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/agents-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 | $0.00669 | $0.00669 |
| Opus 5 | $0.00334 | $0.00334 |
| Sonnet 5 | $0.00134 | $0.00134 |
| Haiku 4.5 | $0.00067 | $0.00067 |
Grade A, and why
mcp-devkit-server 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 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Mapbox MCP DevKit Server
Instructions for AI agents working with the Mapbox MCP DevKit Server. For project overview and user documentation, see README.md and CLAUDE.md.
Critical Patterns
Tool Architecture:
- Tool naming: Tool names (MCP identifiers) must be
snake_case_tool(e.g.,list_styles_tool). TypeScript class names followPascalCaseToolconvention (e.g.,ListStylesTool) - Schema files: Always separate
*.schema.tsfrom*.tool.ts - Schema validation: Use Zod, export both schema and inferred type
- Tool location:
src/tools/tool-name-tool/with all three files (schema, implementation, tests)
Testing:
- After adding/removing tools:
npm test -- src/tools/tool-naming-convention.test.ts --updateSnapshot - Never update snapshots without verifying changes
- Tool snapshots capture class names (TypeScript
PascalCaseTool), tool names (MCPsnake_case_tool), and descriptions
Token Management:
- All Mapbox API tools require
MAPBOX_ACCESS_TOKENwith specific scopes - Token scope errors are the #1 issue - check
README.mdfor required scopes - Use
VERBOSE_ERRORS=truefor debugging authentication failures
Factual Errors to Watch For
Incorrect Tool Naming:
- ❌
list_styles→ ✅list_styles_tool - ❌
ListStyles→ ✅ListStylesTool
Incorrect File Structure:
- ❌ Schema defined in
*.tool.ts→ ✅ Schema in separate*.schema.ts - ❌ Tool in
src/tools/ListStylesTool.ts→ ✅ Tool insrc/tools/list-styles-tool/ListStylesTool.ts
Incorrect Class References:
- ❌
ToolRegistry.registerTool()→ ✅ Tools auto-registered viasrc/tools/index.tsexports - ❌ Manual tool instantiation → ✅ Use plop generator:
npx plop create-tool
Incorrect Token Scope Usage:
- ❌ Using default token for all operations → ✅ Check required scopes per tool in
README.md - ❌
styles:readfor creating styles → ✅styles:writerequired
Essential Commands
npm run build # Always build before running
npm test # Run all tests
npx plop create-tool # Generate new tool scaffold
npm run lint:fix && npm run format:fix # Fix code style
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 · 73 lines · 669 tokens per session scan A d64ee55693a1
mcp-devkit-server AGENTS.md is an instructions file published in the GitHub repository mapbox/mcp-devkit-server (60 stars, last pushed 6d ago), licensed MIT. It adds 669 tokens to every session, about $0.0033 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.