cj-mcp: Instructions file for Codex

AGENTS.md

cj-mcp AGENTS.md is an instructions file for Codex, OpenCode from cityjson/cj-mcp. It costs 1,784 tokens per session, scanned A, original, MIT.

A repository instruction file describing the CityJSON project, its architecture, and how its code is organized. CityJSON is a format for representing 3D city models, while an MCP server gives AI assistants structured access to information or tools.

In plain words
What is it for?
Use it when working on the CityJSON MCP server, its specification converter, or its two-package pnpm workspace monorepo. A monorepo keeps multiple related packages in one repository.
Why use it?
It gives a coding agent the project context and design rules it needs to work consistently in the repository.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is cityjson/cj-mcp's own configuration. It tells Codex and OpenCode how to work on cj-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cj-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to cityjson/cj-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/cityjson/cj-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/cityjson/cj-mcp

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for cj-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cityjson/cj-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/cityjson/cj-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/cityjson/cj-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/cityjson/cj-mcp/agents-md/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.

agentmods 80×15 button for cj-mcp AGENTS.md

Your own site · 80×15
<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="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,784 This file is loaded in full into every session.
When invoked 1,784 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01784 $0.01784
Opus 5.5 $0.00714 $0.00714
Sonnet 5.5 $0.00357 $0.00357
Haiku 4.5 $0.00178 $0.00178

Measured 2mo ago against content hash 1e58da488f31, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 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.

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.

AGENTS.md · 271 lines

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:

  1. spec-converter: Converts Bikeshed (.bs) → HTML → Markdown chapters
  2. 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

Read the full file on GitHub · 271 lines

Changes

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.

  1. 2mo ago First seen · 271 lines · 1,784 tokens per session scan A 1e58da488f31

Subscribe to this mod's changes

cj-mcp AGENTS.md is an instructions file published in the GitHub repository cityjson/cj-mcp (1 stars, last pushed 10mo ago), licensed MIT. It adds 1,784 tokens to every session, about $0.0071 per session on Opus 5.5. 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.

Related

cj-mcp AGENTS.md compared with instructions from other repositories

cj-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
cj-mcp AGENTS.mdcityjson/cj-mcpInstructions file110mo agoMITA1,784Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k3d agoMITA4,313Codex, OpenCode