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-whatsappgit 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-whatsapp)<a href="https://agentmods.dev/skills/openonion/connectonion/rem-source-whatsapp"><img src="https://agentmods.dev/badge/skills/openonion/connectonion/rem-source-whatsapp/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-whatsapp"><img src="https://agentmods.dev/badge/skills/openonion/connectonion/rem-source-whatsapp.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 | $0.00588 |
| Opus 5.5 | $0.00025 | $0.00235 |
| Sonnet 5.5 | $0.00013 | $0.00118 |
| Haiku 4.5 | $0.00006 | $0.00059 |
Grade A, and why
rem-source-whatsapp 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WhatsApp as a source
Read this together with the stage Skill that loaded it. That one says what to produce; this one says only what is true of this source.
What reaches you
Only the chats the user named with co rem sources add whatsapp --chat <id>.
A person or group missing from the batch was not chosen; never treat it as
absent from the user's life.
Each item carries:
role: user— typed by the account owner: the user's own voice, the most important material.role: other— someone else, with their display name asspeaker. Keep both sides, as with mail.correspondent/subject— the chat id.…@g.usis a group;…@s.whatsapp.netor…@lidis one person. A chat id never goes on a page as a name.
The agent's own replies are left out on purpose: they are execution, not the user. If a message refers to "what the bot said", do not reconstruct it.
A batch is one conversation
Whole chats, oldest first. In a group, write each person's page from what they said, and the group's own page (a project, a client relationship, a rolling agenda) from what was agreed in it. One page per person across groups, with each group as a place they were met.
Groups are clients' rooms
Most business groups are one client each. Never carry a fact, number, price or guest from one group onto another group's client page, even when the user and topic are the same. Name the group in the source line of any fact from it.
Photos, documents and voice notes
[image saved at /…/media/3EB0….jpg] is a real local file: open it when it
matters to the page (a contract photo, a floor plan, a screenshot someone asked
about). [document could not be fetched: …] means the file is gone: record
that it existed, never guess its content.
Short messages
"ok", "👍", "done" answer the message before them; read them with it, and never write a page about a thumbs-up. A short "yes go ahead" from the user after someone else's proposal is a decision: the proposal is the content, the "yes" the decision.
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 f4f192858780
- 17d ago First seen · 58 lines · 63 tokens per session scan A fc2139ffd406
rem-source-whatsapp 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 588 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
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.