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-investigate-persongit 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-investigate-person)<a href="https://agentmods.dev/skills/openonion/connectonion/rem-investigate-person"><img src="https://agentmods.dev/badge/skills/openonion/connectonion/rem-investigate-person/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-investigate-person"><img src="https://agentmods.dev/badge/skills/openonion/connectonion/rem-investigate-person.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 | $0.00018 | $0.00664 |
| Opus 5.5 | $0.00007 | $0.00266 |
| Sonnet 5.5 | $0.00004 | $0.00133 |
| Haiku 4.5 | $0.00002 | $0.00066 |
Grade A, and why
rem-investigate-person 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Investigating a person
Identity is given, not guessed
- The user's addresses (the mailbox names in coverage) are never the subject's;
Email/Handlestake only addresses the subject writes from. - Put given and discovered handles (signature, second address, other script) in
Also known as:, unless denied as their name; company names go in their field. - The subject is the owner of a coverage mailbox → the user's own page: follow
rem-owner-page. - A role in a list the user writes about someone else is that person's, not the user's. A role is the subject's only when the subject states it or someone states it about them.
- Another page for the same person: name it in
Uncertainties; do not merge.
Reading the mail
- Cite project documents naming the subject as the owner's record; contact details found only there are not the person's own.
- Read
investigation:factsfirst; put each value in its citedFactsfield. ReadSignature,Calendarand signatures for role, company, office, location and time zone. Date signature changes; qualify both phones. Phonemeans the person's contact number, never a meeting dial-in, passcode or attendee's number. Calendar text is context, not their contact details.- A domain or student affiliation proves no employment; unstated employer →
Company: Unknown. Link a matching organisation in the relationship, citing mail. [attachment]entries are the file's text; the terms are there; cite their id. An unreadable attachment → your final reply.- Mail gives identity and commitments; sessions give intent. Sources disagree → say so; stated in one and implied in another → cite both.
- Check asks/promises across topics before
Nothing open; unrelated replies close none. Questions promise no deadline. Invites, confirmed logistics, arrival, empty forwards or samples do not prove completion. - In a group thread, keep who asked, who decides and who owes; a later reply from the group can close an ask made to this person.
- Reread
Comparison scopeoriginals by exactProvider thread; they are not new contact.
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 · -2 lines 47d9bd7787fe
- 6d ago Changed · -2 lines 52dc933d3c13
- 14d ago Changed · +6 lines · -7 tokens per session 9612cca2489a
- 15d ago Changed · +6 lines 67a69df6d4d0
- 16d ago First seen · 45 lines · 25 tokens per session scan A 31e6caa57d77
rem-investigate-person is a skill published in the GitHub repository openonion/connectonion (1,497 stars, last pushed today), licensed Apache-2.0. It adds 18 tokens to every session and 664 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
agentscope-java
Expert Java developer skill for AgentScope Java framework - a reactive, message-driven multi-agent system built on Project Reactor. Use when working with reactive programming, LLM integration, agent orchestration, multi-agent systems, or when the user mentions AgentScope, ReActAgent, Mono/Flux, Project Reactor, or…
apply-patch
Apply multi-file or tricky edits atomically with git apply instead of many fragile editfile calls. Use when changing several files at once or when editfile fails to match.
git-checkpoint
Use git as a safety net - create a checkpoint commit before risky or large changes and roll back cleanly if a change makes things worse. Use before multi-file refactors.
pptagent
Create and revise editable PowerPoint presentations from a brief using HTML slide sources, rendering, and visual review. Use when the requested deliverable is a PPTX deck. The host authors the slides; text-only hosts can use an external visual reviewer.
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…
web-design
Penguin visual language for generated web pages and app UIs — GitHub-style simplicity with a single blue accent, light and pure-black dark themes, design tokens, component and chat-interface recipes, plus an opt-in warm paper editorial theme.