ddd

ddd is a skill for Claude Code, Codex from Insajin/autopus-adk. It costs 17 tokens per session (615 once invoked), scanned A, original, MIT.

A development method for improving existing code while preserving its current behavior. It follows an analyze, preserve, and improve cycle, using tests and small changes to reduce unintended effects.

In plain words
What is it for?
Use it to analyze callers, side effects, tests, edge cases, and history; add characterization tests; refactor in small steps; and replace old implementations gradually.
Why use it?
It helps developers understand what existing code and its callers rely on before changing it. Recording current behavior in tests makes gradual improvements safer, even when the old behavior is imperfect.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to analyze callers, side effects, tests, edge cases, and history; add characterization tests; refactor in small steps; and replace old implementations gradually.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/insajin/autopus-adk/ddd
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.

Any agent
npx skills add Insajin/autopus-adk --skill ddd
Clone the repo
git clone --depth 1 https://github.com/Insajin/autopus-adk

Made for: Claude Code, Codex.

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 ddd

README.md
[![agentmods](https://agentmods.dev/badge/skills/insajin/autopus-adk/ddd.svg)](https://agentmods.dev/skills/insajin/autopus-adk/ddd)
Your own site
<a href="https://agentmods.dev/skills/insajin/autopus-adk/ddd"><img src="https://agentmods.dev/badge/skills/insajin/autopus-adk/ddd.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 615 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00017 $0.00615
Opus 5 $0.00009 $0.00308
Sonnet 5 $0.00003 $0.00123
Haiku 4.5 $0.00002 $0.00061

Measured 8d ago against content hash 4fb164ed7df9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ddd 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 8d 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.

.omp/skills/ddd/SKILL.md · 80 lines

What it actually says

DDD (Disciplined Design Development) Skill

기존 코드의 동작을 분석하고 보존하면서 점진적으로 개선하는 방법론입니다.

ANALYZE-PRESERVE-IMPROVE 사이클

ANALYZE 단계: 기존 동작 분석

변경 전에 반드시 현재 동작을 완전히 이해합니다:

1. 코드 목적 파악 — 무엇을 하는 코드인가?
2. 호출자 파악 — 누가 이 코드를 사용하는가? (fan_in)
3. 사이드 이펙트 식별 — 어떤 부수 효과가 있는가?
4. 테스트 현황 파악 — 어떤 테스트가 존재하는가?
5. 경계 조건 파악 — 어떤 엣지 케이스가 있는가?

도구 사용:

  • git log --follow -p [file] — 변경 이력 확인
  • grep -r "[function_name]" — 호출자 검색
  • go test -run [test_pattern] -v — 기존 테스트 실행

PRESERVE 단계: 기존 동작 보존

기존 동작을 테스트로 고정합니다 (Characterization Tests):

// 특성 테스트: 현재 동작을 그대로 문서화
func TestLegacyBehavior_CharacterizationTest(t *testing.T) {
    // 이 테스트는 현재 동작을 문서화한다
    // 동작이 "올바른지" 여부와 관계없이 현재 상태를 기록
    result := legacyFunction(existingInput)
    assert.Equal(t, knownOutput, result)
}

금지 사항:

  • 테스트 없이 인터페이스 변경 금지
  • 기존 함수 시그니처 변경 금지 (새 함수 추가는 허용)
  • 사이드 이펙트 제거 전 의존 코드 확인 필수

IMPROVE 단계: 점진적 개선

작은 단계로 나누어 개선합니다:

1. 최대 변환 크기: small (50줄 미만)
2. 각 변환 후 테스트 실행
3. 기존 동작 유지 확인
4. 리팩토링과 기능 변경 분리

적용 패턴

Strangler Fig Pattern

기존 코드를 점진적으로 대체:

  1. 새 구현체 병행 운영
  2. 새 구현체로 트래픽 이전
  3. 구 구현체 제거

Branch by Abstraction

인터페이스로 추상화하여 교체:

  1. 인터페이스 추출
  2. 신규 구현체 작성
  3. 의존성 주입으로 교체

완료 기준

  • 기존 테스트 모두 통과
  • 특성 테스트 추가됨
  • 변경 전후 동작 동일
  • fan_in >= 3 함수에 @AX:ANCHOR 태그
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. 8d ago First seen · 80 lines · 17 tokens per session scan A 4fb164ed7df9

Subscribe to this mod's changes

ddd is a skill published in the GitHub repository Insajin/autopus-adk (110 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 615 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 2026-08-30.