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 srprasanna/mcp-skill-hub --skill advanced-examplegit clone --depth 1 https://github.com/srprasanna/mcp-skill-hubWrote 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/srprasanna/mcp-skill-hub/advanced-example)<a href="https://agentmods.dev/skills/srprasanna/mcp-skill-hub/advanced-example"><img src="https://agentmods.dev/badge/skills/srprasanna/mcp-skill-hub/advanced-example.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 5.1 | $0.00014 | $0.01471 |
| Opus 5 | $0.00007 | $0.00736 |
| Sonnet 5 | $0.00003 | $0.00294 |
| Haiku 4.5 | $0.00001 | $0.00147 |
Grade A, and why
advanced-example scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
system: ["git", "curl"] How it starts
The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Advanced Example Skill
This skill demonstrates all available metadata fields and shows how to organize a complex skill with multiple subdirectories, examples, and templates.
Complete Folder Structure
advanced-example/
├── SKILL.md ← This file with full metadata
├── examples/ ← Example files directory
│ ├── example1.py ← Python example
│ └── example2.txt ← Text example
├── templates/ ← Template files directory
│ └── template.txt ← Template file
└── README.md ← Additional documentation (optional)
All Metadata Fields Explained
Required Fields
- name: Unique identifier (kebab-case recommended)
- description: Brief, clear description of what the skill does
Version and Authorship
- version: Semantic version (MAJOR.MINOR.PATCH)
- author: Creator's name or team
- created: Creation date (ISO format: YYYY-MM-DD)
- updated: Last update date (ISO format)
Dependencies
You can specify dependencies in two formats:
Nested format (recommended for categorized deps):
dependencies:
python: ["package>=1.0.0", "another-package"]
system: ["git", "curl"]
Flat format (simpler):
dependencies: ["package1", "package2", "tool1"]
Categorization and Discovery
- category: Main category for grouping (e.g., "data-analysis", "document-creation")
- tags: Array of tags for search and filtering
- complexity: Difficulty level ("beginner", "intermediate", or "advanced")
Usage Guidance
- when_to_use: Array of scenarios when this skill should be used
- related_skills: Array of related skill names for cross-referencing
Examples
- has_examples: Boolean flag indicating if examples are included
- example_files: Array of paths to example files (relative to skill folder)
Dependency Management
The server supports tracking dependencies so users know what's required:
Python Dependencies
dependencies:
python: ["pydantic>=2.0.0", "numpy>=1.20.0"]
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 217 lines · 14 tokens per session scan A 492c50206d29
advanced-example is a skill published in the GitHub repository srprasanna/mcp-skill-hub (12 stars, last pushed 10mo ago), licensed MIT. It adds 14 tokens to every session and 1,471 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
Complete Rust Development
A comprehensive skill for Rust development that combines error handling, testing, and logging patterns. Demonstrates the 'includes' composition feature by merging content from multiple standalone skills.
Complete Rust Development
A comprehensive skill for Rust development that combines error handling, testing, and logging patterns. Demonstrates the 'includes' composition feature by merging content from multiple standalone skills.
hello-world
Selam veren örnek skill. Yeni başlayanlar için template.
hello-world
A simple example skill that demonstrates basic skill structure.
blog-draft
Draft a blog post from ideas and resources. Use when users want to write a blog post, create content from research, or draft articles. Guides through research, brainstorming, outlining, and iterative drafting with version control.
claude-md
Create or update CLAUDE.md files following best practices for optimal AI agent onboarding.