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/puppylpg/puppylpg.github.io/agents-mdgit clone --depth 1 https://github.com/puppylpg/puppylpg.github.ioWhat 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 | $0.05124 | $0.05124 |
| Opus 5 | $0.02562 | $0.02562 |
| Sonnet 5 | $0.01025 | $0.01025 |
| Haiku 4.5 | $0.00512 | $0.00512 |
Grade A, and why
puppylpg.github.io 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 2d 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent 协作指南
本项目是 Jekyll + Chirpy 主题的个人博客，部署在 GitHub Pages 上。
AGENTS.md 是本仓库面向所有 coding agent 的主入口。Codex、Claude、Cursor、Gemini CLI 等工具都应优先遵循这里的规则；工具私有文件只保留入口转发、权限、hook、命令等专属配置。
仓库背景
这是基于 Chirpy gem 主题的个人 Jekyll 博客。大部分布局、样式、JS 在主题 gem 中；本仓库主要放站点配置、文章内容、少量自定义 layout/plugin 和本地开发脚本。
Ruby 环境、本地开发完整流程以 README.md 为准。这里记录 agent 工作时必须稳定遵守的仓库约定。
项目内 Skill
项目内可复用工作流放在 .agents/skills/：
| Skill | 用途 |
|---|---|
archive-chat |
将当前对话整理成结构化总结并发布为博客文章 |
ai-trends-report |
抓取最新 AI Trends 动态图表，逐图解读并发布为博客文章 |
summarize-article |
将用户给的文章 URL 总结成博客文章 |
blog-lint |
全站健康体检：事实矛盾、过时结论、孤儿文章、枢纽页新鲜度、格式约定，输出体检报告 |
使用这些 skill 时，先读取对应 SKILL.md，再按本文的文章发布通用流程执行预览、确认和发布。
.agents/skills/ 是 skill 的唯一真实维护源。.claude/skills/ 只放 Claude Code 兼容用的薄代理文件，代理文件必须指向 .agents/skills/<skill>/SKILL.md，不要复制完整流程。
文章发布通用流程
任何将文章写入 _ai/、_posts/、_life/ 或 _tutorials/ 的 skill/agent，开始修改前应先执行 git pull --rebase --autostash 同步远端 master。本项目可能由多个环境同时维护，该命令会自动 stash 未提交修改、拉取远端、rebase 后再 pop，一步完成。
落盘后遵循以下流程：
- 本地预览。
- 等用户确认。
- 询问用户后再执行
git commit和git push，不要自动推送。 - 用户不满意时，删除文件或按反馈修改后重来。
- 用户确认并发布后，关闭本地预览服务并做善后清理（见下方「发布后的善后」）。
目标目录与默认分类
| 用户说法 | 目标目录 | 默认 categories |
|---|---|---|
| 未特别说明 / “发到 AI” / 默认 | _ai/ |
[ai] |
| “发到 tech” / “发到 post” / “发到 _posts” | _posts/ |
[tech] |
| “发到 life” / “发到生活” / VPS、树莓派、家庭网络、家庭影院、代理/V2Ray、Windows 排障、系统升级、网络加速等日常折腾 | _life/ |
[life] |
| “发到 tutorial” / “发到 _tutorials” | _tutorials/ |
[tutorial] |
| “更新 wiki” / 主题枢纽页、当前状态类活页面 | _wiki/ |
[wiki] |
- 内容归属按文章主语判断，而不是按是否用到了某项技术判断。
Tech放技术原理、框架机制和可复用工程知识，例如 Java、Spring、Redis、Elasticsearch、Docker Engine、Docker network/storage、Linux/网络/SSH 原理、AI 推理机制等。Life放个人日常、生活记录和折腾实录。VPS、树莓派、家庭网络、家庭影院/影音下载、代理/V2Ray、Windows 环境排障、系统升级、网络加速等文章，即使用到 Docker、Linux、Nginx、DNS、network 等技术，也默认写入_life/。- 若主题有更细分领域，可在默认分类后追加，例如
[ai, tools]、[tech, tools]、[tutorial, docker]、[life, vps, docker]、[life, raspberry-pi, docker, homelab]。迁入_life/的折腾类文章不要只写[life]，应保留docker、vps、network、proxy、windows等可检索主题分类；但不要继续保留tech分类。 - Docker 本身的原理、网络、存储、镜像机制属于
Tech；用 Docker 搭个人服务、升级 VPS、整理家庭影音环境属于Life。
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.
- 2d ago First seen · 237 lines · 5,124 tokens per session scan A f2f2f627457d
puppylpg.github.io AGENTS.md is an instructions file published in the GitHub repository puppylpg/puppylpg.github.io (2 stars, last pushed 7d ago), licensed MIT. It adds 5,124 tokens to every session, about $0.0256 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.