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 mengrru/Spherse --skill magic-phonegit clone --depth 1 https://github.com/mengrru/SpherseWrote 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/mengrru/spherse/magic-phone)<a href="https://agentmods.dev/skills/mengrru/spherse/magic-phone"><img src="https://agentmods.dev/badge/skills/mengrru/spherse/magic-phone/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/mengrru/spherse/magic-phone"><img src="https://agentmods.dev/badge/skills/mengrru/spherse/magic-phone.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 | $0.00057 | $0.02541 |
| Opus 5 | $0.00028 | $0.01270 |
| Sonnet 5 | $0.00011 | $0.00508 |
| Haiku 4.5 | $0.00006 | $0.00254 |
Grade A, and why
magic-phone 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.
How it starts
The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🪄 魔法手机 · 捡手机文学技能
核心理念
数据与 UI 完全分离。 模板 HTML 是稳定的渲染引擎（永不修改），每次创作新角色只需编写 JSON 数据文件。这让「捡手机文学」的创作变成纯粹的数据撰写工作，无需接触任何前端技术。
📁 项目文件体系
项目根目录/
├── 🪄 魔法手机-通用模板.html ← 稳定的 UI 渲染引擎（请勿修改）
├── 🪄 魔法手机-技能指南.md ← 面向人类创作者的技能说明
│
├── 赫敏-魔法手机.data.json ← 角色数据示例
├── 📱 赫敏·格兰杰的手机.html ← 入口页，指向数据文件
│
├── {角色名}-魔法手机.data.json ← 新增角色的数据
├── 📱 {角色名}的魔法手机.html ← 新增角色的入口页
└── ...
各文件角色
| 文件 | 角色 | 修改策略 |
|---|---|---|
🪄 魔法手机-通用模板.html |
CSS + HTML + JS 渲染引擎 | 永不修改 |
{角色名}-魔法手机.data.json |
角色数据（聊天/动态/笔记） | 每次创作新角色时编写 |
📱 {角色名}的魔法手机.html |
模板副本，改一行 DATA_SOURCE |
复制模板 + 改路径 |
📐 数据文件格式规范
顶层结构
{
"title": "📱 哈利·波特的魔法手机",
"owner": { },
"tabs": { },
"contacts": { },
"chatList": [ ],
"chats": { },
"moments": [ ],
"notes": [ ]
}
owner — 机主信息
{
"owner": {
"name": "哈利·波特",
"avatarEmoji": "⚡",
"avatarGradient": "linear-gradient(135deg, #2D5A3A, #4A7C59)",
"status": "魔杖就绪 · 正在想",
"statusHighlight": "今晚要不要去厨房偷点吃的"
}
}
| 字段 | 必填 | 说明 |
|---|---|---|
name |
✅ | 机主全名 |
avatarEmoji |
✅ | 头像显示的 emoji 符号 |
avatarGradient |
✅ | 头像 CSS 渐变背景 |
status |
✅ | 状态文字（普通部分） |
statusHighlight |
❌ | 状态文字中斜体高亮部分 |
tabs — 标签页名称
{
"tabs": {
"chat": "🪄 猫头鹰通信",
"moments": "🌙 月相动态",
"notes": "📜 羊皮笔记"
}
}
三个 key 固定为 chat、moments、notes，value 可自由定制，建议保留魔法风格 emoji。
contacts — 联系人字典
{
"contacts": {
"ron": { "name": "罗恩·韦斯莱", "emoji": "♟", "cls": "ron", "color": "#C0392B" },
"hermione": { "name": "赫敏·格兰杰", "emoji": "📚", "cls": "hermione", "color": "#B8860B" }
}
}
- 键名（id）：唯一标识，需与
chatList和chats中的id对应 cls：CSS 类名，决定头像渐变配色。支持以下预设值：
cls 值 |
渐变配色 | 适用角色 |
|---|---|---|
harry |
深绿→绿 | 哈利·波特 |
ron |
深红→红 | 罗恩·韦斯莱 |
ginny |
深棕→棕 | 金妮·韦斯莱 |
hermione |
金→深金 | 赫敏·格兰杰 |
malfoy |
深蓝灰→灰蓝 | 德拉科·马尔福 |
luna |
深紫→紫 | 卢娜·洛夫古德 |
albus / dumbledore |
深蓝→蓝 | 邓布利多 |
snape |
黑→深灰 | 西弗勒斯·斯内普 |
mcgonagall |
深灰蓝→蓝灰 | 米勒娃·麦格 |
sirius |
深灰→灰 | 小天狼星·布莱克 |
remus |
深褐→褐 | 莱姆斯·卢平 |
tom |
黑→暗红 | 汤姆·里德尔 / 伏地魔 |
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 · 272 lines · 57 tokens per session scan A 6e4a65f20543
magic-phone is a skill published in the GitHub repository mengrru/Spherse (71 stars, last pushed 4d ago), licensed MIT. It adds 57 tokens to every session and 2,541 once invoked, about $0.0003 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
novel-technique-character-card-workshop
A workshop for turning rough character ideas into detailed, usable character profiles. It supports structured question cycles, personality layers, visual themes, and checks against reducing a character to a few labels.
novel-idea-exploration
A guided brainstorming aid for developing a novel’s subject, inspiration, rough plot, or unclear world-building ideas.
novel-writing
A controller for a structured novel-writing cycle, from planning the plot to saving agreed story facts, drafting chapters, reviewing them, and revising them.
novel-workflow-05-emulation-bootstrap
A setup guide for legacy simulation or role-playing projects. It provides the starting context for those older workflows, rather than for ordinary writing.
web-ui-motion
Build polished front-end UI together with a signature motion effect in a single self-contained HTML file, combining SVG.js / SVG filters and the Canvas 2D API. Use when the user asks to build a web page, landing page, dashboard, or component that has a special visual effect, animation, particle system, fluid/water…
threejs-postprocessing
Three.js post-processing - EffectComposer, bloom, DOF, screen effects. Use when adding visual effects, color grading, blur, glow, or creating custom screen-space shaders.