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/wokaka209/markdown_everything/claude-mdgit clone --depth 1 https://github.com/wokaka209/markdown_everythingWrote 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/wokaka209/markdown_everything/claude-md)<a href="https://agentmods.dev/instructions/wokaka209/markdown_everything/claude-md"><img src="https://agentmods.dev/badge/instructions/wokaka209/markdown_everything/claude-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 | $0.00943 | $0.00943 |
| Opus 5 | $0.00472 | $0.00472 |
| Sonnet 5 | $0.00189 | $0.00189 |
| Haiku 4.5 | $0.00094 | $0.00094 |
Grade A, and why
markdown_everything CLAUDE.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 4d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
项目概述
markdown-everything 是一个 AI Agent Skill,将 20+ 种文档格式(PDF、Word、Excel、PPT、图片、音频)转换为 Markdown。核心依赖是 markitdown,针对中文 PDF 做了 pdfplumber 的 Unicode 字符级提取来解决乱码。
常用命令
# 基本转换
python SKILL/markdown-everything/scripts/convert_document.py "文档.pdf" -o "输出.md"
# 直接用 markitdown CLI
markitdown "文档.docx" -o "输出.md"
# JSON 格式输出
python SKILL/markdown-everything/scripts/convert_document.py "文档.docx" --json-output
# 详细日志
python SKILL/markdown-everything/scripts/convert_document.py "文档.docx" --verbose
# 环境管理(PowerShell)
.\SKILL\markdown-everything\scripts\manage_environment.ps1 -Command setup
.\SKILL\markdown-everything\scripts\manage_environment.ps1 -Command check
# 环境管理(Bash)
bash SKILL/markdown-everything/scripts/manage_environment.sh setup
bash SKILL/markdown-everything/scripts/manage_environment.sh check
架构
SKILL/markdown-everything/
├── SKILL.md # Skill 定义,Claude Code 加载此文件触发转换
└── scripts/
├── convert_document.py # 主入口:DocumentConverter 类 + CLI
├── pdf_encoding_fixer.py # PDF 专用:PDFEncodingFixer 类
├── manage_environment.ps1 # Windows 环境管理(Conda/pip)
└── manage_environment.sh # Linux/macOS 环境管理
转换流程
- PDF 文件 →
PDFEncodingFixer.convert()→ pdfplumber Unicode 字符级提取 - 如果 pdfplumber 失败 → 回退到
page.extract_text() - 如果仍然失败 → 回退到标准 markitdown
- 非 PDF 文件 → 直接用
DocumentConverter.convert()调 markitdown - 可选:LLM 后处理(GPT-4 / Claude)
关键类
DocumentConverter(convert_document.py): 封装 markitdown,管理 LLM 客户端初始化,返回{success, text_content, output_file}结构PDFEncodingFixer(pdf_encoding_fixer.py): 用 pdfplumber 的page.chars对象按 Unicode 字段提取文字,绕过 PDF 字节编码问题。包含文本质量检测(中文比例、乱码率)
环境管理脚本
PowerShell 和 Bash 版本功能一致:
- 自动检测 Conda 安装路径(扫描多个默认位置)
- 自动创建 markitdown Conda 环境
- 支持 pip 镜像源(tsinghua/aliyun/douban)
- 支持
MARKITDOWN_USE_PIP=true跳过 Conda 直接用系统 Python
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.
- 4d ago First seen · 84 lines · 943 tokens per session scan A 8bb9454b7137
markdown_everything CLAUDE.md is an instructions file published in the GitHub repository wokaka209/markdown_everything (2 stars, last pushed 4mo ago), licensed MIT. It adds 943 tokens to every session, about $0.0047 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 2026-08-31.
Other instructions, from other repositories
gpt-rag-ingestion azure-boundaries.instructions.md
Instructions for Azure/gpt-rag-ingestion, a project described as: The GPT-RAG Data Ingestion service automates processing of diverse documents—PDFs, images, spreadsheets, transcripts, and SharePoint—readying them for Azure AI Search. It applies smart chunking, generates text and image embeddings, and enables rich…
tablepack AGENTS.md
Instructions for kujiangmudao/tablepack, covering two user paths, multimodal requirement, environment, hard requirements (never skip) and qc checklist (every pdf).
vibelawyer CLAUDE.md
Claude Code instructions for Jack-mi/vibelawyer, covering vibelawyer, 快速命令, 打印 mcp 接入指引, 打印宿主阅卷 playbook and 启动 mcp server(stdio).
financial-analyst-skills AGENTS.md
Instructions for Ruinius/financial-analyst-skills, covering project documentation index, folder structure, skills overview and local server ports.
agent-tools AGENTS.md
Instructions for AtmaticAI/agent-tools, covering claude.md, project overview, commands, development and building.
libreoffice-mcp-tools copilot-instructions.md
Copilot instructions for passerbyflutter/libreoffice-mcp-tools, covering libreoffice mcp tools — copilot instructions, project overview, architecture principles, token efficiency (core design goal) and technology stack.