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 skills/nikolahuang/nova-cli/writing-plansnpx skills add Nikolahuang/nova-cli --skill writing-plansgit clone --depth 1 https://github.com/Nikolahuang/nova-cliWrote 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/skills/nikolahuang/nova-cli/writing-plans)<a href="https://agentmods.dev/skills/nikolahuang/nova-cli/writing-plans"><img src="https://agentmods.dev/badge/skills/nikolahuang/nova-cli/writing-plans.svg" alt="Measured on agentmods" 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 | $0.00035 | $0.00598 |
| Opus 5 | $0.00017 | $0.00299 |
| Sonnet 5 | $0.00007 | $0.00120 |
| Haiku 4.5 | $0.00003 | $0.00060 |
Grade A, and why
writing-plans 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 4d 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
编写计划 - 从设计到实施
概述
将批准的设计分解为详细的实施计划。每个任务都足够小（2-5 分钟），包含确切的文件路径、完整代码和验证步骤。
计划格式
# 实施计划: [功能名称]
## 概述
[1-2 段简短描述]
## 技术上下文
- 语言: [语言和版本]
- 框架: [框架及版本]
- 关键依赖: [列出]
## 任务清单
### 任务 1: [简短描述]
**文件**: `path/to/file.ts`
**时间**: 2-5 分钟
**要编写的代码**:
```typescript
// 完整可运行的代码
验证步骤:
- [具体验证命令或测试]
- [预期输出]
任务 2: [简短描述]
...
## 编写指南
### 任务大小
- 每个任务 2-5 分钟
- 单一职责
- 明确的开始和结束
### 代码完整性
- 完整可运行的代码片段
- 包含必要的导入
- 包含类型定义
### 验证
- 具体的验证命令
- 预期的输出或行为
- 测试命令（如适用）
## TDD 集成
如果使用测试驱动开发：
```markdown
### 任务 1.1: 写失败的测试
**文件**: `path/to/file.test.ts`
```typescript
test('功能描述', () => {
// 测试代码
});
验证: npm test → 测试应该失败
任务 1.2: 写最小实现
文件: path/to/file.ts
// 最小通过代码
验证: npm test → 测试应该通过
## 关键原则
- **粒度适中** - 小到可以快速验证
- **完整性** - 包含所有必要信息
- **可验证** - 每步都有明确的验证方式
- **顺序合理** - 依赖关系清晰
- **YAGNI** - 只计划当前需要的功能
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.
- 4d ago First seen · 99 lines · 35 tokens per session scan A 4ade580e8863
writing-plans is a skill published in the GitHub repository Nikolahuang/nova-cli (14 stars, last pushed 4mo ago), licensed MIT. It adds 35 tokens to every session and 598 once invoked, about $0.0002 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 skills, from other repositories
software-implementation
Write the minimal production code needed to make failing TDD tests pass (Green phase of red-green-refactor). Use when failing tests exist and production code must be written or modified to satisfy them. Reads and interprets failing test output, discovers codebase conventions (module layout, naming, import patterns…
plan
Plan mode: write markdown plan to .mateclaw/plans/, no exec.
pypto-pitfalls
：标量任意位置。- /：tensor 必须在左。函数调用：第一参数必须 Tensor。.
tilelang-cuda-memory
TileLang CUDA 内存访问优化策略，包括 T.allocshared/fragment 使用、数据布局优化、合并访存和 Bank Conflict 避免技巧。适用于内存带宽受限、需要优化数据搬运效率的 TileLang 内核性能优化场景.
tilelang-cuda-synchronization
TileLang CUDA 同步规范，包括 T.syncthreads() 使用规则、线程安全最佳实践和死锁预防策略。适用于编写涉及共享内存访问、多线程协作、或需要避免同步死锁的 TileLang 内核代码生成场景.
pypto-loop-view
最常见的首次生成错误。所有 pypto.view 的 shape 参数必须是编译期常量（字面量或闭包变量）。.