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.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 | $0.00413 | $0.03876 |
| Opus 5 | $0.00206 | $0.01938 |
| Sonnet 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 7d 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.
- 7d 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 5mo ago), licensed MIT. It adds 413 tokens to every session and 3,876 once invoked, about $0.0021 per session on Opus 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.