sdd

sdd is a command for coding agents from Ramsbaby/jarvis. It costs 51 tokens per session (1,511 once invoked), scanned A, original, MIT.

A guide to spec-driven development, a software process that writes and reviews requirements before implementation and acceptance testing. It organizes work from a task description through development, tests, and completion.

In plain words
What is it for?
Use it to start feature work, create task and development documents, define acceptance tests, and record technical and non-functional requirements.
Why use it?
It turns an unclear feature request into documented use cases, edge cases, constraints, architecture, and an implementation plan. This gives developers and reviewers a shared description of what should be built.

Command

Install

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.

agentmods
npx agentmods add commands/ramsbaby/jarvis/sdd
Clone the repo
git clone --depth 1 https://github.com/Ramsbaby/jarvis

Wrote 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.

agentmods badge for sdd

README.md
[![agentmods](https://agentmods.dev/badge/commands/ramsbaby/jarvis/sdd.svg)](https://agentmods.dev/commands/ramsbaby/jarvis/sdd)
Your own site
<a href="https://agentmods.dev/commands/ramsbaby/jarvis/sdd"><img src="https://agentmods.dev/badge/commands/ramsbaby/jarvis/sdd.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,511 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00051 $0.01511
Opus 5 $0.00026 $0.00756
Sonnet 5 $0.00010 $0.00302
Haiku 4.5 $0.00005 $0.00151

Measured 4d ago against content hash e7ddbb5f2903, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdd 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.

dotfiles/claude/commands/sdd.md · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

스펙 주도 개발 (SDD) 가이드

스펙 주도 개발(Spec-Driven Development) 프로세스를 시작합니다. 아래 단계에 따라 기능을 설계하고 구현을 진행해주세요.

SDD 워크플로우

스펙 작성 → 리뷰 → 구현 → 인수 테스트 → 완료

1단계: Task 문서 작성

프로젝트 루트 또는 docs/specs/ 디렉토리에 Task 문서를 작성합니다.

템플릿: task-[기능명].md

# Task: [기능명]

## 개요
- **목적**: (이 기능이 왜 필요한가)
- **담당**: (구현 담당자)
- **우선순위**: P0/P1/P2
- **예상 범위**: S/M/L

## 유스케이스

### UC-1: [주요 시나리오]
- **선행 조건**: ...
- **정상 흐름**:
  1. 사용자가 ...
  2. 시스템이 ...
  3. 결과: ...
- **후행 조건**: ...

### UC-2: [보조 시나리오]
- ...

## 엣지케이스

| ID | 상황 | 예상 동작 | 비고 |
|----|------|----------|------|
| E-1 | 입력값 없음 | 에러 메시지 반환 | |
| E-2 | 네트워크 단절 | 재시도 3회 후 실패 | |
| E-3 | 동시 접근 | 락 획득 실패 시 대기 | |

## 제약 조건
- 성능: ...
- 호환성: ...
- 보안: ...

## 비기능 요구사항
- 로깅: ...
- 모니터링: ...
- 알림: ...

2단계: Development 문서 작성

템플릿: dev-[기능명].md

# Development: [기능명]

## 아키텍처

### 시스템 구성도

(아래 Mermaid 다이어그램을 상황에 맞게 수정)

graph TD
    A[Client] --> B[API Gateway]
    B --> C[Service]
    C --> D[Database]
    C --> E[External API]

### 시퀀스 다이어그램

sequenceDiagram
    participant U as User
    participant S as Service
    participant D as DB
    U->>S: 요청
    S->>D: 조회
    D-->>S: 결과
    S-->>U: 응답

## 구현 계획

### 파일 변경 목록

| 파일 | 변경 유형 | 설명 |
|------|----------|------|
| `src/xxx.ts` | 신규 | 핵심 로직 |
| `src/yyy.ts` | 수정 | 인터페이스 추가 |
| `test/xxx.test.ts` | 신규 | 단위 테스트 |

### 데이터 흐름

1. 입력 → 검증 → 처리 → 저장 → 응답

### 의존성
- 기존 모듈: ...
- 외부 패키지: ...

## 주의사항
- 기존 코드와의 호환성
- 마이그레이션 필요 여부
- 롤백 계획

3단계: Feature 문서 (Single Source of Truth)

템플릿: feature-[기능명].md

# Feature: [기능명]

> Single Source of Truth - 이 문서가 해당 기능의 최종 스펙입니다.

## 상태
- [ ] 스펙 확정
- [ ] 구현 완료
- [ ] 테스트 통과
- [ ] 리뷰 완료
- [ ] 배포 완료

## API / 인터페이스

### 입력
- 파라미터: ...
- 타입: ...
- 필수/선택: ...

### 출력
- 정상 응답: ...
- 에러 응답: ...

### 사용 예시

(코드 또는 커맨드 예시)

## 설정

| 키 | 기본값 | 설명 |
|----|--------|------|
| `config.key` | `value` | 설명 |

## 관련 문서
- Task: `task-[기능명].md`
- Dev: `dev-[기능명].md`
- 테스트: `test/[기능명].test.*`

Read the full file on GitHub · 228 lines

Changes

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.

  1. 4d ago First seen · 228 lines · 51 tokens per session scan A e7ddbb5f2903

Subscribe to this mod's changes

sdd is a command published in the GitHub repository Ramsbaby/jarvis (16 stars, last pushed 12d ago), licensed MIT. It adds 51 tokens to every session and 1,511 once invoked, about $0.0003 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.