mapbox-agent-skills: Instructions file for Codex

AGENTS.md

mapbox-agent-skills AGENTS.md is an instructions file for Codex, OpenCode from mapbox/mapbox-agent-skills. It costs 823 tokens per session, scanned A, original, MIT.

A set of instructions for building Mapbox map applications, including moving from other map tools and improving map performance. Mapbox is a platform for adding interactive maps to websites and apps.

In plain words
What is it for?
Use it when moving from Google Maps to Mapbox, switching between Mapbox GL JS and MapLibre GL JS, or improving markers, data loading, startup time, and memory use in a map application.
Why use it?
It gives a coding agent practical guidance for common Mapbox decisions and migration work, so you do not have to research API differences and performance patterns from scratch.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is mapbox/mapbox-agent-skills's own configuration. It tells Codex and OpenCode how to work on mapbox-agent-skills 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 mapbox-agent-skills configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mapbox/mapbox-agent-skills. 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/mapbox/mapbox-agent-skills/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/mapbox/mapbox-agent-skills

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 mapbox-agent-skills AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mapbox/mapbox-agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/mapbox/mapbox-agent-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 823 This file is loaded in full into every session.
When invoked 823 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 $0.00823 $0.00823
Opus 5.5 $0.00329 $0.00329
Sonnet 5.5 $0.00165 $0.00165
Haiku 4.5 $0.00082 $0.00082

Measured 2mo ago against content hash 8b450ad8dc41, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mapbox-agent-skills 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 · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mapbox Development Knowledge Base

This repo contains specialized Agent Skills for Mapbox development. Skills provide domain expertise that helps you make informed decisions when building map applications.

Available Skills

Migration & Platform Comparison

  • mapbox-google-maps-migration: Migrate from Google Maps Platform to Mapbox GL JS. Covers API equivalents (coordinate order, markers, popups, geocoding), performance advantages (WebGL vs DOM), and migration patterns. Use when transitioning existing Google Maps apps or comparing platforms.
  • mapbox-maplibre-migration: Migrate between Mapbox GL JS ↔ MapLibre GL JS. ~95% API compatible. Covers package/import changes, token handling, style URLs (mapbox:// vs custom), license differences. Use for open-source migrations or understanding compatibility.

Performance & Optimization

  • mapbox-web-performance-patterns: Optimize Mapbox GL JS apps. Covers initialization waterfalls, bundle size, marker performance (HTML vs Canvas vs Symbol layers), clustering, data loading (GeoJSON vs vector tiles), memory management. Critical patterns prioritized by UX impact.
  • mapbox-web-integration-patterns: Framework integration (React, Vue, Svelte, Angular, Next.js). Covers proper initialization/cleanup, state management, SSR handling, component patterns. Use when integrating Mapbox into modern web frameworks.

Design & Styling

  • mapbox-cartography: Map design principles. Covers color theory, visual hierarchy, typography, accessibility, data visualization best practices. Use for creating visually effective, accessible maps.
  • mapbox-style-patterns: Common style patterns and layer configurations. Covers data-driven styling, expressions, filters, layer types. Use when building custom map styles or configuring layers.
  • mapbox-style-quality: Style validation, accessibility checks, performance optimization, testing patterns. Use when ensuring style quality and performance.

Security

  • mapbox-token-security: Access token best practices. Covers public vs secret tokens, URL restrictions, token rotation, scoping, rate limiting. Use when implementing secure token management.

Read the full file on GitHub · 59 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 · 59 lines · 823 tokens per session scan A 8b450ad8dc41

Subscribe to this mod's changes

mapbox-agent-skills AGENTS.md is an instructions file published in the GitHub repository mapbox/mapbox-agent-skills (84 stars, last pushed 3d ago), licensed MIT. It adds 823 tokens to every session, about $0.0033 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 2026-08-30.

Related

mapbox-agent-skills AGENTS.md compared with instructions from other repositories

mapbox-agent-skills AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mapbox-agent-skills AGENTS.mdmapbox/mapbox-agent-skillsInstructions file843d agoMITA823Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode