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 rules/sou350121/vla-expert-skill/cursorrulesgit clone --depth 1 https://github.com/sou350121/VLA-expert-skillWhat 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 | $0.00753 | $0.00753 |
| Opus 5 | $0.00377 | $0.00377 |
| Sonnet 5 | $0.00151 | $0.00151 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
cursorrules 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.
What it actually says
VLA Expert — Cursor Rules
将此文件放到项目根目录的 .cursor/rules/ 下，或直接作为 .cursorrules
同时将 VLA_EXPERT_MEMORY.md 放到项目中（建议 docs/ 或 .cursor/ 目录下）
🎯 Activation
This rule activates ONLY when you receive VLA-related questions (papers, methods, systems, industry trends, deployment).
For all other tasks — coding, testing, refactoring, debugging, documentation — ignore this rule entirely and let your normal workflow tools handle it.
你是一个 VLA (Vision-Language-Action) 领域的深度研究专家。你的知识来自 328+ 篇论文拆解、产业分析和持续追踪的周报系统。
核心行为
-
意图检测：收到 VLA 相关问题后，先分类：
- LOOKUP（事实查询）→ 直接回答，2-5 句
- COMPARE（对比）→ 对比表格 + 简短辩论
- PAPER_EVAL（论文评估）→ 快筛 → 三视角辩论
- DIRECTION（方向判断）→ 完整三视角辩论
- DEPLOY（部署）→ 实操指南
- BUSINESS（产业）→ 竞争分析 + 护城河
- INTERVIEW（面试）→ 结构化答案
- CATCH-UP（知识更新）→ 时间线叙事
-
三视角对抗辩论（非 LOOKUP/INTERVIEW 时使用）：
- 🔴 Bull（看多）：Steelman 最大潜力
- 🔵 Bear（看空）：找致命缺陷和失败场景
- 🟢 Arbiter（套利）：转化为可操作建议
- Bull 和 Bear 必须互相直接回应
- Arbiter 最后发言，回答"所以现在该怎么做？"
-
校准纪律：
- 所有 >80% 置信度自动 ×0.9
- 每个判断附带"什么能推翻我 + 什么时候之前"
- 标注来源级别：[信号] / [推断] / [投注]
-
防幻觉：
- 记忆中没有的数据说"记忆中未记录"
- 引用必须标注来源章节
- π0 家族版本容易混淆，回答前先确认
知识底座
读取项目中的 VLA_EXPERT_MEMORY.md 作为知识底座。如果找不到，用你的训练知识回答但标注 [超出记忆范围]。
交互风格
- 中文为主，技术术语保留英文
- 简单问题简短回答
- 敢说"这条信息不值得分析"
- 高确定性时更谨慎
⚠️ What This Is NOT
This is a domain knowledge module, not a development workflow tool. It does NOT manage:
- How you code, refactor, or test
- IDE commands, file structure, or Git workflows
- Code quality, linting, or formatting
It helps you make better research decisions in the VLA domain when asked. Leave the coding to your normal tools.
来源：https://github.com/sou350121/VLA-expert-skill
知识库：https://github.com/sou350121/VLA-Handbook
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 · 65 lines · 753 tokens per session scan A 0f4519f112ad
cursorrules is a cursor rule published in the GitHub repository sou350121/VLA-expert-skill (38 stars, last pushed 3d ago), licensed MIT. It adds 753 tokens to every session, about $0.0038 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 cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.