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 hajekim/agentic-design-patterns-extension --skill mcpgit clone --depth 1 https://github.com/hajekim/agentic-design-patterns-extensionWrote 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/hajekim/agentic-design-patterns-extension/mcp)<a href="https://agentmods.dev/skills/hajekim/agentic-design-patterns-extension/mcp"><img src="https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-extension/mcp/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/hajekim/agentic-design-patterns-extension/mcp"><img src="https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-extension/mcp.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00413 | $0.03876 |
| Opus 5.5 | $0.00165 | $0.01550 |
| Sonnet 5.5 | $0.00083 | $0.00775 |
| Haiku 4.5 | $0.00041 | $0.00388 |
Grade A, and why
mcp-setup 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 1mo 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
result = subprocess.run( This is a copy
100% identical to mcp-setup — 32 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 438 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Model Context Protocol (MCP) Pattern
Overview
The Model Context Protocol (MCP) Pattern provides a standardized, open protocol for connecting LLM-based agents to external tools, data sources, and capabilities. MCP establishes a universal interface — like USB for AI tools — so any MCP-compatible agent can use any MCP-compatible tool server without custom integration code.
Core Principle: Standardize the contract between agents and tools — one protocol to connect everything.
When This Skill Applies
Activate this pattern when:
- You need plug-and-play tool integration across multiple agent frameworks
- Tools should be reusable across different LLM providers and agent systems
- External services (databases, APIs, file systems) must be exposed as agent tools
- A team maintains shared tool servers used by multiple agents
- You want to decouple tool development from agent development
- Cross-organization tool sharing and interoperability is required
Rule of thumb: Use MCP when tool reusability and interoperability matter more than tight integration — build the tool once, use it everywhere.
MCP Architecture
Client-Server Model
┌─────────────────┐ JSON-RPC 2.0 ┌─────────────────┐
│ MCP Client │ ◄─────────────────► │ MCP Server │
│ (LLM Agent) │ (stdio / HTTP) │ (Tool Provider)│
└─────────────────┘ └─────────────────┘
- MCP Client: The agent (LLM host) that consumes tools and resources
- MCP Server: Exposes tools, resources, and prompts via the MCP protocol
- Transport: Communication via stdio (local) or HTTP/SSE (remote)
- Protocol: JSON-RPC 2.0 for all message exchanges
Four MCP Primitives
| Primitive | Description | Use Case |
|---|---|---|
| Tools | Executable functions the LLM can call | Web search, code execution, API calls |
| Resources | Data the LLM can read (like files/DB) | Documents, database records, config files |
| Prompts | Reusable prompt templates with parameters | Standardized task instructions |
| Sampling | Server requests LLM completions | Server-side agentic reasoning |
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.
- 1mo ago First seen · 438 lines · 413 tokens per session scan A 362aedf533f9
mcp-setup is a skill published in the GitHub repository hajekim/agentic-design-patterns-extension (1 stars, last pushed 6mo ago), licensed MIT. It adds 413 tokens to every session and 3,876 once invoked, about $0.0017 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). It is 100% identical to mcp-setup, differing in 32 lines, and is treated as a copy.
Other skills, from other repositories
prompt-engineering
Use this skill when asked to create, refine, analyze, or optimize prompts for Large Language Models (LLMs). This skill ensures adherence to prompt engineering best practices and enforces a rigorous design workflow.
redteam
Expertise in offensive security research, vulnerability analysis, CMS-focused application testing, and red team operations.
redteam-cms
Focused methodology for authorized CMS fingerprinting, component inventory, misconfiguration review, and vulnerability validation.
redteam-exploit-validation
Focused workflow for validating exploitability safely and turning candidate issues into reproducible, bounded proof.
redteam-recon
Focused reconnaissance workflow for authorized security assessments, bug bounty triage, lab targets, and CTF infrastructure.
redteam-reporting
Focused reporting workflow for converting verified red-team work into clear, reproducible assessment artifacts.