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/cityjson/cj-mcp/agents-mdgit clone --depth 1 https://github.com/cityjson/cj-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/instructions/cityjson/cj-mcp/agents-md)<a href="https://agentmods.dev/instructions/cityjson/cj-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/cityjson/cj-mcp/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 | $0.01784 | $0.01784 |
| Opus 5 | $0.00892 | $0.00892 |
| Sonnet 5 | $0.00357 | $0.00357 |
| Haiku 4.5 | $0.00178 | $0.00178 |
Grade A, and why
cj-mcp AGENTS.md 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 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.
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 — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
This is an MCP (Model Context Protocol) server that provides AI assistants with structured access to the CityJSON specification. The project converts the CityJSON Bikeshed specification into chapter-separated Markdown files and exposes them through MCP tools for efficient LLM consumption.
Architecture
Monorepo Structure
This project uses a pnpm workspace monorepo with two main packages:
- spec-converter: Converts Bikeshed (.bs) → HTML → Markdown chapters
- mcp-server: Serves specification chapters via MCP protocol
Key Design Principles
- On-Demand Loading: AI fetches specific chapters instead of entire spec
- Two-Stage Conversion: Bikeshed → HTML (via uvx) → Markdown (via Turndown)
- Multi-Transport: Supports both stdio (local) and HTTP (remote) modes
- Chapter-Based: Specification split into digestible chapters with metadata
Project Structure
cityjson-spec-mcp/
├── package.json # Root workspace config
├── pnpm-workspace.yaml # Workspace definition
├── biome.json # Linter/formatter config
├── tsconfig.base.json # Shared TypeScript config
├── vendor/
│ └── cityjson-specs/ # Git submodule (CityJSON spec repo)
├── packages/
│ ├── spec-converter/ # Bikeshed → Markdown converter
│ └── mcp-server/ # MCP server implementation
├── specs/ # Generated specification files
│ ├── index.json # Chapter metadata index
│ └── chapters/ # Individual chapter Markdown files
└── scripts/
└── convert-spec.ts # Conversion orchestration
Development Commands
# Install dependencies (uses pnpm)
pnpm install
# Build all packages
pnpm build
# Build specific package
pnpm --filter mcp-server build
pnpm --filter spec-converter build
# Convert specification (Bikeshed → Markdown)
pnpm convert-spec
# Start MCP server (stdio mode)
pnpm start:stdio
# Start MCP server (HTTP mode)
pnpm start:http
# Lint and format
pnpm lint
pnpm lint:fix
pnpm format
# Development mode with watch
pnpm dev
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 · 271 lines · 1,784 tokens per session scan A 1e58da488f31
cj-mcp AGENTS.md is an instructions file published in the GitHub repository cityjson/cj-mcp (1 stars, last pushed 8mo ago), licensed MIT. It adds 1,784 tokens to every session, about $0.0089 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 2026-08-31.
Other instructions, from other repositories
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
intervals-icu-mcp CLAUDE.md
Instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.
ai-toolkit AGENTS.md
AGENTS.md instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).
flyto-core CLAUDE.md
Claude Code instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.