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 agentmods add skills/basementstudio/xmcp/resource-designnpx skills add basementstudio/xmcp --skill resource-designgit clone --depth 1 https://github.com/basementstudio/xmcpWrote 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/basementstudio/xmcp/resource-design)<a href="https://agentmods.dev/skills/basementstudio/xmcp/resource-design"><img src="https://agentmods.dev/badge/skills/basementstudio/xmcp/resource-design.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 | $0.00025 | $0.00894 |
| Opus 5 | $0.00013 | $0.00447 |
| Sonnet 5 | $0.00005 | $0.00179 |
| Haiku 4.5 | $0.00003 | $0.00089 |
Grade A, and why
resource-design 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create xmcp Resource
You are helping the user create a new xmcp resource. Follow this interactive workflow.
Step 1: Gather Information
Before generating any code, ask the user these questions using AskUserQuestion:
-
Resource name (if not provided): What should the resource be named? (Use kebab-case)
-
Resource type: Ask which type of resource they need:
- Static - Fixed content that doesn't change (configuration, documentation)
- Dynamic - Content that depends on parameters (user profiles, reports)
- File-based - Content read from files (logs, data files)
-
URI pattern: How should the resource be accessed?
- Simple:
config://appordocs://readme - With parameters:
users://[userId]/profile - Nested:
reports://[year]/[month]/summary
- Simple:
-
Content details:
- What is the content about?
-
Widget support (optional): Ask if they need OpenAI widget rendering.
Step 2: Generate the Resource
Create the resource file in src/resources/ following the routing conventions:
File Location & Routing
Resources use file-based routing similar to Next.js:
src/resources/
├── (config)/ # Route group (not in URI)
│ └── app.ts # → config://app
├── (users)/
│ └── [userId]/ # Dynamic segment
│ └── profile.ts # → users://[userId]/profile
└── docs/
└── readme.ts # → docs://readme
Routing conventions:
(folder)- Route group, excluded from URI path[param]- Dynamic parameter segment- Filename becomes the final URI segment
Resource Structure Reference
Every xmcp resource has two main exports:
// 1. Metadata (optional) - Resource configuration
export const metadata: ResourceMetadata = { /* ... */ };
// 2. Handler (required) - Default export function
export default function handler(params?) { /* ... */ }
// 3. Schema (optional) - For dynamic resources with parameters
export const schema = { /* ... */ };
Quick Reference
What ships with it
1 file 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.
- 5d ago First seen · 125 lines · 25 tokens per session scan A 6fea2eb811c9
resource-design is a skill published in the GitHub repository basementstudio/xmcp (1,326 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 894 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 2026-08-30.
Other skills, from other repositories
sensitive-logging-audit
Audit and fix sensitive-data exposure through Python runtime logging in openai-agents-python. Use when reviewing logging, print, warnings, stderr, traceback, MCP names, model or tool exceptions, redaction flags, or any diagnostic path that may retain user data.
sovereign-economics-engine
Unified business model evaluator, client filter, pricing engine, and distribution architect. Absorbs 31 business + 8 marketing + 13 content + 2 acquisition protocols.
om-judge-agent-session
Judge generated Open Mercato code from a standalone harness eval or a user-shared agent session bundle. Use for LLM-as-judge validation, generative eval review, session/artifact analysis, harness-quality diagnosis, "judge this session", "analyze this eval", or "oceń sesję/agenta"; checks fixed validation evidence…
om-app-spec-writing
Write and review a business-level App Spec — domain model, workflows with ROI, user stories with failure paths, platform gap analysis in atomic commits, and a phased rollout — BEFORE any feature spec or code exists. One level above om-spec-writing, which decomposes the finished App Spec into feature specs. Use when…
frontmcp-extensibility
Use when extending FrontMCP beyond the core SDK by integrating external npm packages, libraries, or third-party services into providers and tools. Covers VectoriaDB for in-memory semantic and vector search (ML-based embeddings or TF-IDF keyword engines, with persistence) and the tamper-evident, hash-chained skill…
jupyter-live-kernel
Use a live Jupyter kernel for stateful, iterative Python execution via hamelnb. Load this skill when the task involves exploration, iteration, or inspecting intermediate results — data science, ML experimentation, API exploration, or building up complex code step-by-step. Uses terminal to run CLI commands against a…