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 skills add maplibre/maplibre-agent-skills --skill maplibre-native-gl-js-paritygit clone --depth 1 https://github.com/maplibre/maplibre-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/maplibre/maplibre-agent-skills/maplibre-native-gl-js-parity)<a href="https://agentmods.dev/skills/maplibre/maplibre-agent-skills/maplibre-native-gl-js-parity"><img src="https://agentmods.dev/badge/skills/maplibre/maplibre-agent-skills/maplibre-native-gl-js-parity/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.
<a href="https://agentmods.dev/skills/maplibre/maplibre-agent-skills/maplibre-native-gl-js-parity"><img src="https://agentmods.dev/badge/skills/maplibre/maplibre-agent-skills/maplibre-native-gl-js-parity.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00133 | $0.04774 |
| Opus 5.5 | $0.00053 | $0.01910 |
| Sonnet 5.5 | $0.00027 | $0.00955 |
| Haiku 4.5 | $0.00013 | $0.00477 |
Grade A, and why
maplibre-native-gl-js-parity 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 today.
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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MapLibre Native and GL JS Parity
MapLibre GL JS and MapLibre Native read the same style specification but ship features at different times. A style key Native does not know is ignored, and a paint value it cannot parse drops its layer, both without a crash, so the symptom is a map that quietly differs from the browser. The table below names each gap this skill covers, the release that closed it where one has, and what to do on Native instead. Rows were checked against android-v13.7.1 (2026-10-15) and ios-v7.0.0 (2026-10-28).
When to Use This Skill
These are symptoms as you would observe them, before you know the cause:
- The browser shows a globe, the app stays flat: the style sets
"projection": {"type": "globe"}and nothing changes on Android or iOS however far the map zooms out (no Native release draws a globe). - One layer never draws on Android or iOS, no crash, every other layer fine: a paint value uses an expression the installed release does not implement, such as
interpolate-hclbefore android-v13.7.1 or ios-v7.0.0, so the whole layer is dropped. - Porting
map.setTerrain(...)to Kotlin or Swift: there is nothing to port it to (no Native release has 3D terrain). - A
maplibregl.addProtocolhandler needs an Android or iOS equivalent: there is noaddProtocolon Native; app code answers the request in each platform's HTTP stack instead. - Elevation-banded color on a phone without pre-rendered tiles: a
color-relieflayer, on Native since android-v13.0.0 and ios-v6.24.0. - A
.pmtilesarchive in an iOS or Android app: no tile server, conversion, or package;pmtiles://is built in since android-v11.8.0 and ios-v6.10.0.
Scope. The table's six gaps are the ones where a model answering without this skill gets the API or the release wrong. The renderers differ in other places too. For a feature not in the table, find the release that added it in the Native CHANGELOGs.[5] [6] The js-parity label tracks open gaps,[1] but some open issues there describe shipped features.
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.
- today First seen · 202 lines · 133 tokens per session scan A ff4a8d3ac9eb
maplibre-native-gl-js-parity is a skill published in the GitHub repository maplibre/maplibre-agent-skills (159 stars, last pushed yesterday), licensed MIT. It adds 133 tokens to every session and 4,774 once invoked, about $0.0005 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 2026-11-06.
maplibre-native-gl-js-parity compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| maplibre-native-gl-js-paritymaplibre/maplibre-agent-skills | Skill | 159 | yesterday | MIT | A | 133 | Claude Code, Codex |
| add-signalnanocoai/nanoclaw | Skill | 31k | yesterday | MIT | A | 22 | Claude Code |
| kotlin-specialistJeffallan/claude-skills | Skill | 12k | 7d ago | MIT | A | 86 | Claude Code |
| swift-expertJeffallan/claude-skills | Skill | 12k | 7d ago | MIT | A | 98 | Claude Code |
| offensive-mobileSnailSploit/Claude-Red | Skill | 10k | 25d ago | MIT | A | 185 | Claude Code, Codex |
| app-store-optimizationcbrock84/headcount | Skill | 2.6k | 19d ago | MIT | A | 64 | Claude Code |
| react-nativejezweb/claude-skills | Skill | 1.1k | 28d ago | MIT | A | 91 | Claude Code |