harness-factory: Skill for Claude Code

.claude/skills/development/SKILL.md

development is a skill for Claude Code from Kimyongari/harness-factory. It costs 46 tokens per session (2,108 once invoked), scanned A, original, MIT.

A set of rules for writing, changing, testing, and checking code in a project.

In plain words
What is it for?
It guides feature work, bug fixes, refactoring, tests, project planning, and safe work in separate Git workspaces.
Why use it?
It reduces mistakes caused by guessing, skipping nearby code, or declaring work finished before verification.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is Kimyongari/harness-factory's own configuration. It tells Claude Code how to work on harness-factory itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything harness-factory configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Kimyongari/harness-factory. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Kimyongari/harness-factory/main/.claude/skills/development/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Kimyongari/harness-factory

Made for: Claude Code.

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 development

README.md
[![agentmods](https://agentmods.dev/badge/skills/kimyongari/harness-factory/development.svg)](https://agentmods.dev/skills/kimyongari/harness-factory/development)
Your own site
<a href="https://agentmods.dev/skills/kimyongari/harness-factory/development"><img src="https://agentmods.dev/badge/skills/kimyongari/harness-factory/development.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,108 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.
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 $0.00046 $0.02108
Opus 5 $0.00023 $0.01054
Sonnet 5 $0.00009 $0.00422
Haiku 4.5 $0.00005 $0.00211

Measured 8d ago against content hash 82d8b8bc3ff0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

development 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.

.claude/skills/development/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

개발 규칙 (Development)

코드를 작성·수정·검증할 때 따른다. IMPORTANT: 시스템/사용자 메시지가 이 스킬보다 우선한다. 프로젝트 명령어는 AGENT.md의 표를, 절대 수정 금지 경로는 .env, secrets/, .venv/, node_modules/를 따른다.

0. 코드 짜기 전에 생각하기 (가장 싼 수정은 틀린 코드를 안 쓰는 것)

  • 가정을 말로 꺼낸다. 사용자가 의도를 다 안 적었을 때, 무엇을 가정했는지 한 줄로 명시한다.
  • 모호하면 묵묵히 고르지 말고 드러낸다. 두 해석이 다 맞는다면 둘 다 적고 묻는다. 잘못된 무언의 선택 한 번이 묻는 질문 한 번보다 비싸다.
  • 더 단순한 길이 있으면 push back 한다. 시키는 대로만 하지 말고, 같은 문제를 더 작게 푸는 방법이 있으면 제안한다.
  • 막히면 멈춘다. 무엇이 헷갈리는지 이름 붙여 묻는다. 혼란을 추측 코드로 덮지 않는다.
나쁨:  "유저 데이터 export 기능 추가해줘" → 곧장 csv/json/xml exporter 작성
좋음:  "API 엔드포인트, 페이지네이션 JSON, PII 제외 필드만이라 가정. 맞나? 'export'는 다른 세 가지 의미도 가능 — 함께 보여드릴까요?"

작업 흐름 (Read → Think → Plan → Edit → Verify)

  1. Read — 고치기 전에 인접 코드·패턴을 읽고 이 레포의 관례를 파악한다. 라이브러리는 매니페스트(import/패키지 파일)로 존재를 확인한다.
  2. Think — §0을 적용. 모호하면 코드 짜기 전에 먼저 묻는다.
  3. Plan — 3단계 이상이거나 모호하면 PLAN.md에 단계를 적되 단계마다 verify 줄을 함께 적는다(§목표 주도 실행 참고).
  4. Edit — 아래 규칙대로 최소 변경.
  5. Verify.scripts/verify.sh를 통과시킨다. 통과 전 "완료" 보고 금지.

브랜치 전략 (작업 공간)

작업 공간 전략: git worktree로 작업

  • 작업마다 별도 워크트리를 만들어 메인 체크아웃을 건드리지 않는다: git worktree add ../<프로젝트>-<작업명> -b <브랜치명>.
  • 해당 워크트리 디렉터리에서 작업·커밋하고, 끝나면 PR로 병합한 뒤 git worktree remove로 정리한다.
  • main 체크아웃에서 직접 커밋하지 않는다. (여러 작업을 병렬로 격리할 때 유용하다.)

