hello-world

A small example of an Agent Skill: a reusable set of instructions that guides an agent through a specific task. This example teaches the agent to give a brief greeting and ask a helpful follow-up question.

In plain words
What is it for?
Use it when testing skill validation or showing someone how to create a minimal skill. It applies to friendly greeting requests.
Why use it?
It provides a simple reference for understanding the required structure of a skill. It can also check that the repository's skill linter works correctly.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/skillmds/skillmd/hello-world
Any agent
npx skills add skillmds/skillmd --skill hello-world
Clone the repo
git clone --depth 1 https://github.com/skillmds/skillmd

Made for: Claude Code, Codex.

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 148 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00019 $0.00148
Opus 5 $0.00010 $0.00074
Sonnet 5 $0.00004 $0.00030
Haiku 4.5 $0.00002 $0.00015

Measured 2d ago against content hash 9e9ab373e715, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

examples/skills/hello-world/SKILL.md · 23 lines

What it actually says

Hello World

A minimal example of a well-formed Agent Skill. It doubles as this repository's lint fixture: skillmd lint examples/skills must pass with no errors and no warnings.

When to use

Use this skill when the user asks for a friendly greeting, or wants to see what a minimal SKILL.md looks like before writing their own.

Instructions

  1. Greet the user by name when one is available.
  2. Keep the greeting to a single short sentence.
  3. Offer one helpful follow-up question so the conversation keeps moving.
Changes

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.

  1. 2d ago First seen · 23 lines · 19 tokens per session scan A 9e9ab373e715

Subscribe to this mod's changes

hello-world is a skill published in the GitHub repository skillmds/skillmd (1 stars, last pushed 7d ago), licensed MIT. It adds 19 tokens to every session and 148 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

natural-japanese

仕事の日本語文書を読みやすくわかりやすく書く・直すためのスキル。議事録(文字起こしからの議事録化を含む)、調査レポート・分析レポート、社内ガイド・マニュアル、リサーチメモ・ディスカッションペーパー・企画書・提案書・報告書・メール、スライド構成案といったビジネス文書の作成・校正、「結論から書いて」「論旨を明確に」「見出しを端的に」「専門用語をわかりやすく説明して」といった指示のいずれでも使用する。AI臭さの除去(「AIっぽい」「AI臭い」「機械翻訳っぽい」「不自然」「もっと自然な日本語に」「機械っぽい」「人間っぽくして」「単調」「〜することができる、と言えるだろう、のような言い回し」といった直接・間接・口語の指摘、AIで書いたと言われ…

coji/natural-japanese · 603 tokens

release

Cut a protolint release — preflight checks, tagging, and verifying that all six distribution channels actually published. Use when asked to release, publish, ship a version, or when a release partially failed and needs diagnosing.

yoheimuta/protolint · 47 tokens

add-lint-rule

Add a new lint rule to protolint — every file that has to change, and how the official/unofficial, fixable and auto-disable behaviours are wired. Use when asked to add, implement, or write a new rule.

yoheimuta/protolint · 52 tokens

slopless

Use Slopless to review English Markdown for deterministic AI and human slop signals, including vague phrasing, formulaic prose, weak rhythm, filler, and cliches.

berelevant-ai/slopless · 39 tokens

aap-lint

Skill "aap-lint" from automateyournetwork/netclaw, covering ansible lint operations, mcp server, available tools (9), key concepts and workflow: pre-deployment playbook validation.

automateyournetwork/netclaw · 49 tokens

plugin-quality

审查和改进 Zhin.js 插件质量(Plugin Runtime)。Use when asked to review plugin code, audit structure, or improve before publishing. 检查 definePlugin、约定目录、发送链与安全。.

zhinjs/zhin · 49 tokens