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 amap-demo/amap-sdk-skills --skill ios-llm-agent-sdkgit clone --depth 1 https://github.com/amap-demo/amap-sdk-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/amap-demo/amap-sdk-skills/ios-llm-agent-sdk)<a href="https://agentmods.dev/skills/amap-demo/amap-sdk-skills/ios-llm-agent-sdk"><img src="https://agentmods.dev/badge/skills/amap-demo/amap-sdk-skills/ios-llm-agent-sdk/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/amap-demo/amap-sdk-skills/ios-llm-agent-sdk"><img src="https://agentmods.dev/badge/skills/amap-demo/amap-sdk-skills/ios-llm-agent-sdk.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 | $0.00000 | $0.00857 |
| Opus 5.5 | $0.00000 | $0.00343 |
| Sonnet 5.5 | $0.00000 | $0.00171 |
| Haiku 4.5 | $0.00000 | $0.00086 |
Grade A, and why
ios-llm-agent-sdk 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.
What it actually says
MALLMKit SDK Skill
高德地图 MALLMKit SDK 集成技能，支持自然语言查询、路线规划、POI搜索、导航控制等智能地图服务，以及与高德地图 APP 的 IPC 通信（授权认证、建联、收发数据）。
适用场景
- 集成高德智能语音助手到 iOS 应用
- 实现自然语言驱动的地图交互（如"去西藏"、"附近的肯德基"）
- 导航控制与数据监听
- 合作方 APP 与高德地图 APP 建立 IPC 通信链路，收发数据
触发词
| 触发词 | 文档 | 说明 |
|---|---|---|
| 接入LLM Agent SDK | 接入 Agent | Agent 初始化、命令注册、查询调用完整流程 |
| 链接高德app | 链接高德 APP | Link 页面创建、授权认证、建联、导航命令收发完整流程 |
💡 别名：说"接入agent"或"接入agent sdk"也会匹配到"接入LLM Agent SDK"触发词。 💡 别名：说"连接高德app"、"接入linkKit"、"IPC通信"、"与高德APP通信"也会匹配到"链接高德app"触发词。
快速开始
- Agent SDK 首次接入请阅读：快速集成指南
- Link SDK 首次接入请阅读：Link 快速集成指南
API 文档 — Agent SDK（按需查阅）
| 文档 | 说明 |
|---|---|
| 智能查询 | 发起自然语言查询、多轮对话 |
| 查询结果处理 | 处理路线、POI、导航等查询结果 |
| 导航控制 | 开始/停止导航、切换路线、播报模式 |
| 导航数据监听 | 实时监听导航数据回调 |
| 出行方式配置 | 导航环境、路线偏好、家/公司位置 |
| IPC链路管理 | APP链路模式的建联与授权 |
| 生命周期管理 | 场景管理、状态重置、内存管理 |
| 日志管理 | SDK 内部日志监听 |
API 文档 — Link SDK（按需查阅）
| 文档 | 说明 |
|---|---|
| 认证管理 | 通过 AMapAuthorizationManager 完成授权流程与回调处理 |
| 连接管理 | 通过 AMapLinkManager 建立连接、状态监听、自动重连、断开连接 |
| 数据传输与命令 | 发送数据、导航命令（途经点/目的地/播报/开始导航）、数据监听 |
参考文档（深入查阅）
| 文档 | 说明 |
|---|---|
| Agent 核心类参考 | Agent SDK 公共类与枚举速查 |
| 常见问题排查 | 错误码与常见问题解决 |
| 语音指令参考 | 支持的自然语言指令示例 |
| Link 核心类参考 | Link SDK 公共类速查 |
| Link 错误码参考 | Link SDK 错误码速查 |
What ships with it
21 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.
- api/agent-query.md 1.7 KB
- api/authorization.md 2.8 KB
- api/connection.md 1.8 KB
- api/data-transfer.md 4.1 KB
- api/integrate-agent.md 21 KB
- api/lifecycle.md 1.4 KB
- api/link-client.md 2.6 KB
- api/link-quick-start.md 28 KB
- api/logger.md 833 B
- api/navi-control.md 2.0 KB
- api/navi-data-listener.md 2.7 KB
- api/query-result.md 2.8 KB
- api/quick-start.md 2.1 KB
- api/transport-mode.md 1.8 KB
- README_zh.md 6.2 KB
- README.md 7.0 KB
- references/core-classes.md 7.5 KB
- references/link-core-classes.md 1.8 KB
- references/link-error-codes.md 1.9 KB
- references/troubleshooting.md 2.5 KB
- references/voice-commands.md 890 B
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.
- 2mo ago First seen · 57 lines · 0 tokens per session scan A 293927a2c230
ios-llm-agent-sdk is a skill published in the GitHub repository amap-demo/amap-sdk-skills (56 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 857 tokens. 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.
ios-llm-agent-sdk compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ios-llm-agent-sdkamap-demo/amap-sdk-skills | Skill | 56 | 6mo ago | MIT | A | 0 | Claude Code, Codex |
| orca-emulator-androidstablyai/orca | Skill | 117k | yesterday | MIT | A | 102 | Claude Code, Codex |
| glance-canonical-layoutsandroid/skills | Skill | 10k | yesterday | Apache-2.0 | A | 56 | Claude Code |
| android-tombstone-symbolicationdotnet/skills | Skill | 5.8k | yesterday | MIT | A | 176 | Claude Code |
| dogfoodcallstack/agent-device | Skill | 5.3k | yesterday | MIT | A | 55 | Claude Code |
| winapp-mauimicrosoft/winappCli | Skill | 1.4k | yesterday | MIT | A | 68 | Claude Code |
| app_remixrome-os/rome | Skill | 889 | today | MIT | A | 50 | Claude Code, Codex |