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 skills/mapbox/mapbox-agent-skills/mapbox-token-securitynpx skills add mapbox/mapbox-agent-skills --skill mapbox-token-securitygit clone --depth 1 https://github.com/mapbox/mapbox-agent-skillsWhat 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 | $0.00043 | $0.02012 |
| Opus 5 | $0.00022 | $0.01006 |
| Sonnet 5 | $0.00009 | $0.00402 |
| Haiku 4.5 | $0.00004 | $0.00201 |
Grade A, and why
mapbox-token-security 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 — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mapbox Token Security Skill
This skill provides security expertise for managing Mapbox access tokens safely and effectively.
Token Types and When to Use Them
Public Tokens (pk.*)
Characteristics:
- Can be safely exposed in client-side code
- Limited to specific public scopes only
- Can have URL restrictions
- Cannot access sensitive APIs
When to use:
- Client-side web applications
- Mobile apps
- Public-facing demos
- Embedded maps on websites
Allowed scopes:
styles:tiles- Display style tiles (raster)styles:read- Read style specificationsfonts:read- Access Mapbox fontsdatasets:read- Read dataset datavision:read- Vision API access
Secret Tokens (sk.*)
Characteristics:
- NEVER expose in client-side code
- Full API access with any scopes
- Server-side use only
- Can create/manage other tokens
When to use:
- Server-side applications
- Backend services
- CI/CD pipelines
- Administrative tasks
- Token management
Common scopes:
styles:write- Create/modify stylesstyles:list- List all stylestokens:read- View token informationtokens:write- Create/modify tokens- User feedback management scopes
Temporary Tokens (tk.*)
Characteristics:
- Short-lived (max 1 hour)
- Created by secret tokens
- Single-purpose use
- Automatically expire
When to use:
- One-time operations
- Temporary delegated access
- Short-lived demos
- Security-conscious workflows
Scope Management Best Practices
Principle of Least Privilege
Always grant the minimum scopes needed:
❌ Bad:
// Overly permissive - don't do this
{
scopes: ['styles:read', 'styles:write', 'styles:list', 'styles:delete', 'tokens:read', 'tokens:write'];
}
✅ Good:
// Only what's needed for displaying a map
{
scopes: ['styles:read', 'fonts:read'];
}
// Add 'styles:tiles' if your map uses raster tile sources
{
scopes: ['styles:read', 'fonts:read', 'styles:tiles'];
}
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 326 lines · 43 tokens per session scan A 2d7f46a90f8f
mapbox-token-security is a skill published in the GitHub repository mapbox/mapbox-agent-skills (74 stars, last pushed 7d ago), licensed MIT. It adds 43 tokens to every session and 2,012 once invoked, about $0.0002 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…