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 agentmods add skills/openonion/connectonion/oonpx skills add openonion/connectonion --skill oogit 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/oo)<a href="https://agentmods.dev/skills/openonion/connectonion/oo"><img src="https://agentmods.dev/badge/skills/openonion/connectonion/oo.svg" alt="Measured on agentmods" 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 | $0.00056 | $0.01488 |
| Opus 5 | $0.00028 | $0.00744 |
| Sonnet 5 | $0.00011 | $0.00298 |
| Haiku 4.5 | $0.00006 | $0.00149 |
Grade A, and why
oo 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 today.
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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Connect, publish, and follow with oo
Route the request before running anything:
| User wants | Action |
|---|---|
Ask or delegate to a remote 0x... agent |
Use the Connect flow |
| Create the global identity and skill library | Use Setup |
| Share selected local skills | Use Publish |
| Follow a publisher for the first time | Run co sub sync <0xaddress> |
| Refresh one already-pinned publisher | Run co sub sync <address-or-local-alias> |
| Refresh everyone | Run co sub |
| See or remove subscriptions | Run co sub list or co sub remove <address-or-local-alias> |
| Accept or reject a follower | Explain that public subscriptions have no publisher-approval step |
Keep the protocol layers straight
- OIP is the live, authenticated Agent protocol: CONNECT, INPUT, EXEC, events, OUTPUT, session ownership, modes, approvals, and cancellation.
- ANNOUNCE publishes a signed public profile to the relay.
co announceadds a portableprofile-v2signature and monotonic revision. co subis a local pull/sync relationship. It is not a SUBSCRIBE message, push channel, access-control handshake, or proof that the content is safe.
Do not recreate HTTP endpoints, signing, profile verification, rollback state,
or fan-out in ad-hoc Python. The co CLI owns those details.
Connect
Require one exact 66-character address (0x plus 64 hex characters) and a task.
Use the installed SDK; it already probes safe direct endpoints and falls back to
the relay:
from connectonion import connect
remote = connect("0x...")
response = remote.input("the user's task", timeout=300)
print(response.text)
print("done=", response.done)
connect() uses the current project's identity, then ~/.co. If neither
identity exists, tell the user to run co init for global credentials or Setup
below for a global publishable profile. co init ./ explicitly initializes a
project using that global identity; it does not mint a separate project keypair.
Never generate an identity silently.
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.
- today Changed · +2 lines 962433dc0bd4
- yesterday First seen · 154 lines · 56 tokens per session scan A 2a954838e5a9
oo is a skill published in the GitHub repository openonion/connectonion (1,481 stars, last pushed today), licensed Apache-2.0. It adds 56 tokens to every session and 1,488 once invoked, about $0.0003 per session on Opus 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 2026-09-02.
Other skills, from other repositories
edgeone skill scanner
Scan any agent skill for security risks before you install or use it. Powered by Tencent Zhuque Lab A.I.G (AI-Infra-Guard). 100% local static analysis — no file contents or credentials leave your device. Compatible with CodeBuddy, Cursor, Windsurf, Claude Code, OpenClaw and more. Triggers on: 这个 skill 安全吗, skill 安全扫描…
baby-sit
Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.
nano-banana-pro-openrouter
Deterministic OpenRouter image generation adapter for Nano Banana Pro / Gemini image models. Use as skillexec when a meta-skill needs local image files and structured IMAGEREADY records without spawning an LLM agent.
skill-creator-linter
Internal tool (not user-invocable). Called by meta-skill-creator as a DAG step (kind: agent) to lint a candidate meta-skill SKILL.md against G1 (parse + reference check + xmlescape grep + structural lint) and G2 (scheduler dry-run with stub executors). Deterministic, sub-second, no LLM. Returns JSON diagnostics.
paper-abstract-author
Write the abstract after the paper body has been revised, using the final claims and evidence.
langbot-deploy
Deploy and configure a LangBot instance — Docker / Docker Compose, Kubernetes, the config.yaml model, the Box sandbox runtime, the plugin runtime, and the global API key. Use when installing, deploying, upgrading, or configuring LangBot in production or self-hosted environments. Triggers on "deploy langbot", "langbot…