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-source-codexgit 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-source-codex)<a href="https://agentmods.dev/skills/openonion/connectonion/rem-source-codex"><img src="https://agentmods.dev/badge/skills/openonion/connectonion/rem-source-codex/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-source-codex"><img src="https://agentmods.dev/badge/skills/openonion/connectonion/rem-source-codex.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 | $0.00049 | $0.00680 |
| Opus 5.5 | $0.00020 | $0.00272 |
| Sonnet 5.5 | $0.00010 | $0.00136 |
| Haiku 4.5 | $0.00005 | $0.00068 |
Grade A, and why
rem-source-codex 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 6d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex CLI as a source
Read with the stage Skill that loaded it (rem-extract, rem-maintain or
rem-investigate): that one says what to produce, this one what is true of
this source.
Where the user's words are
~/.codex/sessions/YYYY/MM/DD/rollout-<ISO>-<uuid>.jsonl, one JSONL file per
session. The importer recognizes native CLI and Desktop user-input shapes;
harness context, imported history, subagents and scheduled automation prompts
are excluded. An input_scope may identify an older Desktop turn without client
content kinds, or an explicit voice transcription with the mixed transcript
omitted. Preserve those limits: transcribed wording can contain recognition
errors. timestamp_scope marks legacy session-start dates. A session folder
is context, not proof of the product's identity.
The store
- Directories are dated, oldest first.
cwdin the session header is the project, but the notebook's page title wins over the directory name. - A gap in the timeline means a machine change, not expired history.
- Sessions can be hundreds of MB; never assume one fits.
Rules
- A session records intent, not repository state. Write "decided to X because Y", never git SHAs, CI run counts, PR numbers or screenshot paths.
- One session is one sitting, not one project. Same-day sessions usually continue one thread; do not open a page per session.
- Sources: keep the few ids that carry the claim, not every id seen.
- Pasted material is not the user's words. Summarise why a trace, log or file was pasted; do not quote it back.
- A question is not a decision. Keep the mood ("should we use X?" vs "we're using X").
- A bare
/skill argsmessage records that the user ran something, not a belief. Note it only when running it is itself the fact.
What a Codex note looks like
## Decisions
- Decided co rem runner keeps Codex isolated by giving it a temporary
CODEX_HOME containing only auth.json, after finding that `-c mcp_servers={}`
leaves inherited servers enabled. — user, 2026-09-07, codex:s1:412
## Projects
- connectonion: spent the week on co rem feature; the open question at the
end of the batch is whether background maintenance ships on launchd or a
worker of our own. — user, 2026-09-07, codex:s1:88, codex:s1:640
## Agenda
- Promised to check the extraction prompt against a real 60-day mailbox before
raising the batch size again. — user, 2026-09-08, codex:s2:210
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.
- 6d ago Changed · -2 lines 64c9bffb82e3
- 14d ago Changed · +2 lines 6f803b8de04c
- 17d ago First seen · 61 lines · 49 tokens per session scan A 89bb2689c434
rem-source-codex is a skill published in the GitHub repository openonion/connectonion (1,497 stars, last pushed today), licensed Apache-2.0. It adds 49 tokens to every session and 680 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.