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 modu-ai/moai-cowork --skill finance-variance-analysisgit clone --depth 1 https://github.com/modu-ai/moai-coworkWrote 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/modu-ai/moai-cowork/finance-variance-analysis)<a href="https://agentmods.dev/skills/modu-ai/moai-cowork/finance-variance-analysis"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/finance-variance-analysis/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/modu-ai/moai-cowork/finance-variance-analysis"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/finance-variance-analysis.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 | $0.00087 | $0.02480 |
| Opus 5 | $0.00044 | $0.01240 |
| Sonnet 5 | $0.00017 | $0.00496 |
| Haiku 4.5 | $0.00009 | $0.00248 |
Grade A, and why
finance-variance-analysis 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 12d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
분산 분석 (Variance Analysis)
개요
예산(Budget) 대비 실적(Actual)의 차이를 체계적으로 분석하여 경영 의사결정에 필요한 인사이트를 제공한다. 매출 분산, 비용 분산, 이익 분산을 항목별로 분해하고, 차이의 원인(가격·수량·효율·환율 등)을 파악하여 개선 권고안을 도출한다.
면책 고지: 이 스킬은 AI 보조 분석이며 공인 회계사의 전문 자문을 대체하지 않습니다.
트리거 키워드
분산 분석, 예산 대비 실적, 실적 차이, 원가 분석, 재무 KPI, 수익성 분석, 비용 절감, 예실 분석, 예산 초과, 매출 미달
워크플로우
1단계: 분석 데이터 수집
사용자로부터 다음 데이터 요청:
- 분석 기간 (월/분기/반기/연간)
- 항목별 예산(Budget) vs 실적(Actual) 수치
- 전기 실적 (추세 분석용)
- 사업부/제품/지역별 세분화 여부
2단계: 전체 분산 요약
총 분산 = 실적 - 예산
- 유리한 분산 (Favorable, F): 수익은 예산 초과, 비용은 예산 미달
- 불리한 분산 (Unfavorable, U): 수익은 예산 미달, 비용은 예산 초과
분산 분석 요약표 (예시)
| 항목 | 예산 | 실적 | 분산 | 분산율 | 판정 |
|------|------|------|------|--------|------|
| 매출액 | 100억 | 95억 | -5억 | -5.0% | U |
| 매출원가 | 60억 | 58억 | -2억 | -3.3% | F |
| 매출총이익 | 40억 | 37억 | -3억 | -7.5% | U |
| 판관비 | 20억 | 22억 | +2억 | +10.0% | U |
| 영업이익 | 20억 | 15억 | -5억 | -25.0% | U |
3단계: 매출 분산 분해 (Revenue Variance)
매출 분산 = 가격 분산 + 수량 분산
-
가격 분산 (Price Variance) = (실제 단가 - 예산 단가) × 실제 판매량
- 원인: 할인 정책 변경, 경쟁 압력, 제품 믹스 변화
-
수량 분산 (Volume Variance) = (실제 판매량 - 예산 판매량) × 예산 단가
- 원인: 시장 수요 변화, 영업 역량, 마케팅 효과
특이요인 체크:
- 최저임금 인상 영향 (2026년: 10,320원/시간)
- 환율 변동 영향 (수출 비중이 있는 경우)
- 계절성 요인 (추석·설 등 명절 효과)
4단계: 비용 분산 분해 (Cost Variance)
인건비 분산 = 임률 분산 + 능률 분산
- 임률 분산 = (실제 임금률 - 예산 임금률) × 실제 근로시간
- 2026년 주의: 국민연금 0.5%p 인상분 예산 반영 여부 확인
- 능률 분산 = (실제 근로시간 - 예산 근로시간) × 예산 임금률
4대보험 비용 분산 체크 (2026년 변경사항):
| 항목 | 2025년 사업주 부담 | 2026년 사업주 부담 | 변동 |
|---|---|---|---|
| 국민연금 | 4.5% | 4.75% | +0.25%p |
| 건강보험 | 3.545% | 3.595% | +0.05%p |
| 장기요양 | 건보료의 12.81% | 건보료의 12.95% | +0.14%p |
제조원가 분산:
- 재료비 분산: 재료 가격 분산 + 재료 사용량 분산
- 제조간접비 분산: 예산 대비 고정비·변동비 분리 분석
5단계: KPI 추적 및 벤치마킹
재무 KPI 대시보드:
| KPI | 예산 | 실적 | 전기 | 업종 평균 |
|---|---|---|---|---|
| 매출총이익률 | ||||
| 영업이익률 | ||||
| EBITDA 마진 | ||||
| 인건비 비율 | ||||
| 판관비 비율 |
업종별 영업이익률 참고 (2025년 기준):
- IT 서비스: 10-20%
- 제조업 평균: 5-8%
- 유통업: 2-5%
- 서비스업: 8-15%
- 스타트업 (성장단계): 음수-5%
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.
- 12d ago First seen · 182 lines · 87 tokens per session scan A 8c42b0bb926f
finance-variance-analysis is a skill published in the GitHub repository modu-ai/moai-cowork (300 stars, last pushed 9d ago), licensed Apache-2.0. It adds 87 tokens to every session and 2,480 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
recipe-create-expense-tracker
Set up a Google Sheets spreadsheet for tracking expenses with headers and initial entries.
portfolio-review
Analyze your actual holdings -- allocation, concentration, sector and theme overlap, correlated-risk flags, and the questions worth asking yourself. Works from a broker CSV export or a pasted list. Analysis only, never buy/sell advice.
ticker-brief
One company on one page -- what the business actually does, how it makes money, recent results and guidance, valuation context, the honest bull and bear case, and the risks. Research support, not a recommendation. Use before buying, before earnings, or when a position needs a fresh look.
earnings-watch
Earnings-season prep for your holdings and watchlist -- report dates, what the market is actually watching per name, prior-quarter context, and a post-report debrief template. Preparation, not prediction. Use in the weeks around earnings season.
stocks
Stock quotes, history, search, compare, crypto via Yahoo.
management-deep-dive
A research workflow for evaluating a company’s managers and leaders. It treats buying shares as partly trusting the people who run the business.