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-style-qualitynpx skills add mapbox/mapbox-agent-skills --skill mapbox-style-qualitygit clone --depth 1 https://github.com/mapbox/mapbox-agent-skillsWrote 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.
[](https://agentmods.dev/skills/mapbox/mapbox-agent-skills/mapbox-style-quality)<a href="https://agentmods.dev/skills/mapbox/mapbox-agent-skills/mapbox-style-quality"><img src="https://agentmods.dev/badge/skills/mapbox/mapbox-agent-skills/mapbox-style-quality.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00044 | $0.01763 |
| Opus 5 | $0.00022 | $0.00881 |
| Sonnet 5 | $0.00009 | $0.00353 |
| Haiku 4.5 | $0.00004 | $0.00176 |
Grade A, and why
mapbox-style-quality 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 5d 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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mapbox Style Quality Skill
This skill provides expert guidance on ensuring Mapbox style quality through validation, accessibility, and optimization tools.
When to Use Quality Tools
Pre-Production Checklist
Before deploying any Mapbox style to production:
- Validate all expressions - Catch syntax errors before runtime
- Check color contrast - Ensure text is readable (WCAG compliance)
- Validate GeoJSON sources - Ensure data integrity
- Optimize style - Reduce file size and improve performance
- Compare versions - Understand what changed
- Remove empty layers - Delete layers with no visible paint properties as a final cleanup step
- Simplify redundant boolean expressions - Clean up filters with unnecessary boolean logic (e.g.,
["all", expr]→expr,["any", false, expr]→expr)
During Development
When adding GeoJSON data:
- Always validate external GeoJSON with
validate_geojson_toolbefore using as a source
When writing expressions:
- Validate expressions with
validate_expression_toolas you write them - Catch type mismatches early (e.g., using string operator on number)
- Verify operator availability in your Mapbox GL JS version
- Test expressions with expected data types
When styling text/labels:
- Check foreground/background contrast with
check_color_contrast_tool - Aim for WCAG AA minimum (4.5:1 for normal text, 3:1 for large text)
- Use AAA standard (7:1 for normal text) for better accessibility
- Consider different background scenarios (map tiles, overlays)
Before Committing Changes
Compare style versions:
- Use
compare_styles_toolto generate a diff report - Review all layer changes, source modifications, and expression updates
- Understand the impact of your changes
- Document significant changes in commit messages
Before Deployment
Optimize the style:
- Run
optimize_style_toolto reduce file size - Remove unused sources that reference deleted layers
- Eliminate duplicate layers with identical properties
- Simplify redundant boolean expressions in filters (e.g., collapse
["all", expr]toexpr, remove tautological conditions) - Remove empty layers (layers with no visible paint properties) as a final cleanup step
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.
- 5d ago First seen · 233 lines · 44 tokens per session scan A d72c58e34e6e
mapbox-style-quality is a skill published in the GitHub repository mapbox/mapbox-agent-skills (74 stars, last pushed 10d ago), licensed MIT. It adds 44 tokens to every session and 1,763 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
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
hallmark
Anti-AI-slop design skill for greenfield pages, audits, redesigns, and design extraction from URLs or screenshots. Use when the user asks to build a new app or landing page, wants to redesign something, invokes Hallmark by name, or uses audit/redesign/study.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
prototype-web
可点击的功能性 Web 原型, 含导航、英雄区、特性区、CTA.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.