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 VoDaiLocz/kilo-kit-mcp --skill mcp-agent-patternsgit clone --depth 1 https://github.com/VoDaiLocz/kilo-kit-mcpWrote 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/vodailocz/kilo-kit-mcp/mcp-agent-patterns)<a href="https://agentmods.dev/skills/vodailocz/kilo-kit-mcp/mcp-agent-patterns"><img src="https://agentmods.dev/badge/skills/vodailocz/kilo-kit-mcp/mcp-agent-patterns/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/vodailocz/kilo-kit-mcp/mcp-agent-patterns"><img src="https://agentmods.dev/badge/skills/vodailocz/kilo-kit-mcp/mcp-agent-patterns.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 | $0.00044 | $0.00828 |
| Opus 5 | $0.00022 | $0.00414 |
| Sonnet 5 | $0.00009 | $0.00166 |
| Haiku 4.5 | $0.00004 | $0.00083 |
Grade A, and why
mcp-agent-patterns 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Agent Patterns (Model Context Protocol)
Overview
The Model Context Protocol (MCP) provides a standardized way for AI agents to interact with external tools, data resources, and environments. This skill defines architectural patterns and implementation best practices for building, connecting, and optimizing MCP-based systems within the KILO-KIT ecosystem.
When To Use
- Implementing custom MCP servers or clients.
- Integrating external services (APIs, DBs, filesystems) as MCP servers.
- Optimizing context windows when dealing with large tool catalogs.
- Implementing real-time resource synchronization or complex multi-server orchestrations.
- Security-critical integrations requiring isolated execution environments.
Core MCP Concepts
- Tools: Executable functions exposed to the LLM.
- Resources: Data sources that can be read by the LLM (e.g., file contents, database records).
- Prompts: Reusable templates or workflows designed to be used by the LLM.
- Sampling: A protocol allowing an MCP server to request the host client to perform LLM inference on its behalf, enabling agentic tool behavior.
Advanced Patterns
Dynamic Tool Catalog & Progressive Loading
To prevent token bloat:
- Manifest Exposure: Expose only essential, high-level tool definitions initially.
- On-Demand Loading: Load detailed JSON Schemas only when a tool is selected or explicitly requested by the agent context.
MCP Sampling Protocol
When a server needs LLM intelligence (e.g., parsing unstructured output or making a decision):
- The server issues a
sampling/createMessagerequest to the client. - The client acts as the host/gateway, maintaining control over the model selection and cost.
Resource Streaming & Subscriptions
- Use URI Templates (
res://server/type/{id}) to create flexible resource paths. - Implement Resource Subscriptions to push data updates from the server to the client without polling.
Eager vs Lazy Tool Registration
- Eager: Best for small sets of essential core tools (zero-latency startup).
- Lazy: Mandatory for large or dynamic catalogs to keep initial prompts lean.
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.
- yesterday Changed 4d2b9fd612d8
- 9d ago First seen · 66 lines · 44 tokens per session scan A a2fed8d178fc
mcp-agent-patterns is a skill published in the GitHub repository VoDaiLocz/kilo-kit-mcp (26 stars, last pushed yesterday), licensed Apache-2.0. It adds 44 tokens to every session and 828 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
llm-structured-output
Get reliable JSON, enums, and typed objects from LLMs using responseformat, tooluse, and schema-constrained decoding across OpenAI, Anthropic, and Google APIs.
drizzle-orm-expert
Expert in Drizzle ORM for TypeScript — schema design, relational queries, migrations, and serverless database integration. Use when building type-safe database layers with Drizzle.
landing-page-generator
Generates high-converting Next.js/React landing pages with Tailwind CSS. Uses PAS, AIDA, and BAB frameworks for optimized copy/components (Heroes, Features, Pricing). Focuses on Core Web Vitals/SEO.
tdmcp-pipeline
Orchestrates the tdmcp feature team end-to-end: design/wireframe → build → integrate → QA → release. Use whenever the user wants to build, implement, develop, ship, or add one or more tdmcp features/tools/effects/controls/AI-prompts for TouchDesigner, or to run them through a coordinated design→develop→QA→deploy…
memb-skill
BDB local-first long-term memory engine (memB). Use when querying, remembering, or adapting preferences, code architectures, and developer patterns across tasks.
startcycle-graph-user
Use when a task needs a small, throwaway multi-agent fan-out (a couple of parallel workers plus a review pass) in ANY project, without the full /startcycle-graph contract — no .agents/graph.md bootstrap, no state.json schema, no persistent files. Model-tiered by role (opus plan, sonnet review, haiku or an external CLI…