Oh My PPT is a local-first desktop application that uses AI to create, edit, present, and export editable HTML-based slide presentations. It is for people making presentations, lessons, stories, reports, or pitches who want to describe their content and then adjust the resulting pages, visuals, animations, and layouts.
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 agentmods add instructions/arcsin1/oh-my-ppt/agents-mdgit clone --depth 1 https://github.com/arcsin1/oh-my-pptWrote 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/instructions/arcsin1/oh-my-ppt/agents-md)<a href="https://agentmods.dev/instructions/arcsin1/oh-my-ppt/agents-md"><img src="https://agentmods.dev/badge/instructions/arcsin1/oh-my-ppt/agents-md.svg" alt="Measured on agentmods" 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 | $0.00900 | $0.00900 |
| Opus 5 | $0.00450 | $0.00450 |
| Sonnet 5 | $0.00180 | $0.00180 |
| Haiku 4.5 | $0.00090 | $0.00090 |
Grade A, and why
oh-my-ppt AGENTS.md 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 5d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- oh-my-ppt CLAUDE.md — 88% identical, 36 lines differ
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent.md
不要跑
npm run lint。 不要跑npm run build。
Project
Electron 桌面应用,主进程 (src/main/) + 渲染进程 (src/renderer/) + 共享类型 (src/shared/)。
Code Style
singleQuote,no semi,printWidth: 100,trailingComma: none- 路径别名:
@shared/*,@renderer/*
Execution Rules
- 先定位变更属于生成、编辑、导入、导出还是运行时;不要只修单一路径
- 公共规则改动要同时确认生成与编辑链路是否覆盖,尤其是整页编辑、deck 编辑、selector 编辑
- 改运行时资源时,同步确认 session asset 兼容/刷新机制
- 修 bug 时优先补定向回归测试,覆盖当前问题和相邻入口
- 验证优先跑最小相关测试;不要跑
npm run lint或npm run build
Testing
- 框架:Vitest + happy-dom,测试文件放
tests/unit/下,按功能域分子目录,文件名*.test.ts - 跑测试:
pnpm test,跑单个文件:pnpm test -- tests/unit/xxx/foo.test.ts - 修 bug 或加功能时,必须补对应测试到
tests/unit/;测试不通过就继续修代码直到通过 - 注意:样式ui改动不需要写测试
React 组件编写规范
核心原则
1. 逻辑内聚,少传 props
- 能写在组件内的逻辑就写在组件内,不要通过 props 从父组件传进来
- 事件处理、数据获取、状态管理,都优先写在组件自己里面
// ✅ 好
function ProductCard({ id }) {
const [count, setCount] = useState(0)
const handleBuy = () => { /* 逻辑写这里 */ }
return <button onClick={handleBuy}>购买</button>
}
// ❌ 坏
function ProductCard({ count, onBuy }) { /* 逻辑都从外面传 */ }
2. 跨组件状态用 Zustand
- 多个组件需要共享的数据 → 放 zustand store
- 不要通过 props 一层层传
const useStore = create((set) => ({
user: null,
setUser: (user) => set({ user })
}))
// 任何组件直接拿来用,不用传 props
const user = useStore(state => state.user)
3. 复用逻辑抽成自定义 Hook
- 多个组件都需要相同的有状态逻辑时,抽成自定义 Hook
- Hook 放在
hooks/目录下,以use开头
// hooks/useProductData.js
function useProductData(productId) {
const [product, setProduct] = useState(null)
const [loading, setLoading] = useState(false)
useEffect(() => {
fetchProduct(productId).then(setProduct)
}, [productId])
return { product, loading }
}
// 组件中使用
function ProductCard({ id }) {
const { product, loading } = useProductData(id)
// 不用从 props 传 product 和 loading
}
4. 什么情况才用 props?
只传这两类东西:
- 配置项:
size,disabled,variant - 纯展示数据:
title,description
简单检查
写代码前问一句:"这个逻辑/状态能不能直接写在当前组件里?"
- 能 → 就写里面
- 不能,但多个组件都需要 → 放 zustand 或抽成自定义 Hook
- 实在不行 → 才传 props
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.
- 5d ago First seen · 103 lines · 900 tokens per session scan A 2e812d73ebaf
oh-my-ppt AGENTS.md is an instructions file published in the GitHub repository arcsin1/oh-my-ppt (1,921 stars, last pushed yesterday), licensed Apache-2.0. It adds 900 tokens to every session, about $0.0045 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 instructions, from other repositories
nextclaw AGENTS.md
AGENTS.md instructions for Peiiii/nextclaw, covering nextclaw ai 常驻内核, 产品愿景, 沟通与推进, 深思与目标模式 and 协作与 git 安全.
moonproxy-desktop AGENTS.md
AGENTS.md instructions for MoonProxyHQ/moonproxy-desktop, covering moonproxy, 功能, 技术栈, 目录结构 and 配置与数据存储.
code-by-wire CLAUDE.md
Instructions for luojiahai/code-by-wire, covering claude.md, development, website, architecture and code style.
markra AGENTS.md
AGENTS.md instructions for markrahq/markra, covering markra engineering guidelines, package management, tech stack, code organization and codemirror editor invariants.
Token-Dashboard CLAUDE.md
Instructions for Arylmera/Token-Dashboard, covering claude.md, project overview, status, architecture and data source.
ideate AGENTS.md
Instructions for paultyng/ideate, covering agents.md, build features as mcp tools first, ui second, when to add ui and pattern.