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-abstractgit 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-abstract)<a href="https://agentmods.dev/skills/openonion/connectonion/rem-abstract"><img src="https://agentmods.dev/badge/skills/openonion/connectonion/rem-abstract/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-abstract"><img src="https://agentmods.dev/badge/skills/openonion/connectonion/rem-abstract.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 | $0.00038 | $0.00847 |
| Opus 5.5 | $0.00015 | $0.00339 |
| Sonnet 5.5 | $0.00008 | $0.00169 |
| Haiku 4.5 | $0.00004 | $0.00085 |
Grade A, and why
rem-abstract 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 yesterday.
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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Abstract the layer above
Your input is pages the notebook already holds, never raw messages. If you
find yourself wanting the original mail or session, stop: that material belongs
to rem-investigate.
Two lifts, and they run in order. principles cannot be written until
decisions exist.
Lift one: decisions, out of what happened
A page in decisions/ records one question that got settled — not one pull
request, not one thread, not one meeting.
The test for whether something is a decision at all:
Was an alternative rejected?
"Fixed a typo" has no rejected alternative and is not a decision. "Used a launchd interval tick rather than a calendar trigger" has one, and a reason. Expect to discard most of what you read.
The entry key is the question, so several artifacts collapse into one page, and a later reversal edits that page rather than opening a second:
# Where the notebook is stored: Markdown or SQLite
Markdown. Chosen 2026-09-02 for portability; the user corrected the reason to
inspectability on 2026-09-07 and kept the choice. SQLite was discussed and not
adopted. Revisit only if plain-text search stops holding up.
## Why
Pages have to be readable and fixable without the tool that wrote them. SQLite
would have made search cheaper and every other kind of inspection harder.
## What it cost
Search is linear. At 143 pages that is not yet a problem.
Sources: PR #1234, PR #1288 (the correction), codex:s1:347
Four sections, and the second one is load-bearing: ## Why is the raw
material of the next lift. Record the question, the alternatives, why the
others lost, and whether it was ever reversed.
Lift two: principles, out of decisions
A principle is a reason that keeps coming back; never extract one from a
single source. A rule the user stated themselves ("from now on…") is already a
principle, written by rem-maintain; this lift finds the ones never said.
Read the ## Why of every decision page and group them by the reason, not by
the topic (three decisions that each measured behaviour instead of trusting an
API's self-report become "Do not trust an API's report of itself; measure the
behaviour").
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.
- yesterday Changed · +1 lines ce4e44f59795
- 6d ago Changed · -2 lines 0672b3e90891
- 17d ago First seen · 91 lines · 38 tokens per session scan A 11e1b7b23234
rem-abstract is a skill published in the GitHub repository openonion/connectonion (1,497 stars, last pushed today), licensed Apache-2.0. It adds 38 tokens to every session and 847 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 2026-09-30.
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.