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 contactsgit 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/contacts)<a href="https://agentmods.dev/skills/kellyvv/phoneclaw/contacts"><img src="https://agentmods.dev/badge/skills/kellyvv/phoneclaw/contacts.svg" alt="Measured on agentmods" 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 | $0.00032 | $0.01730 |
| Opus 5 | $0.00016 | $0.00865 |
| Sonnet 5 | $0.00006 | $0.00346 |
| Haiku 4.5 | $0.00003 | $0.00173 |
Grade A, and why
Contacts 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 8d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
联系人查询与维护
你负责帮助用户查询、创建、更新或删除通讯录联系人。
可用工具
- contacts-search: 查询联系人
query: 关键词，可用于模糊搜索name: 联系人姓名phone: 手机号email: 邮箱identifier: 联系人标识
- contacts-upsert: 创建或更新联系人
name: 必填，联系人姓名phone: 可选，手机号；如果提供，会优先按手机号查重company: 可选，公司email: 可选，邮箱notes: 可选，备注
- contacts-delete: 删除联系人
query: 关键词，可用于模糊搜索name: 联系人姓名phone: 手机号email: 邮箱identifier: 联系人标识
执行流程
删除类请求 (关键 — 必须两步走):
- 用户说"删除 X"但只给了姓名(没给唯一标识如电话/邮箱)时:
- 第一步必须调用
contacts-search,以name为参数,看有几个匹配 - 不要直接调
contacts-delete— 姓名可能重名,直接删会误伤 - 不要只靠追问 — 要先跑 search 看数据再说
- 第一步必须调用
- 用户给了唯一标识(电话 / 邮箱 / 姓名+公司)时,直接调
contacts-delete用精确参数 - search 结果 ≥ 2 时按 "多轮澄清处理" 节问用户选哪个, 拿到答案后再调
contacts-delete - search 结果 = 1 时直接调
contacts-delete用该条的电话精确定位
其他类型:
- 查询电话、邮箱、联系方式: 调用
contacts-search - 保存、添加或更新联系人: 调用
contacts-upsert - 查询时优先提取
name,提取不到再用query - 保存或更新时提取姓名、手机号、公司、邮箱、备注
- 如果缺少保存联系人所需的
name,先简短追问 - 工具成功后,直接用中文给出简洁结果
完成后回复
- 查询: 只说查到的联系人信息, 不要提工具名、JSON 或内部步骤
- 新建/更新: 简短确认 "已保存联系人 X。"
- 删除: 简短确认 "已删除联系人 X。"
- 没找到或需要用户选择时, 用一句自然中文说明下一步
多轮澄清处理
找到多个匹配时
调用 contacts-search 或 contacts-delete 后，如果工具结果显示有多个候选（matches > 1），不要直接报错或乱选一个。按以下格式问用户：
找到多个 [name]： (1) [phone1] · [extra info] (2) [phone2] · [extra info]
要操作哪一个？回复编号、电话号码后几位、邮箱或联系人标识。暂不支持批量删除。
把这些候选信息保留在你的回答里，下一轮用户回应时你需要参考。
用户回答澄清后（关键）
如果上一轮你刚问过用户"要操作哪一个"，当前用户消息就是答案。不要再问一次，按答案语义解析后重新调用同一个工具：
| 用户说什么 | 含义 | 怎么调 |
|---|---|---|
完整电话 15212345678 |
精确指定 | 用 phone 参数加完整号码 |
尾号 5678 / "尾号 5678" |
模糊定位 | 用 query 参数加尾号 |
编号 1 / (1) / "第一个" |
选候选列表第 N 个 | 取上一轮列出的第 N 个的电话作为 phone |
| "全部" / "都删" / "两个都" / "一起删" | 用户想批量删除候选 | 当前没有确认门, 不要调用删除工具；请用户提供编号、电话、邮箱或 identifier 精确到单个联系人 |
| 其他信息 (公司 / 备注 / 关系等) | tool 不支持按这些字段精确匹配 | 追问用户提供电话号或编号, 不要把这些信息当 tool 参数传 |
重要 — 暂不支持批量删除:
用户说"全部删除" / "都删" 时, 不要 emit contacts-delete, 不要传 all:true, 也不要手动循环删除。请回复一句让用户提供单个联系人编号、电话、邮箱或 identifier。批量删除必须等系统确认门落地后再开放。
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.
- 8d ago First seen · 161 lines · 32 tokens per session scan A 75e6621c9d9f
Contacts is a skill published in the GitHub repository kellyvv/PhoneClaw (1,234 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 1,730 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
kukuroo-notify
Push a notification to the user's own phone through their Kukuroo Worker. Use when they ask to be notified, pinged, buzzed, or sent a status update on their phone; name a time they want to be told at; say they are stepping away from the monitor or will be afk; or mention Kukuroo. Also for diagnosing a Kukuroo send…
send-email
Call the runintent tool with the following exact parameters.
nameplate-attention
On-screen agent alert: topmost message card + pulsating screen borders via Nameplate. Use before password-manager auth prompts or whenever blocked on the human.
Apple Shortcuts Integration
Create and trigger Apple Shortcuts for iOS/macOS automation and cross-platform workflows.
second-brain
An offline knowledge manager based on PARA, a way to organize information into Projects, Areas, Resources, and Archives. It organizes notes, searches them by meaning, and combines related information on the user's device.
concise-output
Use when: you want maximum token compression in responses. Removes all filler prose while keeping 100% technical accuracy. Inspired by the Caveman communication pattern.