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 find-selling-pointsgit 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/find-selling-points)<a href="https://agentmods.dev/skills/openonion/connectonion/find-selling-points"><img src="https://agentmods.dev/badge/skills/openonion/connectonion/find-selling-points/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/find-selling-points"><img src="https://agentmods.dev/badge/skills/openonion/connectonion/find-selling-points.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00077 | $0.01799 |
| Opus 5 | $0.00039 | $0.00899 |
| Sonnet 5 | $0.00015 | $0.00360 |
| Haiku 4.5 | $0.00008 | $0.00180 |
Grade A, and why
find-selling-points 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 10d 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Find Selling Points
Find what is genuinely unusual about this project, prove it, and write it down in a form someone can publish without lying.
This skill exists because the failure mode is not "we could not think of anything". It is the opposite: it is easy to generate plausible marketing sentences, and plausible marketing sentences about software are wrong most of the time. Everything below is built to make a claim expensive to assert and cheap to check.
The two rules
Rule 1 — a claim you cannot cite does not exist. Every point ends in
file:line. If you cannot cite it, you delete it. Not soften it, not hedge it —
delete it. A missing selling point costs nothing. A false one costs a customer.
Rule 2 — say what someone can DO, not how the code looks. "Functions become tools automatically" is a fact about our source. "You can hand a client a link and they talk to the agent in a browser with nothing installed" is a fact about their day. Only the second kind ships.
What does not count
Reject these on sight. They are the reflexes to suppress, not options to weigh:
- Comparisons to other frameworks. "Fewer lines than LangChain", "unlike AutoGPT", any table with a competitor column. Comparing files us in their category and dates instantly. We are not a better framework; we are not a framework.
- Line counts. "2 lines", "3 lines", "8 lines". Nobody writes those lines — the CLI writes the project. The number was retired on purpose; do not resurrect it in a new costume.
- Developer ergonomics as the headline. Type hints, decorators, no boilerplate, clean API. Real, and nobody outside the repo cares. These are supporting detail at best.
- Anything an LLM could write about any agent library. If the sentence survives find-and-replacing our name with a competitor's, it says nothing.
- Adjectives standing in for facts. "Powerful", "seamless", "production-ready", "enterprise-grade". Replace with the specific thing, or cut.
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.
- 10d ago First seen · 172 lines · 77 tokens per session scan A f6e9432ef352
find-selling-points is a skill published in the GitHub repository openonion/connectonion (1,480 stars, last pushed yesterday), licensed Apache-2.0. It adds 77 tokens to every session and 1,799 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
agent-lightning
Provides the action space, tradeoffs, and evaluation context for improving an editable AI agent against a benchmark while preserving its deployment contract. Use when optimizing agent accuracy, cost, latency, or reliability.
agentfield-use
Whenever you have a discrete task to perform — one the user delegated, or one that arose inside your own work — check FIRST whether an installed AgentField agent covers it, and offload to it by default when one does. Coverage, not task size, is the test: even a small job goes to a covering agent. The check is cheap …
remote-claude-code
Run Claude Code on a remote host over SSH — a persistent expect-driven login session, headless claude -p with the stdin fix, the interactive TUI inside a remote tmux driven by send-keys/capture-pane (one keystroke at a time, capture-verified; relayed user messages go through verbatim), and multi-turn continuity via…
agentfield-personal
Build and install a personal AI agent on this machine's AgentField: real source in /agentfield-agents, packaged with agentfield-package.yaml, installed with af install, started with af run, registered on the local control plane, and visible in AgentField Desktop with a keys form and an auto-start toggle. Use when the…
agent-optimization
Improve an Agent State through versioned scores and score-linked Traces from a frozen Benchmark.
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.