PhoneClaw is a local AI agent framework that runs on phones and edge devices, using on-device models to understand requests and perform mobile tasks through native skills. It is for people who want an AI assistant on an iPhone or similar device with access to functions such as calendars, reminders, contacts, health data, voice, and image understanding, while optionally using web search or a Mac Gateway for selected tasks.
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 kellyvv/PhoneClaw --skill healthgit clone --depth 1 https://github.com/kellyvv/PhoneClawWrote 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/kellyvv/phoneclaw/health)<a href="https://agentmods.dev/skills/kellyvv/phoneclaw/health"><img src="https://agentmods.dev/badge/skills/kellyvv/phoneclaw/health/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/kellyvv/phoneclaw/health"><img src="https://agentmods.dev/badge/skills/kellyvv/phoneclaw/health.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00039 | $0.01637 |
| Opus 5 | $0.00019 | $0.00818 |
| Sonnet 5 | $0.00008 | $0.00327 |
| Haiku 4.5 | $0.00004 | $0.00164 |
Grade A, and why
Health 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 11d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
健康数据查询
你负责读取用户的健康数据并给出简短解读。数据全部在本地处理, 不上传。
工具选择
| 用户意图 | 工具 |
|---|---|
| 今天运动量 / 今天活动量 / 今天运动情况 / 今天锻炼情况 | health-activity-summary |
| 分析健康数据 / 健康报告 / 健康周报 / 整体健康情况 / 最近N天健康数据 | health-report (days 按用户时间推断；一周=7，两周=14，一个月=30) |
| 今天/昨天/最近N天步数 / 走了多少步 | health-query (metric=steps, range=today/yesterday/last_n_days, days 按用户意图传入) |
| 今天走了多远 / 走了多少公里 / 步行距离 / 路程 | health-query (metric=distance, range=today) |
| 今天消耗了多少卡路里 / 热量 / 千卡 | health-query (metric=active_energy, range=today) |
| 静息心率 | health-query (metric=resting_heart_rate, range=recent) |
| 最近心率 / 心跳 / 当前心率 | health-query (metric=heart_rate, range=recent) |
| 心率变异性 / HRV | health-query (metric=hrv, range=recent) |
| 体重 / 最近体重 | health-query (metric=weight, range=latest) |
| 昨晚睡了多久 / 睡眠质量 | health-query (metric=sleep, range=last_night) |
| 最近一周睡眠 | health-query (metric=sleep, range=week) |
| 最近运动 / 健身记录 | health-query (metric=workout, range=recent) |
注意: "运动量" / "活动量" / "运动情况" 默认用 health-activity-summary, 不要只查步数。只有用户明确问"走了多少步"才用 health-query(metric=steps)。 注意: "走了多远" / "距离" / "公里" / "米" / "路程" 是距离查询, 必须用 health-query(metric=distance), 不要用 steps。 注意: "健康数据" / "健康报告" / "分析健康" 是综合分析, 必须用 health-report, 不要只查睡眠或步数。只有用户明确说"睡眠"时才用 health-query(metric=sleep)。 注意: 用户在上一轮单项查询后只修正时间范围/天数 (例如"不是 5 天, 是 7 天"), 必须沿用上一轮同一个 metric, 只改 range/days。上一轮是步数就继续用 health-query(metric=steps, range=last_n_days, days=7), 不要升级成 health-report。 首次健康授权会一次请求步数、步行+跑步距离、活动能量、静息心率、睡眠、体能训练、体重、心率、心率变异性读取权限。
时间范围推断
- "一周" / "本周" / "最近一周" / "7 天" → days=7
- "两周" / "最近两周" / "14 天" → days=14
- "一个月" / "最近一个月" / "30 天" → days=30
- "这几天" 未给具体天数 → days=7
days限制在 1 到 90；不要自己把日期展开成列表, 只传天数
执行流程
- 根据用户意图选择正确的工具, 立即调用, 不要追问
- 拿到工具结果后, 直接使用返回结果里的自然语言摘要, 不要自己套模板或输出占位符
- 综合健康报告 (health-report) 会一次读取该时间范围内所有支持的健康项, 直接使用返回报告
- 单项查询 (health-query) 和今天运动概况 (health-activity-summary) 都直接使用返回摘要
- 不要自己编造健康数据, 必须用 tool 返回的真实数字
- 不要在没调用 tool 之前说"我没有权限"或"我不知道" — 先调工具再说
完成后回复
- 所有健康数据都用简短自然中文说明, 不要提工具名、JSON 或内部步骤
- 睡眠、心率、距离、卡路里、运动记录都只说核心数字和一句轻量解读
- 没有数据时, 直接说明没有可用记录, 不要猜测
What ships with it
2 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.
- 11d ago First seen · 133 lines · 39 tokens per session scan A 7d5cedb22348
Health is a skill published in the GitHub repository kellyvv/PhoneClaw (1,239 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 39 tokens to every session and 1,637 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
perfetto-sql
Translates natural language data intents into syntactically valid Perfetto SQL queries and executes them against a local trace file. Use this skill to extract slice, thread, or memory data from Android Perfetto traces using traceprocessor. Standalone quick path; for end-to-end profiling (recording + heap dumps +…
healthkit
Read, write, and query Apple Health data using HealthKit. Covers HKHealthStore authorization, sample queries, statistics queries, statistics collection queries for charts, saving HKQuantitySample data, background delivery, workout sessions with HKWorkoutSession and HKLiveWorkoutBuilder, HKUnit, and…
sensorkit
Access research-grade sensor data using SensorKit. Use when reading ambient light levels, accelerometer data, rotation rates, device usage patterns, keyboard metrics, or media events for approved research studies. Requires SensorKit entitlement and research study authorization.
sensorkit
Access ambient, motion, biometric, and interaction research data using SensorKit. Use when configuring sensor readers, handling authorization and study onboarding, fetching sample streams, managing user data deletion, or building research and clinical studies.
implementing-llms-litgpt
Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…