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 commands/laborany/laborany/analyzegit clone --depth 1 https://github.com/laborany/laboranyWrote 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/commands/laborany/laborany/analyze)<a href="https://agentmods.dev/commands/laborany/laborany/analyze"><img src="https://agentmods.dev/badge/commands/laborany/laborany/analyze.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 | $0.00000 | $0.01531 |
| Opus 5 | $0.00000 | $0.00766 |
| Sonnet 5 | $0.00000 | $0.00306 |
| Haiku 4.5 | $0.00000 | $0.00153 |
Grade A, and why
analyze 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 3d 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.
This is a copy
100% identical to analyze — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ppt-analyze 命令 - 文稿分析
命令说明
分析用户提供的 Markdown 文稿，提取核心内容，输出结构化的 PPT 页面清单。
触发方式
/ppt-analyze @文稿.md
或者用户说：
- "帮我分析这份文稿，拆解成 PPT 页面"
- "把这个文档转成 PPT 结构"
执行流程
Step 1: 读取文稿
- 读取用户指定的 Markdown 文件
- 如果用户没有指定文件，提示用户通过
@引用文件
Step 2: 内容分析
分析文稿时，关注以下维度：
| 维度 | 分析内容 |
|---|---|
| 主题 | 文章的核心主题是什么？涉及哪些领域？ |
| 结构 | 文章的逻辑结构（总分、递进、并列等） |
| 关键词 | 提取 5-10 个核心关键词 |
| 要点 | 每个章节/段落的核心观点 |
| 数据/案例 | 是否有需要可视化的数据或案例 |
Step 3: 页面拆解
根据内容分析，将文稿拆解为 PPT 页面。遵循以下原则：
拆解原则：
- 每页只聚焦 1 个核心观点
- 信息密度适中（避免过载）
- 考虑演示节奏（开场→展开→高潮→收尾）
页面类型：
| 类型 | 用途 | 特点 |
|---|---|---|
| 封面页 | 开场，展示标题和主题 | 低密度，视觉冲击 |
| 引言页 | 引出话题，建立共鸣 | 中密度，设问或痛点 |
| 观点页 | 展示核心论点 | 高密度，论点+论据 |
| 图表页 | 数据可视化 | 中密度，图表为主 |
| 流程页 | 展示步骤/流程 | 中密度，时间线或步骤 |
| 对比页 | A vs B 对比 | 中密度，左右对比 |
| 总结页 | 回顾要点 | 中密度，要点列表 |
| 结束页 | 收尾，行动呼吁 | 低密度，CTA |
Step 4: 输出页面清单
以 Markdown 表格形式输出，包含：
## 📑 PPT 页面结构
| 页码 | 类型 | 标题 | 内容要点 | 密度 |
|------|------|------|----------|------|
| 1 | 封面页 | [主标题] | [副标题/来源] | 低 |
| 2 | 引言页 | [引言标题] | [核心问题/痛点] | 中 |
| 3 | 观点页 | [观点1标题] | [要点1, 要点2, 要点3] | 高 |
| ... | ... | ... | ... | ... |
### 📊 内容概要
- **总页数**: X 页
- **核心主题**: [主题描述]
- **关键词**: [关键词1], [关键词2], ...
- **预计时长**: 约 X 分钟（每页 1-2 分钟）
### 💡 拆解说明
[简要说明拆解逻辑和考量]
Step 5: 确认与调整
输出后，询问用户：
以上是我对文稿的页面拆解方案。
你可以：
1. ✅ 确认，继续下一步（/ppt-design）
2. ✏️ 修改某些页面的拆解
3. ➕ 增加或删除页面
4. 🔄 重新拆解（换一种结构）
请告诉我你的想法。
输出示例
## 📑 PPT 页面结构
| 页码 | 类型 | 标题 | 内容要点 | 密度 |
|------|------|------|----------|------|
| 1 | 封面页 | 如何在一天内彻底修复你的人生 | 行为改变与身份重塑的 7 个原则 | 低 |
| 2 | 引言页 | 为什么新年决心总是失败？ | 痛点共鸣，引出核心问题 | 中 |
| 3 | 观点页 | I. 身份先于行动 | 一阶改变 vs 二阶改变，冰山隐喻 | 高 |
| 4 | 观点页 | II. 行为即目标 | 目的论，潜意识目标分析 | 高 |
| 5 | 观点页 | III. 身份是保护机制 | 8步循环图，身份防御机制 | 高 |
| 6 | 图表页 | IV. 心智的 9 个阶段 | 金字塔图，发展阶段可视化 | 中 |
| 7 | 观点页 | V. 智力 = 得到你想要的 | 成功公式，控制论5步循环 | 高 |
| 8 | 过渡页 | 一天协议：开启全新生活 | 三阶段流程预览 | 低 |
| 9 | 流程页 | 早晨 · 心理挖掘 | 14个深度问题，三组卡片 | 高 |
| 10 | 流程页 | 全天 · 打断自动驾驶 | 6个定时提醒，沉思问题 | 中 |
| 11 | 流程页 | 晚上 · 综合见解 | 整合4问，三层透镜目标 | 高 |
| 12 | 观点页 | VII. 人生游戏化 | 六组件映射表 | 中 |
| 13 | 总结页 | 核心洞见回顾 | 7个观点的一句话总结 | 中 |
| 14 | 结束页 | 明天就开始协议 | 行动呼吁，原文链接 | 低 |
### 📊 内容概要
- **总页数**: 14 页
- **核心主题**: 个人成长、行为改变、身份重塑
- **关键词**: 身份、行为、心智、协议、目标、改变
- **预计时长**: 约 15-20 分钟
### 💡 拆解说明
这篇文章结构清晰，包含 7 个核心观点 + 1 套实操协议。
我按照「引言→观点展开→实操方法→总结」的节奏进行拆解，
确保每页聚焦一个核心概念，便于观众消化。
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.
- 3d ago First seen · 142 lines · 0 tokens per session scan A 899fbc0dd727
analyze is a command published in the GitHub repository laborany/laborany (80 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,531 tokens. A static security scan graded it A with 0 findings. It is 100% identical to analyze, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
architect
Generate a comprehensive architecture document for a system or feature based on requirements.
document-all
Auto-document the entire codebase by generating module-level docs, function signatures, and API references.
report
Generate a project analytics report covering code quality, velocity, and health metrics.
explain
Explain a code file, function, or concept in clear, structured language.
design-api
Design a RESTful or GraphQL API based on the project's domain model and requirements.
write-adr
Create a new Architecture Decision Record documenting a technical decision.