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/shangyankeji/super-dev/cursorrulesgit clone --depth 1 https://github.com/shangyankeji/super-devWhat 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 | $0.00506 | $0.00506 |
| Opus 5 | $0.00253 | $0.00253 |
| Sonnet 5 | $0.00101 | $0.00101 |
| Haiku 4.5 | $0.00051 | $0.00051 |
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
Super Dev Cursor Rules
在 Cursor 中使用 Super Dev 进行规范驱动开发。
核心原则
- 规范先行 - 在编码前阅读并理解规范
- 遵循关键词 - 严格遵守 SHALL/MUST/SHOULD/MAY
- 验证格式 - 确保所有规范符合 OpenSpec 标准
读取规范
当用户要求实现功能时：
- 首先检查
.super-dev/changes/目录 - 运行
super-dev spec list查看活跃变更 - 运行
super-dev spec show <change-id>查看规范详情 - 阅读 proposal.md、tasks.md、specs/**/*.md
实现规范
实现代码时：
- 确保 SHALL 和 MUST 需求全部实现
- SHOULD 需求尽可能实现
- MAY 需求可选实现
- 实现 Scenario 中描述的行为
验证要求
完成实现后：
- 运行
super-dev spec validate <change-id>验证格式 - 确保所有测试通过
- 检查代码符合规范要求
目录约定
.super-dev/specs/- 当前规范（单一事实源）.super-dev/changes/- 提议的变更（工作区）.super-dev/archive/- 已归档的变更
命令快捷方式
用户可能使用以下简写：
.spec list → super-dev spec list
.spec show <id> → super-dev spec show <id>
.spec validate → super-dev spec validate
.spec view → super-dev spec view
需求级别
- SHALL: 强制要求，必须实现
- MUST: 技术约束，必须满足
- SHOULD: 推荐做法，强烈建议
- MAY: 可选功能，可以跳过
场景格式
使用 Given-When-Then 格式：
#### Scenario: Description
Given <precondition>
When <action>
Then <outcome>
Delta 类型
- ADDED: 新增需求
- MODIFIED: 修改现有需求
- REMOVED: 删除需求
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 · 78 lines · 506 tokens per session scan A 30a20671962c
cursorrules is a cursor rule published in the GitHub repository shangyankeji/super-dev (273 stars, last pushed 2mo ago), licensed MIT. It adds 506 tokens to every session, about $0.0025 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
language-agnostic-patterns
Language-agnostic programming patterns: SOLID, design patterns, clean code, and architecture. Load when refactoring, designing abstractions, or reviewing structure — not for everyday syntax.
cursor-tools-mastery
Cursor 3.7 runtime guide: choose the right tool, canvases, Design Mode, /worktree, /best-of-n, Await, and parallel execution where safe.
cursor-agent-orchestration
Cursor 3.7 orchestration guide: when to plan, when to delegate, nested subagents, multi-environment handoffs, /best-of-n, and Await for long-running branches.
fable5-reasoning
Fable 5 reasoning protocols: task interpretation, risk-first decomposition, approach selection, interleaved thinking, hypothesis ledgers, premortems, calibration, and the stuck-strategy ladder. Load for complex, ambiguous, or long-horizon tasks, for debugging strategy, or whenever progress stalls.
cursor-mcp-optimization
Cursor 3.7 MCP optimization: browser Design Mode, canvases, Figma, Cloudflare tools, MCP Apps structured content, and direct action patterns.
design-systems
Design system mechanics: tokens, shadcn/ui, Tailwind v4, composition, theming. Load for UI implementation — aesthetics and anti-slop live in the anti-slop-design skill.