범위 규율 (가장 흔한 실패 모드)

  • 요청한 것만 한다. 버그 수정에 주변 정리를 끼워넣지 않는다.
  • 비슷한 세 줄이 섣부른 추상화보다 낫다. 가상의 미래 요구를 위해 설계하지 않는다.
  • 기존 파일 수정 > 새 파일 생성. 반쪽 구현을 남기지 않는다.
  • 발견한 표류/죽은 코드는 고치지 말고 .docs/plans/tech-debt.md에 적고 넘어간다(범위 밖 청소는 별도 PR).

목표 주도 실행 (명령형을 검증 가능한 목표로 변환)

LLM은 검증 가능한 목표를 향해선 안정적으로 루프를 돈다. 모호한 명령형엔 표류한다. 모든 작업을 "X 한다 → Y 로 검증한다" 로 다시 적는다.

명령형 요청 검증 가능한 목표
"검증 로직 추가" 잘못된 입력에 대한 테스트를 먼저 작성 → 통과시키기
"버그 수정" 버그를 재현하는 테스트 작성 → 통과시키기
"X 리팩터링" 변경 전·후 기존 테스트가 모두 통과하는지 보장
"더 빠르게" 목표치 있는 벤치마크 작성 → 달성

여러 단계라면 PLAN.md에 단계마다 verify 줄을 함께 적는다:

1. 멱등키 검사 추가         → verify: 신규 단위 테스트 통과, 기존 결제 테스트도 그린
2. 웹훅 핸들러에 연결       → verify: 중복 웹훅 통합 테스트 통과
3. 24h 만료 처리            → verify: 타임트래블 테스트 통과, verify.sh 그린

Read the full file on GitHub · 118 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. 8d ago First seen · 118 lines · 46 tokens per session scan A 82d8b8bc3ff0

Subscribe to this mod's changes

development is a skill published in the GitHub repository Kimyongari/harness-factory (5 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 2,108 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

anti-slop-design

Category-aware design skill that builds distinctive, production-grade UIs. Brand-vs-product register, color strategy commitment, scene-based theme choice, palettes, font pairings, UX patterns, shadcn/token integration, empty-error-loading copy, secondary slop signals, multimodal design parity from mocks, and a…

madebyaris/advance-minimax-m3-cursor-rules · 78 tokens

3d-web-experiences

Build distinctive, performant, production-grade 3D on the web with Three.js, React Three Fiber, and WebGL. Use when the user asks to "build a 3D scene", "add a 3D hero/landing", "make a product viewer/configurator", mentions three.js / react-three-fiber / r3f / drei / webgl / shaders, or asks to make an existing 3D…

madebyaris/advance-minimax-m3-cursor-rules · 147 tokens

deep-research

Conducts multi-step deep research on any topic using iterative search, reflection, and synthesis. Use when the user asks to research, investigate, survey, compare, analyze, deep-dive, or explore a topic in depth. Covers web research, codebase analysis, documentation review, mixed-source investigation, and M3…

madebyaris/advance-minimax-m3-cursor-rules · 72 tokens

minimax-m3-long-context

How to use MiniMax M3's 1M-token MSA context productively: what to load vs. compress, when to retrieve vs. ingest, how to keep skills shallow in the always-on prompt and deep in skills, and how to plan retention across iterations. Load when the task might exceed 200K tokens, when the user asks to "keep all of this in…

madebyaris/advance-minimax-m3-cursor-rules · 101 tokens

minimax-m3-multimodal-input

How to use MiniMax M3's native multimodal input (image, video) for grounded decisions in coding work. Covers reading attached images/frames, treating them as ground truth for visual claims, screenshot diffing, design parity from mockups, and routing visual evidence through reports and PRs. Load when the user attaches…

madebyaris/advance-minimax-m3-cursor-rules · 121 tokens

minimax-multimodal-toolkit

MiniMax-native multimodal workflow for image, video, voice, music, and media-processing tasks. Use when the user asks to generate image/video/audio assets, wants MiniMax-specific media APIs, needs TTS or voice workflows, wants reproducible local media outputs, or needs FFmpeg-style processing around generated media.…

madebyaris/advance-minimax-m3-cursor-rules · 97 tokens