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 Adelie-Squad/solosquad --skill xyz-hypothesisgit clone --depth 1 https://github.com/Adelie-Squad/solosquadWrote 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/adelie-squad/solosquad/xyz-hypothesis)<a href="https://agentmods.dev/skills/adelie-squad/solosquad/xyz-hypothesis"><img src="https://agentmods.dev/badge/skills/adelie-squad/solosquad/xyz-hypothesis/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/adelie-squad/solosquad/xyz-hypothesis"><img src="https://agentmods.dev/badge/skills/adelie-squad/solosquad/xyz-hypothesis.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 | $0.00083 | $0.00606 |
| Opus 5 | $0.00042 | $0.00303 |
| Sonnet 5 | $0.00017 | $0.00121 |
| Haiku 4.5 | $0.00008 | $0.00061 |
Grade A, and why
xyz-hypothesis 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 11d 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
XYZ Hypothesis
검증 가능한 가설 형식:
[X%] of [Y segment] will [Z behavior] within [T period], because [R rationale]. 합성 위치(v1.3.5): 가설 수립 서브워크플로의 종착 렌즈(신규 구축·개선 두 메인이 공유).
형식
hypothesis:
x_percent: "예: 80%"
y_segment: "예: 신규 org 를 추가하는 founder"
z_behavior: "예: 첫 messenger send 를 1회 시도 내 성공"
t_period: "예: org 추가 후 5분 이내"
r_rationale: "lazy-create 패턴 + post-add seed 가 wizard 와 동등한 보장 제공"
verification:
method: "instrumentation 으로 retry 횟수 카운트"
success_threshold: "first-try 성공률 ≥ 80%"
measurement_window: "구현 후 30일"
confidence: 75 # 0-100, RO-PNA Confidence Score
Anti-Sycophancy 강제 (입장 + 반증)
position: "lazy-create 도입 시 80% 첫시도 성공"
falsification:
- "first-try < 50% → 다른 root cause (예: discord API 권한)"
- "100% 인데 사용자 보고 지속 → metric 정의가 wrong proxy"
≥ 2 approaches 룰 (단일 가설 금지)
항상 최소 2개 가설(approach·pros·cons) 제시 후 recommended 명시(근거 포함).
V/U/V/F Assumption 분류
각 가설 핵심 가정을 Value / Usability / Viability / Feasibility 4영역으로 분류, 가장 위험한 가정을 표시.
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.
- 11d ago First seen · 57 lines · 83 tokens per session scan A 688202fcdb23
xyz-hypothesis is a skill published in the GitHub repository Adelie-Squad/solosquad (19 stars, last pushed 20d ago), licensed MIT. It adds 83 tokens to every session and 606 once invoked, about $0.0004 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
defining-and-exploring-problems
Teaches the discipline of correct problem definition and structured solution exploration before any evaluation begins. Covers the problem-solution firewall, root cause identification, the premortem, second-order thinking ('and then what?'), binary thinking traps, integrative Both-And options, and opportunity cost…
saas-launcher
Sıfırdan production-ready bir SaaS uygulaması kur. Ödeme, kimlik doğrulama, veritabanı, e-posta, landing page, SEO ve API güvenliği dahil tüm katmanları kapsar. Kullanıcı SaaS kurmak, web uygulaması başlatmak, AI aracı oluşturmak veya online ürün çıkarmak istediğinde bu skill'i kullan — "startup kur", "proje başlat"…
saas-payments
SaaS uygulaması için ödeme ve abonelik sistemi kur. Stripe veya Lemon Squeezy ile checkout, webhook, abonelik yönetimi, fiyatlandırma planları ve müşteri portalı yapılandır. Bu skill'i kullanıcı ödeme, abonelik, fiyatlandırma, Stripe, gelir, plan, subscription veya checkout ile ilgili bir şey istediğinde kullan. "Para…
saas-api-security
SaaS uygulaması için API güvenlik katmanı kur. Rate limiting, plan bazlı erişim kontrolü, input validation, hata yönetimi, CORS ve health check. Bu skill'i kullanıcı API güvenliği, rate limiting, yetkilendirme, input doğrulama, hata yönetimi veya API koruması ile ilgili bir şey istediğinde kullan. "API'yi koru", "rate…
saas-analytics
SaaS uygulaması için PostHog analytics ve ürün analizi kur. Event tracking, kullanıcı tanımlama, feature flag, session replay, funnel analizi ve gizlilik uyumlu yapılandırma. Bu skill'i kullanıcı analytics, PostHog, event tracking, kullanıcı davranışı, feature flag, A/B test, dönüşüm analizi veya metrik takibi ile…
saas-testing
SaaS uygulaması için test stratejisi kur. Vitest ile birim test, Playwright ile E2E test, API route testi, webhook mock, Stripe test modu ve CI entegrasyonu. Bu skill'i kullanıcı test, test yazma, E2E, birim test, Playwright, Vitest, coverage veya kalite güvencesi ile ilgili bir şey istediğinde kullan. "Test yaz"…