中文说明 →

에이전트 시대의 오래된 코더의 전략: 코드를 읽지 말고 — 시험을 통과하게 만든다.

코딩 에이전트가 자신의 작업을 증명하는 능력을 갖추게 하는 기술입니다. 모든 줄을 읽는 대신, 에이전트는 코드를 여러 차례 검사하며 코딩 전에 테스트 계획을, 코딩 후에 증거 보고서를 건네줍니다. 당신은 코드를 검토하는 것이 아니라 그 두 문서를 검토합니다.

일반 마크다운이기 때문에, Claude Code, Codex CLI, Cursor, Aider, 혹은 본인의 에이전트 루프 등 지시를 따르는 모든 코딩 에이전트와 함께 작동합니다.

설치

old-coder 설치하기:

또는 수동으로 사용할 수도 있습니다:

• Claude Code — 스킬을 스킬 폴더에 복사한 후 /old-coder를 호출하거나 고확률 요청에 대해 트리거 설정:

• 기타 에이전트 — skills/old-coder/SKILL.md를 AGENTS.md, 규칙 파일, 시스템 프롬프트에 추가하고, references/ 디렉터리를 함께 유지하세요.

선택 동료: old-coder-api

이 저장소에는 집중된 HTTP/JSON API 설계 및 검토 기술도 포함되어 있습니다. 호환성, 권한, 멎등성, 페이지네이션, 속도 제한, 운영성 게이트를 원할 때 설치하세요:

두 스킬 설치:

Old Coder skill（老码农 skill）

中文说明 →

An old coder’s strategy for the agent era: don’t read the code — make it run the gauntlet.

A skill that makes coding agents prove their work. Instead of you reading every line, the agent pushes its code through a gauntlet of checks and hands you a test plan before coding and an evidence report after. You review those two documents, not the code.

It’s plain markdown, so it works with any coding agent that follows instructions: Claude Code, Codex CLI, Cursor, Aider, or your own agent loop.

Installation

Install old-coder:

npx skills add https://github.com/amazingang/old-coder --skill old-coder

Or manually:

• Claude Code — copy the skill into a skills folder, then invoke /old-coder or let it trigger on high-assurance requests:

  cp -r skills/old-coder ~/.claude/skills/
  # or copy it to /.claude/skills/
  

• Other agents — add skills/old-coder/SKILL.md to your AGENTS.md, rules file, or system prompt, and keep its references/ directory alongside it.

Optional companion: old-coder-api

This repository also includes a focused HTTP/JSON API design and review skill. Install it when you want compatibility, authorization, idempotency, pagination, rate-limit, and operability gates:

npx skills add https://github.com/amazingang/old-coder --skill old-coder-api

To install both skills:

npx skills add https://github.com/amazingang/old-coder --skill old-coder --skill old-coder-api

When both apply, old-coder owns workflow, approval, and evidence; old-coder-api owns the API contract, and its gate decisions become SPEC constraints and gauntlet checks.

The idea

From Uncle Bob (Robert C. Martin), on working with coding agents (original tweet):

My current strategy is to not read any of the code written by my agents. That’s the only way I can take advantage of their productivity. What I do instead is to surround the agents with extreme constraints. Unit tests, gherkin tests, QA procedures, quality metrics, mutation testing, test coverage, and a plethora of others. In the end, I have very high confidence in the code they produce because they’ve had to run the gauntlet of all of my constraints and tests.

If you’re not going to read the code, the things you do read have to carry the trust instead.

How it works

flowchart LR
    SPEC["📋 SPECagent writes a test plan,you approve it"]
    RED["🔴 REDwrite a test,watch it fail"]
    GREEN["🟢 GREENwrite code untilit passes"]
    REF["🧹 REFACTORclean up,tests untouched"]
    G["🛡️ GAUNTLETrun every check"]
    EV["📊 EVIDENCEyou read the report,not the code"]
    SPEC --> RED --> GREEN --> REF --> G --> EV