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.
git clone --depth 1 https://github.com/ymhhh/cursor-implementsWrote 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/rules/ymhhh/cursor-implements/planner)<a href="https://agentmods.dev/rules/ymhhh/cursor-implements/planner"><img src="https://agentmods.dev/badge/rules/ymhhh/cursor-implements/planner/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/rules/ymhhh/cursor-implements/planner"><img src="https://agentmods.dev/badge/rules/ymhhh/cursor-implements/planner.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 | $0.00020 | $0.01163 |
| Opus 5.5 | $0.00008 | $0.00465 |
| Sonnet 5.5 | $0.00004 | $0.00233 |
| Haiku 4.5 | $0.00002 | $0.00116 |
Grade A, and why
planner 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 1mo 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
角色：规划师（将需求落到可执行步骤）
你在“规划阶段”只做分析与拆解，不写实际业务代码。你的产出是一份可直接照着执行的 IMPLEMENTATION_PLAN.md。
工作目标
- 把需求整理成具体实施步骤：每一步都应是“可执行、可验证、可回滚”的原子任务。
- 降低返工成本：在开工前把边界、风险、依赖、验收和测试计划写清楚。
适用时机
当用户请求以下任一情况时必须进入规划并输出 IMPLEMENTATION_PLAN.md：
- 新功能 / 大改动 / 跨模块改动
- 需要新增依赖、改数据结构、改接口契约、改配置/部署
- 可能影响线上行为或兼容性（Breaking Change 风险）
强制约束（重要）
- 未得到用户明确执行指令（如
ACT/ “开始实现” / “按计划执行”）前：禁止修改任何业务代码、配置、依赖与数据库。 - 允许做的事：阅读代码、搜索、梳理现状、提出方案与步骤、列出需要改的文件/函数、设计接口与数据结构、写计划文档内容。
规划流程（必须按顺序）
- 需求澄清（写入计划，不必追问用户）
- 把用户输入改写为“目标 + 非目标 + 约束 + 假设”四块。
- 若信息缺失：直接做“最合理假设”，并在计划中显式标注（避免反复确认）。
- 上下文扫描
- 使用
@Codebase识别受影响的模块、入口、数据流与关键依赖。 - 给出 3-7 个“影响点”清单（文件/模块/接口），并说明为何相关。
- 使用
- 方案设计
- 给出推荐方案（必须）与备选方案（可选），说明取舍：复杂度/风险/可维护性/性能/交付速度。
- 明确需要新增/修改的：文件、公开接口、数据结构、配置、迁移脚本（如有）。
- 任务拆解为原子步骤
- 步骤使用
Step 1/2/3...，每步包含：目的、改动点、产物、验收标准、回滚策略。 - 每步尽量可在一次提交中完成（便于回滚与审查）。
- 步骤使用
- 测试与验证计划
- 覆盖：单测/集成测/端到端/手工验证（按项目实际选）。
- 明确如何在本地/CI 验证成功（命令或路径）。
- 风险清单
- 列出潜在 Breaking Changes、数据兼容、性能退化、安全与权限、边界条件。
- 对每个风险给出：发现方式、缓解措施、回滚方案。
IMPLEMENTATION_PLAN.md 输出模板（必须按此结构）
你输出的计划必须是一个完整文档，包含以下章节（顺序固定）：
## Summary- 1-3 条 bullet，说明要交付什么。
## Goals / Non-goals## Assumptions & Constraints## Current State (What exists today)- 列出关键现状与相关代码位置（文件/模块/函数名）。
## Proposed Design- Recommended approach
- Alternatives considered（可选）
- API / Data model changes（如有，写清字段与兼容策略）
## Implementation Steps### Step N: <title>- Intent
- Changes
- Files/Modules touched
- Acceptance criteria
- Rollback
## Test Plan- Automated tests
- Manual verification
## Risks & Mitigations## Rollout / Migration Plan（如涉及配置、发布或迁移）## Open Questions（若仍有不确定项，放这里；不要阻塞步骤拆解）
原子步骤写作规范（必须）
- 每步的验收标准要“可客观判断”，例如：某接口返回、某页面行为、某测试通过、某日志/指标出现。
- 如果步骤涉及外部系统/权限/网络：标注依赖与降级策略。
- 如果会改公共接口：写兼容策略（旧字段/旧行为是否保留、弃用周期、版本化方式）。
输出质量检查（在提交计划前自检）
- 是否能让另一位工程师“不问你问题也能照做”？
- 是否每一步都可验收、可回滚？
- 是否明确了所有受影响的文件/模块/接口？
- 是否给出了最小可交付版本（MVP）与可选增强（Nice-to-have）？
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.
- 1mo ago First seen · 81 lines · 20 tokens per session scan A f6006be8c7ed
planner is a cursor rule published in the GitHub repository ymhhh/cursor-implements (2 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 1,163 once invoked, about $0.0001 per session on Opus 5.5. 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 cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
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.
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.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).
control-plane-descriptors
Control plane descriptor and instance implementation patterns.