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 skills add LeeYudok/agents-scaffold --skill search-firstgit clone --depth 1 https://github.com/LeeYudok/agents-scaffoldWrote 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/leeyudok/agents-scaffold/search-first)<a href="https://agentmods.dev/skills/leeyudok/agents-scaffold/search-first"><img src="https://agentmods.dev/badge/skills/leeyudok/agents-scaffold/search-first/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/leeyudok/agents-scaffold/search-first"><img src="https://agentmods.dev/badge/skills/leeyudok/agents-scaffold/search-first.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00117 | $0.00922 |
| Opus 5 | $0.00059 | $0.00461 |
| Sonnet 5 | $0.00023 | $0.00184 |
| Haiku 4.5 | $0.00012 | $0.00092 |
Grade A, and why
search-first 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 9d 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
search-first — 짜기 전에 찾는다
바퀴 재발명 방지 워크플로. 커스텀 코드는 검색이 빈손일 때의 마지막 선택지다.
발동 시점
- 기존 솔루션이 있을 법한 새 기능/유틸/헬퍼를 만들려는 순간
- 의존성·통합(외부 API, 파서, 클라이언트 등) 추가 직전
- "X 기능 추가해줘" 요청을 받고 바로 코드를 쓰려는 순간
검색 순서 (안쪽 → 바깥쪽)
| 순서 | 채널 | 방법 |
|---|---|---|
| 1 | 이 레포 안 | rg 로 관련 모듈/테스트 스윕 — 이미 있는데 못 본 것일 수 있음 |
| 2 | 사내 미러 | <your-git-host>/mirrors/ 그룹 먼저 (OSS agents/skills/아이콘 등 미러). 외부 원본 직접 참조 대신 미러로 들여와서 사용. 미러 그룹이 없으면 건너뜀 |
| 3 | 패키지 레지스트리 | npm / PyPI / crates.io 등 프로젝트 스택에 맞는 곳 |
| 4 | MCP / 스킬 | 이미 연결된 MCP 서버가 그 기능을 제공하는지, .claude/skills/ 에 같은 스킬이 있는지 |
| 5 | GitHub / 웹 | 유지보수되는 OSS 구현체·템플릿 검색. 채택 시 mirrors 로 포크해서 사용 |
채널이 사용 불가(오프라인, 인증 없음 등)면 조용히 건너뛰지 말고 어느 채널을 못 봤는지 명시한다.
평가 → 결정
후보는 기능 적합도 / 유지보수 상태(최근 커밋·이슈 응답) / 라이선스 / 의존성 무게로 평가.
| 신호 | 결정 |
|---|---|
| 정확히 맞음 + 관리 잘됨 + MIT/Apache | 채택 — 설치해서 그대로 사용 |
| 부분 일치 + 좋은 기반 | 확장 — 설치 + 얇은 래퍼 |
| 약한 후보 여러 개 | 조합 — 작은 패키지 2~3개 결합 |
| 쓸 만한 게 없음 | 직접 구현 — 단, 검색에서 본 설계를 참고해서 |
비trivial 기능이면 서브에이전트로
Agent(subagent_type="general-purpose", model="sonnet", prompt="
다음 기능의 기존 솔루션 조사: [설명]
언어/프레임워크: [스택], 제약: [있으면]
검색: 레포 내부 → 사내 미러(<your-git-host>/mirrors) → npm/PyPI → MCP → GitHub
리턴: 후보 비교표 + 채택/확장/직접구현 권고
")
안티패턴
- 코드 직행: 검색 없이 유틸부터 작성
- 미러 무시: GitHub 원본을 바로 참조 (내부 미러로 들여온 뒤 사용이 원칙)
- 조용한 스킵: 검색 채널이 죽어 있었는데 "없음"으로 보고
- 과도한 래핑: 라이브러리를 두껍게 감싸 장점을 죽임
- 의존성 비대: 작은 기능 하나에 거대 패키지 도입
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.
- 9d ago First seen · 58 lines · 0 tokens per session scan A 284e9a4417e6
search-first is a skill published in the GitHub repository LeeYudok/agents-scaffold (25 stars, last pushed 10d ago), licensed MIT. It adds 117 tokens to every session and 922 once invoked, about $0.0006 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
memstack-automation-n8n-workflow-builder
Use this skill when the user says 'n8n workflow', 'build a workflow', 'automation workflow', 'connect services', or needs visual workflow design with node mapping, data transformations, and error handling for n8n. Do NOT use for standalone webhook endpoints or cron jobs.
memstack-automation-cron-scheduler
Use this skill when the user says 'cron job', 'scheduled task', 'run every', 'cron expression', 'recurring job', or needs production-grade scheduled jobs with overlap prevention, monitoring, and structured logging. Do NOT use for n8n workflows or event-driven webhooks.
rtk-optimizer
Wrap high-verbosity shell commands with RTK to reduce token consumption. Use when running git log, git diff, cargo test, pytest, or other verbose CLI output that wastes context window tokens.
session-save
Save the current session state (decisions, modified files, current status, and next steps) to a handoff file for later resume.
handoff-create
Generate a structured handoff document from the current session. Captures scope, relevant files with line numbers, key discoveries, work completed, current status, next steps, and code snippets. Use before ending a session or handing work to another agent.
handoff-update
Update an existing handoff document with current session progress. Applies section-specific merge rules: append-only for Work Done (never deletes history), replace for Status and Next Steps, merge for Files and Discoveries. Falls back to creating a new handoff if no source file is found.