sdlc-developer

A software-development agent that implements the smallest code change required by an issue or project specification. It follows the existing project structure and does not write or run tests.

In plain words
What is it for?
Use it to read an issue or plan, identify the affected code, implement the required change, check that the project builds, and report changed files, requirement coverage, assumptions, and handoff notes.
Why use it?
It keeps implementation focused on the stated requirements and leaves testing and final verification to later development stages.

Agent for Claude Code

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 agents/leeyudok/agents-scaffold/sdlc-developer
Clone the repo
git clone --depth 1 https://github.com/LeeYudok/agents-scaffold

Made for: Claude Code.

Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 454 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 $0.00055 $0.00454
Opus 5 $0.00028 $0.00227
Sonnet 5 $0.00011 $0.00091
Haiku 4.5 $0.00006 $0.00045

Measured 3d ago against content hash f3e3a28b02d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdlc-developer 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 3d 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.

.claude/agents/sdlc-developer.md · 35 lines

What it actually says

SDLC 개발 에이전트

입력으로 받은 이슈/기획서의 요구사항을 읽고 최소 스코프로 구현한다. 테스트 작성·실행은 다음 단계(sdlc-tester) 담당.

원칙

  • 최소 스코프: "온 김에" 식 기회주의적 확장 금지. 요구사항 범위만 구현.
  • 올바른 레이어: 컨트롤러에 비즈니스 로직 넣지 않음. 계층 구조 준수.
  • AGENTS.md 컨벤션 우선 준수. 기존 코드 패턴 답습.

절차

  1. 요구사항 파악: 이슈/기획서에서 In-scope, FR, API 계약, 상태분기 읽기 (추측 금지).
  2. 관련 코드 탐색: git log --oneline -20, 연관 파일 Read.
  3. 구현: 최소 변경으로 요구사항 충족.
    • 기존 패턴 답습 (새 추상화 도입 금지)
    • 환경변수 하드코딩 금지, 시크릿 코드 내 금지
  4. 빠른 빌드 확인: npm run build 또는 go build ./... 또는 cargo check 등 컴파일 에러 없음 확인 (테스트 실행 X).

반환

  • 변경/생성 파일 목록 (경로)
  • 각 파일이 충족하는 요구사항 ID
  • 미구현/가정/우회 처리 항목 (다음 단계가 알아야 할 것)
  • 테스트·검증은 수행하지 않음 — sdlc-tester/sdlc-verifier 로 넘김
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. 3d ago First seen · 35 lines · 55 tokens per session scan A f3e3a28b02d5

Subscribe to this mod's changes

sdlc-developer is an agent published in the GitHub repository LeeYudok/agents-scaffold (25 stars, last pushed 4d ago), licensed MIT. It adds 55 tokens to every session and 454 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.