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 kdcokenny/ocx --skill hello-worldgit clone --depth 1 https://github.com/kdcokenny/ocxWrote 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/kdcokenny/ocx/hello-world)<a href="https://agentmods.dev/skills/kdcokenny/ocx/hello-world"><img src="https://agentmods.dev/badge/skills/kdcokenny/ocx/hello-world/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/kdcokenny/ocx/hello-world"><img src="https://agentmods.dev/badge/skills/kdcokenny/ocx/hello-world.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 | $0.00015 | $0.00302 |
| Opus 5.5 | $0.00006 | $0.00121 |
| Sonnet 5.5 | $0.00003 | $0.00060 |
| Haiku 4.5 | $0.00002 | $0.00030 |
Grade A, and why
hello-world 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 27d 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.
What it actually says
Hello World
A simple example skill demonstrating the OCX skill format.
TL;DR
This skill teaches an AI assistant how to greet users in a friendly, personalized way.
When to Use
- When the user asks for a greeting
- When introducing yourself to a new user
- When demonstrating basic conversation skills
Instructions
When greeting a user:
- Be warm and welcoming - Use a friendly, approachable tone
- Personalize when possible - If you know the user's name, use it
- Keep it brief - A greeting should be concise, not a paragraph
- Match the context - Formal greetings for professional contexts, casual for informal
Examples
Casual greeting:
Hey there! How can I help you today?
Professional greeting:
Good morning. I'm ready to assist you with your project.
Personalized greeting:
Hi Sarah! Great to see you again. What are we working on today?
What NOT to Do
- Don't be overly enthusiastic (avoid excessive exclamation marks)
- Don't use outdated slang or try too hard to be "hip"
- Don't make assumptions about the user's mood or day
Notes
This is an example skill included with the OCX registry starter template. Feel free to modify or delete it as you build your own registry.
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.
- 27d ago Changed · +5 lines · +15 tokens per session 832d0f05415d
- 1mo ago First seen · 44 lines · 0 tokens per session scan A 35259b5c768f
hello-world is a skill published in the GitHub repository kdcokenny/ocx (977 stars, last pushed 27d ago), licensed MIT. It adds 15 tokens to every session and 302 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 2026-08-30.
Other skills, from other repositories
cli-builder
Guide for building TypeScript CLIs with Bun. Use when creating command-line tools, adding subcommands to existing CLIs, or building developer tooling. Covers argument parsing, subcommand patterns, output formatting, and distribution.
contract-integrity
Maintains an Agulater Agent Operational Contract after agent files change. Use when changing AGENTS.md, harness policy, graphs, skills, context layers, evaluation, or handoff behavior.
change-safety
Plans small software changes, protects existing work, and selects proportionate verification.
task-orientation
Turns a new request into a bounded task by selecting context, naming uncertainty, and defining verification. Use at the start of a new task or after a material task change.
evidence-synthesis
Builds research findings from inspected sources while preserving uncertainty and provenance.
imaging-data-commons
Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.