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/copilot-instructionsgit 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 | $0.00619 | $0.00619 |
| Opus 5 | $0.00309 | $0.00309 |
| Sonnet 5 | $0.00124 | $0.00124 |
| Haiku 4.5 | $0.00062 | $0.00062 |
Grade A, and why
mcp-devkit-server copilot-instructions.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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Copilot Repository Instructions
Instructions for GitHub Copilot working on the Mapbox MCP DevKit Server. See Copilot repository instructions guide.
1. Review Code Before Suggesting Changes
- Read existing patterns before proposing solutions
- Check
src/tools/for tool implementation patterns - Reference
CLAUDE.mdfor architecture decisions - Verify token scope requirements in
README.md
2. Security & Token Management
- Never hardcode tokens or credentials
- All Mapbox API calls require
MAPBOX_ACCESS_TOKENwith specific scopes - Token scope mismatches are the primary failure mode
- Use
VERBOSE_ERRORS=truefor debugging auth issues - Reference token scope requirements in
README.mdbefore implementing
3. Code Quality & Style
- TypeScript strict mode - No implicit any, proper typing required
- Tool naming - Tool names (MCP identifiers) must be
snake_case_tool(e.g.,list_styles_tool). TypeScript class names followPascalCaseToolconvention (e.g.,ListStylesTool) - Schema separation - Schema in
*.schema.ts, implementation in*.tool.ts - Use plop generator -
npx plop create-toolfor new tools - Zod validation - All tool inputs validated with Zod schemas
- ESLint and Prettier handle formatting - run
npm run lint:fix && npm run format:fix
4. Testing Requirements
- Run tests before committing -
npm test - Update snapshots deliberately - After adding/removing/modifying tools:
npm test -- src/tools/tool-naming-convention.test.ts --updateSnapshot - Never update snapshots without understanding what changed
- Snapshot tests capture tool metadata (TypeScript class names in
PascalCaseToolformat, MCP tool names insnake_case_toolformat, descriptions)
5. Collaboration Standards
- Focused commits - One logical change per commit
- Build before testing - Always
npm run buildbefore running - Check CI - Tests must pass before merge
- Reference issues/PRs in commit messages
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 · 61 lines · 619 tokens per session scan A c04a5860656d
mcp-devkit-server copilot-instructions.md is an instructions file published in the GitHub repository mapbox/mcp-devkit-server (60 stars, last pushed 6d ago), licensed MIT. It adds 619 tokens to every session, about $0.0031 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.