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 commands/sumulige/sumulige-claude/tddgit clone --depth 1 https://github.com/sumulige/sumulige-claudeWrote 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/commands/sumulige/sumulige-claude/tdd)<a href="https://agentmods.dev/commands/sumulige/sumulige-claude/tdd"><img src="https://agentmods.dev/badge/commands/sumulige/sumulige-claude/tdd.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 | $0.00014 | $0.02097 |
| Opus 5 | $0.00007 | $0.01048 |
| Sonnet 5 | $0.00003 | $0.00419 |
| Haiku 4.5 | $0.00001 | $0.00210 |
Grade A, and why
tdd 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 5d 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 — 393 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/tdd - Test-Driven Development Workflow
Guide the complete TDD cycle: write tests first, then implement.
Usage
/tdd # Start TDD workflow for new feature
/tdd <feature-name> # Start TDD for specific feature
/tdd --from-todo # Start TDD from active todo task
/tdd --continue # Continue from current step
Integration with /todos
/tdd 与任务系统 /todos 无缝集成:
/todos: 创建任务 "实现用户认证"
↓
/tdd --from-todo: 从任务开始 TDD 流程
├── Step 1: 读取任务描述作为 User Story
├── Step 2-6: TDD 循环(自动更新任务进度)
└── Step 7: 完成后标记任务状态
↓
/todos: 任务自动标记为完成
进度映射
| TDD Step | Todo 进度 |
|---|---|
| Step 1: User Story | [x] Planning |
| Step 2-5: RED → GREEN | [x] In progress |
| Step 6: Refactor | [x] Testing |
| Step 7: Coverage OK | [x] Review → Complete |
从 Todo 开始 TDD
/tdd --from-todo
- 读取
development/todos/active/中的任务 - 用户选择要开发的任务
- 提取任务描述作为 User Story
- 开始 TDD 循环
- 完成后自动更新任务状态
The 7-Step TDD Cycle
Step 1: Define Requirements (User Story)
Before writing any code, define what you're building.
If using --from-todo:
- 读取任务文件中的描述和子任务
- 将子任务转换为验收标准
- 确认或补充需求
Otherwise:
## User Story
As a [user type],
I want to [action],
So that [benefit].
## Acceptance Criteria
- [ ] Criterion 1
- [ ] Criterion 2
- [ ] Criterion 3
Ask the user: What feature are we building? What are the acceptance criteria?
Todo 进度更新: [x] Planning
Step 2: Write Tests First (RED)
Create test file BEFORE implementation:
// Example: tests/feature.test.js
describe('Feature Name', () => {
// Happy path
test('should do X when Y', () => {
// Arrange
const input = ...;
// Act
const result = feature(input);
// Assert
expect(result).toBe(expected);
});
// Edge cases
test('should handle empty input', () => { ... });
test('should handle null input', () => { ... });
// Error cases
test('should throw error when invalid', () => { ... });
});
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.
- 5d ago First seen · 393 lines · 14 tokens per session scan A 5c57e6008fe4
tdd is a command published in the GitHub repository sumulige/sumulige-claude (2 stars, last pushed 6mo ago), licensed MIT. It adds 14 tokens to every session and 2,097 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
doctor
Run read-only health checks on the Kobiton automate plugin (CLI, credentials, profile).
bug
Reproduce then TDD-fix a ready-for-agent bug ticket in this checkout. Web bugs get a browser repro first.
work-flow-feature
Complete workflow for developing a new feature, from exploration to merge.
work-batch
Autonomous and sequential execution of user stories from a PRD file (JSON or Markdown).
work-quick
Quick workflow for trivial changes (1-3 files, < 50 lines, zero risk).
speckit.checklist
Generate a custom checklist for the current feature based on user requirements.