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/mapbox/mcp-devkit-server/claude-mdgit clone --depth 1 https://github.com/mapbox/mcp-devkit-serverWhat 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 | $0.01632 | $0.01632 |
| Opus 5 | $0.00816 | $0.00816 |
| Sonnet 5 | $0.00326 | $0.00326 |
| Haiku 4.5 | $0.00163 | $0.00163 |
Grade A, and why
mcp-devkit-server CLAUDE.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 2d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Mapbox MCP DevKit Server
Overview
This is an MCP (Model Context Protocol) server providing "geospatial intelligence capabilities through Mapbox APIs" for AI agents, enabling map styling, GeoJSON visualization, token management, and geocoding.
Tech Stack
- Runtime: Node.js 22+ LTS
- Language: TypeScript (strict mode)
- Testing: Vitest
- Package Manager: npm
Project Structure
The codebase organizes into:
src/index.ts- Main entry point with .env loading and server initializationsrc/config/toolConfig.ts- Configuration parser for tool filtering and MCP-UI togglessrc/tools/- MCP tool implementations withBaseToolabstract class and registrysrc/prompts/- MCP prompt implementations withBasePromptabstract class and registrysrc/resources/- Static reference data (style specs, token scopes, Streets v8 fields)src/utils/- HTTP pipeline, JWT parsing, tracing, and version utilitiesskills/- Agent Skills providing domain expertise (cartography, security, style patterns)
Key Architectural Patterns
Tool Architecture: All tools extend BaseTool<InputSchema, OutputSchema> or MapboxApiBasedTool<InputSchema, OutputSchema>. Tools auto-validate inputs and outputs using Zod schemas. Each tool lives in src/tools/tool-name-tool/ with separate *.input.schema.ts, *.output.schema.ts, and *.ts files.
Prompt Architecture: All prompts extend BasePrompt abstract class. Prompts orchestrate multi-step workflows, guiding AI assistants through complex tasks with best practices built-in. Each prompt lives in src/prompts/ with separate files per prompt (e.g., CreateAndPreviewStylePrompt.ts). Prompts use kebab-case naming (e.g., create-and-preview-style).
HTTP Pipeline System: "Never patch global.fetch—use HttpPipeline with dependency injection instead." The HttpPipeline class applies policies (User-Agent, retry logic) via a chain-of-responsibility pattern. See src/utils/httpPipeline.ts:20.
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.
- 2d ago First seen · 137 lines · 1,632 tokens per session scan A f542f9d7e28e
mcp-devkit-server CLAUDE.md is an instructions file published in the GitHub repository mapbox/mcp-devkit-server (60 stars, last pushed 6d ago), licensed MIT. It adds 1,632 tokens to every session, about $0.0082 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 instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.