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-search-integrationnpx skills add mapbox/mapbox-agent-skills --skill mapbox-search-integrationgit 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-search-integration)<a href="https://agentmods.dev/skills/mapbox/mapbox-agent-skills/mapbox-search-integration"><img src="https://agentmods.dev/badge/skills/mapbox/mapbox-agent-skills/mapbox-search-integration.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 | $0.00026 | $0.02708 |
| Opus 5 | $0.00013 | $0.01354 |
| Sonnet 5 | $0.00005 | $0.00542 |
| Haiku 4.5 | $0.00003 | $0.00271 |
Grade A, and why
mapbox-search-integration 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 4d 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 — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mapbox Search Integration Skill
Expert guidance for implementing Mapbox search functionality in applications. Covers the complete workflow from asking the right discovery questions, selecting the appropriate search product, to implementing production-ready integrations following best practices from the Mapbox search team.
Use This Skill When
User says things like:
- "I need to add search to my map"
- "I need a search bar for my mapping app"
- "How do I implement location search?"
- "I want users to search for places/addresses"
- "I need geocoding in my application"
This skill complements mapbox-search-patterns:
mapbox-search-patterns= Tool and parameter selectionmapbox-search-integration= Complete implementation workflow
Discovery Phase: Ask the Right Questions
Before jumping into code, ask these questions to understand requirements:
Question 1: What are users searching for?
Ask: "What do you want users to search for?"
Common answers and implications:
- "Addresses" → Use Search Box API (the default for interactive address search, including geocoding). Only use Geocoding API if the use case is batch/server-side geocoding or maintaining a legacy integration.
- "Points of interest / businesses" → POI search, use Search Box API with category search
- "Both addresses and POIs" → Search Box API
- "Specific types of POIs" (restaurants, hotels, etc.) → Search Box API
- "Countries, cities, postcodes or neighborhoods" → Search Box API for interactive search; Geocoding API only for batch/server-side geocoding
- "Custom locations" (user-created places) → May need custom data + search integration
Follow-up if not stated initially: "Are your users searching for points of interest data? Restaurants, stores, categories of businesses?"
Implications:
- "Yes, POIs are included" → Use the Search Box API
- "No, the user does not need POI search" → Still default to Search Box API for interactive/autocomplete use cases. Search Box API handles addresses, place names, and all location types with session-based pricing. Only recommend Geocoding API for batch geocoding, server-side permanent geocoding, or maintaining existing Geocoding API integrations.
What ships with it
10 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.
- evals/evals.json 2.3 KB
- references/android-search.md 4.2 KB
- references/best-practices.md 6.7 KB
- references/framework-hooks.md 4.0 KB
- references/ios-search.md 3.9 KB
- references/nodejs-search.md 2.1 KB
- references/pitfalls.md 3.4 KB
- references/react-search.md 4.6 KB
- references/testing-monitoring.md 2.6 KB
- references/web-search-js.md 11 KB
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.
- 4d ago First seen · 265 lines · 26 tokens per session scan A acf1decea3f6
mapbox-search-integration is a skill published in the GitHub repository mapbox/mapbox-agent-skills (74 stars, last pushed 9d ago), licensed MIT. It adds 26 tokens to every session and 2,708 once invoked, about $0.0001 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…