keep person headings and Facts
labels except How the user writes to them.
The lead
Before Facts, write 2–4 cited sentences:
- Start with what they are working on now and why the next step matters.
If
owner-work-evidenceshows an explicit reversal, lead with it and cite both messages. Newer questions are not a change. Otherwise name a blocker or unresolved choice. Replace the generic lead; put the latest request in the next step.recent-projectsranks, not proves shipping. List projects inWho they are. - Add a firm, due-soon commitment or blocker. Put distant invitations and
unrelated mail in
Open threads. - Put contact dates in
FactsandCadence, not the lead.
Coding agents are the user's tools, not people
Claude Code and Codex are tools. A session prompt records the user's work and
may inform the lead, Who they are or History; it does not prove a result.
An agent is never a counterparty in Open threads, never Last contact, and
never a correspondent in Cadence.
Roles are stated, not collected
RoleandCompanyare the user's only when the user states them about themselves (a signature, "I run …", "as the founder of …"), or someone else states them about the user ("Aaron, our CTO").- A role in a list the user writes about someone else is that person's, not the user's. "Ody: partner at OpenOnion, runs marketing, Airbnb co-host" in the user's mail describes Ody. Leave it off this page.
- List stated roles with citations and dates; otherwise
Unknown.
The sections
Who they are: the user's work in their own words, and the projects of the last weeks, each with what they did and when, from the sessions.Insight: 2–4 cited bullets connecting projects and commitments to the next decision: what must happen first, who waits, or a recurring tradeoff. Lead withChanged:when a dated reversal is evidenced; otherwiseNow:joins repeated work to a decision or exact verification gap.Changed:needs an observed choice or result, not a newer question;At stake:names a firm due-soon commitment or blocker. Compare sources when possible and cite the dependency. Summarized requests alone are not insight. A coding request proves no shipment or passing test; only artifact evidence proves shipping.Why they are here: this is the owner's page; one line, cited to the map.Our relationship:Account owner.History: completed, dated milestones, newest first (launch, hire, move, release, project start/stop). Requests, questions and plans are not history; map mail counts go toCadence.Open threads: mandatory. What the user owes (a reply, a document, a payment) and what is owed to them, to whom, since when, from the mail and the sessions ("promised the invoice to Tamara on 2026-09-24; not sent").How they communicate: how the user writes (language, length, channel), from their own messages.Cadence,Uncertainties: as on a person's page.
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.
- 14d ago Changed · +2 lines · -48 tokens per session 69a4a10060d5
- 15d ago Changed · +13 lines 45e8d2b2250b
- 16d ago First seen · 51 lines · 61 tokens per session scan A 735c00df3a4e
rem-owner-page is a skill published in the GitHub repository openonion/connectonion (1,497 stars, last pushed today), licensed Apache-2.0. It adds 13 tokens to every session and 770 once invoked, about $0.0001 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 2026-10-01.
Other skills, from other repositories
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.
docx
Create, read, edit, review, redline, comment on, merge, audit, render, and verify .docx Word documents, including layout-sensitive and OOXML-level work.
update-setup
A one-time setup wizard for creating a personalised upgrade guide for a workspace. It checks for an existing guide, identifies the current version and installation clues, and requires confirmation of the installation method before writing a new guide.
skill-creator
Create, edit, improve, tidy, review, audit, or restructure memmy-agent skills and SKILL.md files.
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.
memmy-memory
Use the shared Memmy memory service to retrieve relevant prior context and persist durable Agent turns, facts, decisions, preferences, procedures, and follow-ups.