Borrowing it
Nothing to install: this file belongs to shen-shanshan/vllm-dev-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/shen-shanshan/vllm-dev-skills/master/AGENTS.mdgit clone --depth 1 https://github.com/shen-shanshan/vllm-dev-skillsWrote 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/shen-shanshan/vllm-dev-skills/agents-md)<a href="https://agentmods.dev/instructions/shen-shanshan/vllm-dev-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/shen-shanshan/vllm-dev-skills/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/shen-shanshan/vllm-dev-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/shen-shanshan/vllm-dev-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00793 | $0.00793 |
| Opus 5.5 | $0.00317 | $0.00317 |
| Sonnet 5.5 | $0.00159 | $0.00159 |
| Haiku 4.5 | $0.00079 | $0.00079 |
Grade B, and why
vllm-dev-skills AGENTS.md scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
完成后用 `ls -l ~/.claude/skills/<skill-name>` 确认链接指向正确。若同名链接已存在且指向本仓库，无需重复创建。 What it actually says
AGENTS.md
Instructions for AI coding agents working in this repository.
Project Layout
skills/<skill-name>/SKILL.md— skill definitions; generated reports go toskills/<skill-name>/outputs/.TODO.md— roadmap, personal learning plan for technical reports, and blog writing tasks.
Rules
Sync generated technical reports to TODO.md
每次通过 vllm-feature-tutorial 或 vllm-model-tutorial 生成技术报告后，必须同步更新 TODO.md：
-
在
## Technical Reports（个人学习计划）小节的末尾追加一行，格式如下（路径相对于仓库根目录）：- [ ] skills/vllm-feature-tutorial/outputs/<report_name>.md (Generated: ✅ / Read: ) - [ ] skills/vllm-model-tutorial/outputs/<report_name>.md (Generated: ✅ / Read: ) -
如果该报告路径已在
TODO.md中存在（例如重新生成同一份报告），不要重复添加。 -
不要修改已有条目的
Read状态和复选框，这些由用户自己维护。 -
完成后在回复中告知用户
TODO.md已更新。
Sync project docs when adding/updating skills
每次在 skills/ 下新增或更新 skill 后，必须完成以下同步工作。这里的“更新 skill”仅指修改 skill 定义本身（SKILL.md 及其配套的 references / scripts / templates 等文件）；使用 skill 生成内容到 skills/<skill-name>/outputs/ 下不算更新，不触发本规则。
-
链接新 skill 到 Claude Code 官方 skill 目录（仅新增 skill 时）：将其软链接到本机
~/.claude/skills/下，使 Claude Code 能识别：ln -sfn "$(pwd)/skills/<skill-name>" ~/.claude/skills/<skill-name>完成后用
ls -l ~/.claude/skills/<skill-name>确认链接指向正确。若同名链接已存在且指向本仓库，无需重复创建。 -
更新
README.md：- 新增 skill：在
## 🚀 Skills表格中按 Category 将其插入到合适位置（Name 链接到./skills/<skill-name>/SKILL.md，填写 Category / Description / Rec），并在## 📖 Usages中补充对应的使用示例（Prompt 等），保持与已有条目一致的格式。 - 更新 skill：若 skill 的功能、描述、触发方式或用法有变化，同步修改表格中的 Description 及
## 📖 Usages中的对应内容。
- 新增 skill：在
-
更新项目介绍博客：调用
vllm-technical-blog-writerskill，更新docs/blogs/introduction_to_vllm_dev_skills/下的博客（introduction_to_vllm_dev_skills.md与zhihu.md需保持内容同步），在对应的研发环节小节（如 2.1 需求发现 ~ 2.8 技术写作）中新增或修改该 skill 的介绍，必要时同步调整“后续计划”等相关段落。同时将两篇博客开头 NOTE 中的日期（本文将会随项目演进持续更新（Last Update：YYYY/MM/DD））更新为当天日期。 -
完成后在回复中告知用户以上哪些内容已更新（软链接 /
README.md/ 博客）。
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.
- yesterday First seen · 43 lines · 793 tokens per session scan B b3a1736d0586
vllm-dev-skills AGENTS.md is an instructions file published in the GitHub repository shen-shanshan/vllm-dev-skills (25 stars, last pushed yesterday), licensed Apache-2.0. It adds 793 tokens to every session, about $0.0032 per session on Opus 5.5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-27.
Other instructions, from other repositories
vibe-coding-prompt-template backend.instructions.md
Instructions for KhazP/vibe-coding-prompt-template: Read AGENTS.md, agentdocs/techstack.md, and agentdocs/codepatterns.md.
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).