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/huangwb8/m2w/agents-mdgit clone --depth 1 https://github.com/huangwb8/m2wWrote 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/huangwb8/m2w/agents-md)<a href="https://agentmods.dev/instructions/huangwb8/m2w/agents-md"><img src="https://agentmods.dev/badge/instructions/huangwb8/m2w/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 | $0.02927 | $0.02927 |
| Opus 5 | $0.01463 | $0.01463 |
| Sonnet 5 | $0.00585 | $0.00585 |
| Haiku 4.5 | $0.00293 | $0.00293 |
Grade A, and why
m2w 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 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.
How it starts
The opening of the file, as written. The whole thing — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.
m2w: Markdown to WordPress - 项目指令
项目目标
m2w 是一个将本地 Markdown 文章批量上传或更新到 WordPress 的工具。
核心特性：
- 支持两种模式：REST API（推荐）和传统 XML-RPC 密码模式
- 异步批量上传/更新文章
- 支持分类、标签、文章状态等元数据配置
- 自动检测 Markdown frontmatter 并合并到 WordPress 字段
项目定位：
- 核心入口：m2w/up.py（异步 orchestrator）
- REST API 逻辑：m2w/rest_api/
- 传统 XML-RPC 逻辑：m2w/password/
环境要求
- Python 版本：>= 3.7.6
- 核心依赖（见 setup.py）：
python-frontmatter：解析 Markdown frontmattermarkdown：Markdown 转 HTMLhttpx：异步 HTTP 客户端python-wordpress-xmlrpc：传统 XML-RPC 支持
本地开发安装：
pip install -e .
配置要点
主配置文件
运行前需准备 config/user.json，可包含多个站点配置。
配置结构：
{
"站点域名": {
"domain": "https://example.com",
"username": "用户名",
"application_password": "WordPress 应用密码",
"path_markdown": ["本地 Markdown 目录路径"],
"post_metadata": {
"category": ["分类"],
"tag": ["标签"],
"status": "publish"
},
"path_legacy_json": "可选：历史 JSON 文件路径"
}
}
配置自动生成
m2w/config/config.py 在缺失配置时会自动生成模板并退出，提醒用户补全。
测试配置
@test/config/user.json 是实际可用的测试配置示例。
重要提示：
- 该文件包含真实凭证，仅供本地演示使用
- 请勿外泄或对生产站点直接运行
- 所有新优化的 m2w 代码，都要在 @test 里通过测试才可以交付
常用命令
基本使用
# 运行主程序
python myblog.py
# 或在自定义脚本中调用
from m2w import up
up.run()
构建与发布
# 生成发布包
python setup.py sdist bdist_wheel
# 本地验收安装
pip install ./dist/m2w-<ver>.tar.gz
# 发布到 PyPI（参考 setup.py 顶部注释）
twine upload dist/*<ver>*
验证策略
当前状态：暂无自动化测试
手动测试流程：
- 使用 @test/myblog-test.py 进行演练
- 使用 @test/main 内的 Markdown 文件测试
- 检查 WordPress 站点文章状态
注意事项：
- 测试会实际请求目标站点
- 务必使用测试站点/测试凭证
- 变更上传逻辑后建议手动跑一次完整流程
版本管理
版本号同步
修改版本号需同时更新：
- setup.py 中的版本号
- m2w/init.py 中的版本号
- README.md 和 CHANGELOG.MD
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 · 320 lines · 2,927 tokens per session scan A c53045f4abc6
m2w AGENTS.md is an instructions file published in the GitHub repository huangwb8/m2w (44 stars, last pushed 7mo ago), licensed MIT. It adds 2,927 tokens to every session, about $0.0146 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
epytor AGENTS.md
Instructions for peiyucn/epytor, covering 项目指令 — epytor, 语言, 需求, 开发 and 基本规则.
epytor CLAUDE.md
Instructions for peiyucn/epytor, a project described as: WYSIWYG Markdown editor for VS Code, powered by Milkdown.
mq commit.instructions.md
Instructions for harehare/mq: Use the following format for commit messages.
core copilot-instructions.md
Instructions for asdecided/core: These decisions are already accepted. Do not re-open or contradict them; ask the AsDecided MCP tools (getartifact, searchartifacts) for the full text before proposing a change that touches one.
hana-developer-cli-tool-example connection-pooling-timeout-management.instructions.md
Use when creating or updating code that manages database connections. Enforces consistent timeout configuration, proper connection cleanup, graceful error handling, and connection pooling best practices across CLI commands, routes, and tests.
coder CLAUDE.md
Claude Code instructions for coder/coder, a project described as: Secure environments for developers and their agents.