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/ggombee/code-forge/startup-validatornpx skills add ggombee/code-forge --skill startup-validatorgit clone --depth 1 https://github.com/ggombee/code-forgeWhat 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 | $0.00052 | $0.01706 |
| Opus 5 | $0.00026 | $0.00853 |
| Sonnet 5 | $0.00010 | $0.00341 |
| Haiku 4.5 | $0.00005 | $0.00171 |
Grade A, and why
startup-validator 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Startup Validator Skill
검증된 프레임워크로 스타트업 아이디어를 평가 (낙관이 아닌 데이터 기반)
사용 시점
| 상황 | 예시 |
|---|---|
| 아이디어 검증 | 새 스타트업 컨셉 평가 |
| 펀딩 전 | 피칭 전 약점 파악 |
| 피봇 결정 | 현 방향 vs 전환 |
| 경쟁 리뷰 | 경쟁사 대비 포지션 |
| PMF 체크 | Product-Market Fit 준비도 |
사용: /startup-validator [아이디어]
검증 프레임워크
1. Peter Thiel 7 Questions (Zero to One)
| # | 질문 | 평가 기준 | 배점 |
|---|---|---|---|
| 1 | 10배 나은 기술을 만들 수 있는가? | 파괴적 vs 점진적 | 15 |
| 2 | 지금이 적절한 시점인가? | 시장 성숙도, 규제, 기술 준비 | 10 |
| 3 | 작은 시장에서 높은 독점 점유율로 시작하는가? | 니치 집중 vs 광범위 확산 | 15 |
| 4 | 적합한 팀이 있는가? | Founder-market fit | 10 |
| 5 | 유통 방법이 있는가? | 채널, GTM 전략 | 15 |
| 6 | 10-20년 방어 가능한가? | Moat 내구성 | 15 |
| 7 | 비자명한 비밀을 발견했는가? | 고유한 인사이트 | 20 |
2. YC PMF Indicators (Michael Seibel)
| 지표 | 설명 |
|---|---|
| 수요 압력 | 수요/사용이 공급 능력을 초과 |
| 유기적 성장 | 40-60% 입소문 |
| 지원 과부하 | 고객 요청 감당 어려움 |
| 다운타임 반응 | 서비스 중단 시 사용자 강한 반응 |
| 반복 사용 | 핵심 지표 반복 행동 패턴 |
Pre-PMF 체크:
- 이것은 "머리에 불 붙은" 문제인가?
- 사용자가 소규모 팀의 거친 v1도 채택할 것인가?
- 고객이 지불하고 있는가 (또는 명확히 지불 의향)?
3. The Mom Test (Rob Fitzpatrick)
| 규칙 | 좋은 질문 | 나쁜 질문 |
|---|---|---|
| 고객 삶 초점 | "지난번에 어떻게 해결했나요?" | "우리 제품 쓰실 건가요?" |
| 과거 행동 | "마지막으로 X한 게 언제?" | "보통 얼마나 자주 X하세요?" |
| 듣기 > 말하기 | 침묵과 후속 질문 | 긴 제품 피칭 |
거부할 나쁜 데이터: 빈 칭찬, 가정법 ("쓸 것 같아요"), 커밋 없는 기능 위시리스트
4. JTBD Forces of Progress
변화 촉진:
PUSH: 현 상황의 고통
PULL: 새 솔루션의 매력
변화 저항:
HABIT: 현 행동의 관성
ANXIETY: 전환 불안
전환 신호: Push + Pull > Habit + Anxiety
5. Lean Canvas Critical Checks
| 블록 | 검증 질문 | 위험도 |
|---|---|---|
| Problem | 상위 3개 문제가 실재하는가? | High |
| Customer Segments | 얼리어답터가 명확한가? | High |
| UVP | 차별점을 한 문장으로 설명 가능한가? | High |
| Solution | MVP 범위로 검증 가능한가? | Medium |
| Channels | 실용적 획득 경로가 있는가? | Medium |
| Revenue | 사용자가 지불할 것인가? | High |
| Cost Structure | 유닛 이코노믹스가 성립하는가? | Medium |
| Key Metrics | 핵심 지표 1개가 정의되었는가? | Medium |
| Unfair Advantage | 복사하기 어려운 것이 있는가? | High |
채점 체계
총점 (100점)
| 영역 | 배점 | 규칙 |
|---|---|---|
| Thiel 7 Questions | 100 | 위 표 기준 |
| PMF 보너스 | +10 | 3개+ PMF 체크 통과 시 |
| 치명적 약점 페널티 | -10/개 | 미해결 치명적 약점당 |
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.
- 2d ago First seen · 175 lines · 52 tokens per session scan A 79eee6fc8213
startup-validator is a skill published in the GitHub repository ggombee/code-forge (13 stars, last pushed 2mo ago), licensed MIT. It adds 52 tokens to every session and 1,706 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
credit-analysis
固收与信用分析：信用债评级、利差分析、违约风险评估、城投债研究、可转债定价与策略。.
correlation-regime
Correlation-regime detection and crisis attribution — edge-density regime states with hysteresis, causal (no look-ahead) smoothing, regime-aware exposure context, first-mover crisis attribution with honest NAME / MACRO / AMBIGUOUS / ABSTAIN verdicts, and a correlation-rewiring leaderboard that catches slow bleed-outs.
behavioral-finance
Behavioral finance applications: theories of overreaction and underreaction, behavioral explanations for momentum and reversal, investor sentiment cycles, cognitive-bias checklists, and debiasing quantitative strategies.
deep-company-series
Write a publication-grade 8-part deep-dive series on a single company (120k words total): cognitive reset / moat / profit engine / hidden assets / era variable (e.g. AI) / financials Buffett-style / management / valuation+redlines. The core IP is NOT writing but REVISING — a strict fact-check checklist catches…
earnings-revision
Earnings estimate revisions, guidance analysis, and post-earnings drift (PEAD) — track analyst consensus changes, earnings surprise patterns, and management guidance shifts for US/HK equities.
performance-attribution
Performance attribution analysis — Brinson sector/stock-selection attribution, factor alpha/beta decomposition, market-timing evaluation, and benchmark comparison framework.