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 asgard-ai-platform/skills --skill biz-management-accountinggit clone --depth 1 https://github.com/asgard-ai-platform/skillsWrote 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/asgard-ai-platform/skills/biz-management-accounting)<a href="https://agentmods.dev/skills/asgard-ai-platform/skills/biz-management-accounting"><img src="https://agentmods.dev/badge/skills/asgard-ai-platform/skills/biz-management-accounting/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/asgard-ai-platform/skills/biz-management-accounting"><img src="https://agentmods.dev/badge/skills/asgard-ai-platform/skills/biz-management-accounting.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 | $0.00145 | $0.03385 |
| Opus 5 | $0.00072 | $0.01692 |
| Sonnet 5 | $0.00029 | $0.00677 |
| Haiku 4.5 | $0.00015 | $0.00338 |
Grade A, and why
biz-management-accounting 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.
How it starts
The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
管理會計工具箱（Management Accounting Toolkit）
定位
管理會計 ≠ 財務會計：財務會計對外（股東、監管、稅務），管理會計對內（經理人決策、績效評核）。本 skill 聚焦四大核心工具，協助 EMBA 學員完成「成本分析／差異檢討／內部計價／部門績效」類作業。
與 Asgard 既有 skill 的邊界：
biz-financial-ratios/biz-dupont/data-financial-analysis— 對外財報分析biz-breakeven— 單一產品損益平衡，不處理多產品成本分攤- 本 skill — 對內管理決策，處理製造費用分攤、預實差異、內部交易、績效評核
何時使用
觸發條件
- 個案中出現「這個產品到底賺不賺錢」、「成本分攤方法是否公平」
- 製造業個案需分析轉撥計價、責任中心
- 期末報告要評核部門績效或診斷成本結構
- 管理決策模擬（外包決策、產品組合、資源配置）
不適用
- 對外財報分析 → 用
biz-financial-ratios - 總體損益平衡 → 用
biz-breakeven - 資本預算決策 → 用
biz-dcf - 單位經濟學（獲客／留存） → 用
biz-unit-economics
IRON LAW — 管理會計的三條鐵律
IRON LAW 1：成本分攤方法決定決策品質
錯誤的分攤方法會讓賺錢產品看起來賠錢、賠錢產品看起來賺錢。
導入 ABC 前，永遠先問「現行成本系統是否扭曲了產品線決策？」
IRON LAW 2：沒有對照就沒有差異分析
「本月材料成本超支 300 萬」毫無意義。
必須拆解為：價格差異 × 用量差異，才能指出責任歸屬與改善方向。
IRON LAW 3：績效評核只能基於可控成本
用不可控成本評核經理人 = 系統失靈 + 士氣崩潰。
責任中心會計的前提是「可控性原則」，違反此原則的績效制度一定產生扭曲行為。
Rationalization Table — 當 Claude 想「本案例外」時，先自問
| 可能想 | 但 Iron Law 仍適用，因為 |
|---|---|
| 「個案只給傳統成本資料，就沿用吧」 | 即使資料有限，結論也必須標註「此成本系統可能扭曲產品決策」；沉默 = 背書 |
| 「本月差異小於 5%，不必拆」 | 差異分析的價值在診斷責任歸屬，不在金額；小差異也拆價格 × 用量 |
| 「老闆要用 BU 總利潤排名評比廠長，就照做」 | 若含不可控成本，結論必須加註「評核有失公允」；可控性原則不讓步 |
四大核心工具
工具一：ABC 作業成本制（Activity-Based Costing）
用於：多產品／多製程／高間接費用比例的企業，傳統分攤（以工時或機器小時）會扭曲成本。
五步法
- 辨識作業（Activities）：例如「機器設置」、「品質檢驗」、「訂單處理」
- 歸集成本池（Cost Pools）：把製造費用按作業歸集
- 選定成本動因（Cost Drivers）：設置次數、檢驗小時、訂單筆數
- 計算作業費率：成本池金額 ÷ 動因總量
- 分攤至產品：產品耗用的動因量 × 費率
關鍵判斷
- 若傳統分攤 vs. ABC 結果差異 > 15%，表示產品成本嚴重扭曲
- 小量客製化產品常被傳統系統「低估成本」，大量標準品則被「高估成本」
工具二：差異分析（Variance Analysis）
用於：預實差異檢討、成本控制、責任歸屬
三大差異類型
| 差異 | 公式 | 責任歸屬 |
|---|---|---|
| 材料價格差異 | (實際單價 − 標準單價) × 實際用量 | 採購部門 |
| 材料用量差異 | (實際用量 − 標準用量) × 標準單價 | 生產部門 |
| 人工效率差異 | (實際工時 − 標準工時) × 標準工資率 | 現場主管 |
| 製造費用能量差異 | (預計產能 − 實際產能) × 固定製造費用率 | 廠務／高層 |
| 製造費用支出差異 | 實際費用 − 預算費用 | 廠務 |
分析流程
- 取得標準成本卡與實際發生數
- 拆解每項差異
- 判讀：差異大小、有利／不利、責任部門
- 提出改善行動
工具三：轉撥計價（Transfer Pricing）
用於：集團內事業部／利潤中心間的內部交易
四種定價方法比較
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 220 lines · 145 tokens per session scan A 467400a92236
biz-management-accounting is a skill published in the GitHub repository asgard-ai-platform/skills (228 stars, last pushed 3mo ago), licensed MIT. It adds 145 tokens to every session and 3,385 once invoked, about $0.0007 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 2026-09-03.
Other skills, from other repositories
comps-analysis
Build comparable-company valuation workbooks in Excel.
stocks
Stock quotes, history, search, compare, crypto via Yahoo.
polymarket
Query Polymarket: markets, prices, orderbooks, history.
portfolio-review
A workflow for researching companies and managing a group of investments. It uses shared research rules and checks the date and data sources before reporting.
price-alert
Fire when the tracked token does something - new ATH, sharp 1h move, or operator-set target crossed. Silent on normal days.
unlock-monitor
Token unlock and vesting tracker - quantify supply pressure via absorption ratio, classify cliff vs linear, and deliver one-line market reads.