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 sskarz/nanoclawbster --skill mcp-buildergit clone --depth 1 https://github.com/sskarz/nanoclawbsterWrote 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/sskarz/nanoclawbster/mcp-builder)<a href="https://agentmods.dev/skills/sskarz/nanoclawbster/mcp-builder"><img src="https://agentmods.dev/badge/skills/sskarz/nanoclawbster/mcp-builder/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/sskarz/nanoclawbster/mcp-builder"><img src="https://agentmods.dev/badge/skills/sskarz/nanoclawbster/mcp-builder.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 | $0.00036 | $0.01552 |
| Opus 5.5 | $0.00014 | $0.00621 |
| Sonnet 5.5 | $0.00007 | $0.00310 |
| Haiku 4.5 | $0.00004 | $0.00155 |
Grade A, and why
mcp-builder 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 2mo 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.
import { execSync } from "child_process"; How it starts
The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Building Custom MCP Servers
MCP (Model Context Protocol) servers extend what I can do by exposing new tools. I can write, register, and use them across sessions.
File locations
- Server code:
/workspace/group/mcp-servers/<server-name>/index.js - Shared dependencies:
/workspace/group/mcp-servers/package.json - Registration:
/workspace/group/.mcp.json
All paths under /workspace/group/ persist across container restarts.
Step-by-step: Create and register an MCP server
1. Set up shared dependencies (first time only)
All MCP servers share a single node_modules at the mcp-servers/ root. Only do this once:
mkdir -p /workspace/group/mcp-servers
cd /workspace/group/mcp-servers
if [ ! -f package.json ]; then
npm init -y
# Add "type": "module" for ES module support
node -e "const p=require('./package.json'); p.type='module'; require('fs').writeFileSync('package.json', JSON.stringify(p, null, 2)+'\n')"
npm install @modelcontextprotocol/sdk zod
fi
2. Write the server
Create /workspace/group/mcp-servers/<name>/index.js:
import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
import { z } from "zod";
const server = new McpServer({ name: "<name>", version: "1.0.0" });
server.tool(
"tool-name",
"Description of what this tool does",
{ param: z.string().describe("A parameter") },
async ({ param }) => ({
content: [{ type: "text", text: `Result: ${param}` }],
})
);
const transport = new StdioServerTransport();
await server.connect(transport);
Node resolves imports from the shared node_modules up the directory tree — no per-server install needed.
3. Test it
echo '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"capabilities":{},"clientInfo":{"name":"test"},"protocolVersion":"2024-11-05"}}' | node /workspace/group/mcp-servers/<name>/index.js
Should return a JSON response without errors.
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.
- 2mo ago First seen · 216 lines · 36 tokens per session scan A 6aa80d83cf96
mcp-builder is a skill published in the GitHub repository sskarz/nanoclawbster (2 stars, last pushed 3mo ago), licensed MIT. It adds 36 tokens to every session and 1,552 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
evaluation-nemo-evaluator
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.
stripe-projects
Provision SaaS services + sync creds via Stripe Projects.
gemini-api-agent-platform
Guides the usage of the Gemini API on Agent Platform with the Google Gen AI SDK for enterprise AI applications. Covers SDK usage (Python, JS/TS, Go, Java, C#), capabilities like Live API, tools, multimedia generation, caching, and batch prediction.
event-store-design
Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.
cqrs-implementation
Implement Command Query Responsibility Segregation for scalable architectures. Use when separating read and write models, optimizing query performance, or building event-sourced systems.
workflow-orchestration-patterns
Design durable workflows with Temporal for distributed systems. Covers workflow vs activity separation, saga patterns, state management, and determinism constraints. Use when building long-running processes, distributed transactions, or microservice orchestration.