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-projectgit 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-project)<a href="https://agentmods.dev/skills/openonion/connectonion/rem-investigate-project"><img src="https://agentmods.dev/badge/skills/openonion/connectonion/rem-investigate-project/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-project"><img src="https://agentmods.dev/badge/skills/openonion/connectonion/rem-investigate-project.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 | $0.00025 | $0.00728 |
| Opus 5.5 | $0.00010 | $0.00291 |
| Sonnet 5.5 | $0.00005 | $0.00146 |
| Haiku 4.5 | $0.00003 | $0.00073 |
Grade A, and why
rem-investigate-project 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.
What it actually says
Investigating a project
A project is told by two witnesses: the owner's messages say what they wanted, decided and saw; the repository's current line says what was built and when. Join them; neither alone is the page.
- Start from the current line.
checkout-statenames it (usuallyorigin/main) and whether the working tree lags; the history packet lists its commits and the unmerged branches committed lately. A working tree on an old branch is not the project: read files at the named revision withgit show, never from the checkout. - Hear the owner. Read every supplied message: why they started it, the choices they made (price, scope, audience, people), what they reversed. These are the page's voice, quoted; the repository verifies them. Purpose comes from those words or the README at that revision.
- Close every thread you can. For each ask, issue or plan in the
messages, look for its outcome: later messages, commit subjects
(
git log --all --grep '<term>'), branch names. A commit after the ask that does what it asked closes it; cite both and date the close. Only what nothing closed, and is recent, stays open. - Date where it stands from the newest commits and messages. A request newer than every verified change is the current goal, not done work.
- Inspect code only for what the page claims (purpose, flow, commands, a conflict with what the owner said). Do not tour files.
Citing
- Cite supplied
project-source:,codex:orclaude-code:IDs. A file you inspect at a commit isgit:/absolute/mapped/repository:<full-commit-sha>:relative/file; a live file isfile:/absolute/path@<sha256>fromshasum -a 256.origin: git:, command output and bare paths are not source IDs. - Only files under the page's mapped
Pathscan support it. investigation:*items (page, coverage, inventory, repositories, scope) are reading guides, never citable.- Keep existing
Pathsand theirSessions,First seenandLast seenlines exactly. A new path needs a retained source. - Search limits go in your reply, not the page.
Whose project a message is about
- A session's folder says where an agent ran, not what the message concerns. Use a message here only when it names a distinctive project, file, version or behaviour of this repository; an unnamed follow-up only when an earlier input in that session establishes this project.
- With zero assigned session inputs, keep
InsightandOpen threadsbareUnknown; dated commits may still say where the code stands. - Keep actors, nouns and scope exact: "ask the owner" is not calling agents; more property listings are not more details per property.
- A
WebsiteFact needs an original that connects the site to this project. - A request is not permission, delivery or completion; a source comment about a test is not a run.
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 · -30 lines c72ca98a7384
- 6d ago Changed · -2 lines f864abfb3585
- 13d ago Changed · +51 lines d574f4393833
- 14d ago Changed · +3 lines 571362836c51
- 15d ago Changed · +6 lines 60f15b09c651
- 16d ago First seen · 29 lines · 25 tokens per session scan A efcca239cb98
rem-investigate-project is a skill published in the GitHub repository openonion/connectonion (1,497 stars, last pushed today), licensed Apache-2.0. It adds 25 tokens to every session and 728 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
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…
company-ceo
Run a PenguinHarness organization as its CEO — turn the mission into a ticket tree, hire HR and finance first, partition the shared workspace, schedule the calendar, open a channel per stream, review tickets and report to the board in the all-hands channel.
company-hr
Run HR for a PenguinHarness organization — guarantee every employee has an enabled calendar event, hire and offboard employees (channels included), evaluate and improve them (with the default-rsi-toolkit plugin's agent-optimization skill), and keep the handbook's role conventions current.
company-mirror
Run a PenguinHarness organization that mirrors a real company — one digital twin per real colleague, each twin's desk bound to that colleague's chat bot, twins answering what the handbook already knows and relaying the rest to one another instead of hiring, scheduling and filing tickets.
company-setup
Create a company-mode organization together with the user — collect its id, name, mission, shared workspace, model and CEO budget one question at a time, confirm the whole thing in one summary, then run penguin org create and hand the user over to company mode.
agentlas-operations
A set of operating procedures for running Agentlas, a system for coordinating agents, reusable workforces, automation graphs, and shared agent resources. It covers candidate selection, graph creation, asset discovery, and memory rules.