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 instructions/g12789/mcp-quickstart/agents-mdgit clone --depth 1 https://github.com/G12789/mcp-quickstartWrote 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/instructions/g12789/mcp-quickstart/agents-md)<a href="https://agentmods.dev/instructions/g12789/mcp-quickstart/agents-md"><img src="https://agentmods.dev/badge/instructions/g12789/mcp-quickstart/agents-md.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 | $0.00714 | $0.00714 |
| Opus 5 | $0.00357 | $0.00357 |
| Sonnet 5 | $0.00143 | $0.00143 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
mcp-quickstart AGENTS.md 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl.js curl tokenizer/parser + curl->tool codegen (the --from-curl feature) How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding agents working in this repository.
What this project is
mcp-quickstart is a CLI that scaffolds Model Context Protocol (MCP) servers. It is
published to npm as create-mcp-quickstart and invoked via
npm create mcp-quickstart@latest or npx mcp-quickstart.
Layout
src/
index.js CLI entry: arg parsing, prompts, orchestration
scaffold.js recursive template copy + placeholder replacement (incl. extra vars)
openapi.js OpenAPI loader + spec->tools codegen (the --from-openapi feature)
curl.js curl tokenizer/parser + curl->tool codegen (the --from-curl feature)
schema.js JSON/OpenAPI schema -> zod string (+ $ref resolve, infer from value)
templates/
typescript-stdio/ working TS MCP server (stdio)
typescript-http/ working TS MCP server (streamable HTTP, Express)
typescript-openapi/ TS MCP server generated from an OpenAPI spec / curl ({{TOOLS}} injection)
typescript-cloudflare/ remote MCP server for Cloudflare Workers (createMcpHandler, wrangler)
typescript-cloudflare-openapi/ API-backed remote MCP server for Workers ({{TOOLS}} injection + http.ts); used when a generated source is combined with --transport cloudflare
python-stdio/ working Python MCP server (stdio)
python-http/ working Python MCP server (streamable HTTP, FastMCP)
Conventions
- Pure ESM, Node >= 18, no build step for the CLI itself.
- Template files use
{{projectName}}/{{projectNameSnake}}placeholders, replaced inscaffold.js. - Dotfiles are stored with a leading underscore (
_gitignore,_env.example) and renamed on generation, so npm does not mangle them when publishing. - Inside generated templates, keep pure logic in
tools.ts/tools.pyand the MCP wiring inindex.ts/server.py. This keeps tests dependency-free. - On stdio servers, logs go to stderr only — stdout is the protocol channel.
How to test changes
npm install
node src/index.js tmp-out --lang ts -y # generate a TS project
node src/index.js tmp-out-py --lang python -y
node src/index.js tmp-api --from-openapi scripts/fixtures/sample-openapi.json -y
node src/index.js tmp-curl --from-curl scripts/fixtures/sample-curl.txt -y
node src/index.js tmp-edge --from-openapi scripts/fixtures/sample-openapi.json --transport cloudflare -y # API -> Workers
npm run test:e2e # scaffolds + builds + tests every variant
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.
- 4d ago First seen · 61 lines · 714 tokens per session scan A d2f2d07a68f7
mcp-quickstart AGENTS.md is an instructions file published in the GitHub repository G12789/mcp-quickstart (81 stars, last pushed 2mo ago), licensed MIT. It adds 714 tokens to every session, about $0.0036 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
expo_boilerplate CLAUDE.md
Instructions for chohra-med/expo_boilerplate, covering claude.md — mobilelauncher lt, 🌿 branches — the trunk is development, there is no main, project skill, what this project is and the master rules.
mcp-me AGENTS.md
Instructions for paladini/mcp-me, covering agent instructions, critical rules, pre-commit checklist, project structure and version locations.
vibe-stack AGENTS.md
Instructions for vibestackdev/vibe-stack, covering agents.md — ai coding agent instructions, project overview, tech stack, architecture principles and directory structure.
vibe-stack CLAUDE.md
Instructions for vibestackdev/vibe-stack, covering claude.md — vibe stack architecture rules, for use with claude code (anthropic's agentic cli), project overview, tech stack and critical build commands.
expo_boilerplate AGENTS.md
Instructions for chohra-med/expo_boilerplate, covering agents.md — mobilelauncher lt, project and 🎯 the master rules location.
mcp-me copilot-instructions.md
Instructions for paladini/mcp-me, covering copilot instructions, available mcp resources, when to proactively load my profile and the askaboutme tool.