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.
npx agentmods add skills/jh941213/codex-lattice/simplifynpx skills add jh941213/codex-lattice --skill simplifygit clone --depth 1 https://github.com/jh941213/codex-latticeWrote 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.
[](https://agentmods.dev/skills/jh941213/codex-lattice/simplify)<a href="https://agentmods.dev/skills/jh941213/codex-lattice/simplify"><img src="https://agentmods.dev/badge/skills/jh941213/codex-lattice/simplify.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00070 | $0.00890 |
| Opus 5 | $0.00035 | $0.00445 |
| Sonnet 5 | $0.00014 | $0.00178 |
| Haiku 4.5 | $0.00007 | $0.00089 |
Grade A, and why
simplify scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
코드 단순화
최근 변경된 코드를 리뷰하고 단순화합니다.
Step 1: 변경 범위 파악
git diff --name-only HEAD~1 # 최근 변경 파일 확인
Step 2: 리팩토링 패턴 적용
불필요한 추상화 제거
// BEFORE: 한 번만 쓰이는 헬퍼
function formatUserName(user: User) { return `${user.first} ${user.last}`; }
const name = formatUserName(user);
// AFTER: 인라인
const name = `${user.first} ${user.last}`;
조건문 단순화
// BEFORE: 깊은 중첩
if (user) {
if (user.isActive) {
if (user.hasPermission) {
doThing();
}
}
}
// AFTER: 얼리 리턴
if (!user?.isActive || !user.hasPermission) return;
doThing();
중복 제거
// BEFORE: 반복 패턴
const users = data.filter(d => d.type === 'user').map(d => d.name);
const admins = data.filter(d => d.type === 'admin').map(d => d.name);
// AFTER: 3회 이상 반복될 때만 추출
const namesByType = (type: string) => data.filter(d => d.type === type).map(d => d.name);
주의: 2회 반복은 추출하지 않음. 3회부터 고려.
Step 2.5: 중복 코드 탐지
# jscpd — copy-paste 감지 (3줄 이상 중복)
npx jscpd src/ --min-lines 3 --reporters console 2>/dev/null | head -30
# ast-grep — 구조적 패턴 탐지
sg --pattern 'console.log($$$)' --lang ts 2>/dev/null | head -10
Step 3: 검증
수정 후 반드시 확인:
npm run typecheck || npx tsc --noEmit # 타입 안전
npm test # 테스트 통과
체크리스트
- 함수 50줄 이하
- 파일 800줄 이하
- 중첩 4단계 이하
- 매직 넘버 → 상수
- 명확한 변수명
- console.log 제거
- 사용하지 않는 import 제거
- any 타입 제거
절대 단순화하지 않을 것 (NEVER)
- NEVER 에러 핸들링 제거 — try/catch, 유효성 검사는 의도적 코드
- NEVER 생성된/벤더 파일 수정 — node_modules, generated, vendor 디렉토리
- NEVER 설정 파일 단순화 — tsconfig, eslint, webpack 등은 건드리지 않음
- NEVER 관련 없는 함수 병합 — 비슷해 보여도 도메인이 다르면 분리 유지
- NEVER 테스트 코드 단순화 — 테스트의 명시성은 의도적. DRY 적용 금지
- NEVER 타입 정의 제거 — 중복처럼 보여도 타입 안전성 유지
범위 결정
- 사용자가 특정 파일 지정 시 → 해당 파일만
- 지정 없으면 →
git diff --name-only HEAD~1(최근 커밋 변경 파일) - 변경 범위 밖 코드는 절대 수정하지 않음
원칙
- 동작은 변경하지 않음 (리팩토링만)
- 3줄 비슷한 코드 > 조기 추상화
- 과도한 최적화 지양
- 수정 전
git stash또는 현재 상태 확인 → 수정 후 검증 → 실패 시 원복
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.
- 4d ago First seen · 101 lines · 70 tokens per session scan A 00f8005673d1
simplify is a skill published in the GitHub repository jh941213/codex-lattice (19 stars, last pushed 3mo ago), licensed MIT. It adds 70 tokens to every session and 890 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…