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 translategit 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/translate)<a href="https://agentmods.dev/skills/kellyvv/phoneclaw/translate"><img src="https://agentmods.dev/badge/skills/kellyvv/phoneclaw/translate/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/translate"><img src="https://agentmods.dev/badge/skills/kellyvv/phoneclaw/translate.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 | $0.00016 | $0.00714 |
| Opus 5 | $0.00008 | $0.00357 |
| Sonnet 5 | $0.00003 | $0.00143 |
| Haiku 4.5 | $0.00002 | $0.00071 |
Grade A, and why
Translate 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 10d 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
专业翻译
直接输出译文, 不加前缀、不解释过程、不列备选。
识别源文本
- 用户消息里有引号或冒号后的内容 → 取该段
- 用户用了"这段 / 刚才那段 / 上面 / 前面"等指代词 → 取对话历史中最近一条 assistant 消息的正文 (跳过 ⚠️ 警告行和"好的"之类单句确认)
- 以上都没有 → 才允许追问 "请提供需要翻译的文本"
识别目标语言
- 用户明示 (如 "译成英文") → 按用户要求
- 用户问 "是什么意思" → 默认译成中文
- 源文本是中文且未指定 → 默认译成英文
翻译准则
信达雅: 忠实原意 + 符合目标语言语法习惯 + 匹配原文语域 (正式/口语/文学/技术)。
具体:
- 完整性优先: 引号内、冒号后、代码块内或用户明确给出的源文本必须整体翻译, 不要漏掉开头/结尾/问候/语气词/并列分句, 不要只翻最后一个分句
- 成语用等效表达, 不字面直译 ("画蛇添足" → "gild the lily")
- 中译英要补全省略的主语, 英译中按中文习惯省略
- 日韩 → 中/英 调整 SOV→SVO 语序
- 标点用目标语言体系 (中文全角, 英文半角)
- 专有名词 (人名/地名/品牌) 保留或用公认译法
输出
只输出译文文本本身。源文本歧义且需要上下文澄清时, 先给最可能译文, 下一段简短补一句"另一种可能是 ..."。
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.
- 10d ago First seen · 72 lines · 16 tokens per session scan A c17a69908480
Translate is a skill published in the GitHub repository kellyvv/PhoneClaw (1,237 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 714 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
ios-marketing-capture
Use when the user wants to automate capture of marketing screenshots for a SwiftUI iOS app across multiple locales, devices, or appearances. Covers full-screen shots, isolated element renders (carousel cards, widgets), and reproducible output naming. Triggers on marketing screenshots, locale screenshots, widget…
maui-localization-theming
Implement MAUI localization and theming. USE FOR: RESX/AppResources, runtime culture switching, RTL/FlowDirection, platform language metadata, AppThemeBinding, DynamicResource, light/dark/system themes, UserAppTheme. DO NOT USE FOR: general layout, accessibility audits, icon/splash assets.
appstore-ppp-pricing
Bulk-sets App Store in-app purchase and subscription prices across 175+ countries by purchasing power parity, using the appstore-ppp-prices CLI. Use whenever the user wants to localize, bulk-update, lower, raise or review regional App Store pricing — "set regional prices", "PPP pricing", "make my app cheaper in…
swift-formatstyle
Locale-aware value formatting and parsing on iOS/macOS with Foundation's FormatStyle / ParseableFormatStyle protocols — the modern replacement for NumberFormatter / DateFormatter / DateComponentsFormatter subclasses. Covers number styles (IntegerFormatStyle / FloatingPointFormatStyle via .number with .precision /…
natural-language
On-device text intelligence for an iOS fintech app with Apple's NaturalLanguage + Translation frameworks — language ID (NLLanguageRecognizer, languageHints/constraints), tokenization (NLTokenizer word/sentence), linguistic tagging (NLTagger with .lexicalClass/.nameType/.lemma, enumerateTags, tagHypotheses…
localization-patterns
Localization patterns for mobile - string resources, plurals, RTL support, Compose localization, KMP shared strings, and locale management.