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 charlieviettq/awesome-agent-skill --skill biz-ermgit clone --depth 1 https://github.com/charlieviettq/awesome-agent-skillWrote 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/charlieviettq/awesome-agent-skill/biz-erm)<a href="https://agentmods.dev/skills/charlieviettq/awesome-agent-skill/biz-erm"><img src="https://agentmods.dev/badge/skills/charlieviettq/awesome-agent-skill/biz-erm/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/charlieviettq/awesome-agent-skill/biz-erm"><img src="https://agentmods.dev/badge/skills/charlieviettq/awesome-agent-skill/biz-erm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00251 | $0.05606 |
| Opus 5 | $0.00125 | $0.02803 |
| Sonnet 5 | $0.00050 | $0.01121 |
| Haiku 4.5 | $0.00025 | $0.00561 |
Grade A, and why
"biz-erm" 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.
This is a copy
89% identical to biz-erm — 9 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 425 lines — stays where its author put it; the contents beside it link to each section on GitHub.
企業風險管理框架(Enterprise Risk Management, ERM)
定位
為什麼 EMBA 要學 ERM 框架
台灣企業風險管理常見兩種極端:
- 過度工具化:只做財務風險 VaR、信用評分,但沒有治理結構
- 過度形式化:有風險委員會但只開會、沒風險胃納、沒 KRI 觸發機制
本 skill 拉回「框架+治理」層,整合 COSO ERM 2017 與 ISO 31000,讓學員能:
- 分層診斷(治理→文化→流程→工具)
- 設計可執行的風險治理結構
- 避免「有報表沒行動」的 ERM 陷阱
與相近 Asgard skill 的邊界
algo-risk-altman-z— 財務危機預測(單一量化工具)algo-risk-benford— 舞弊偵測數學algo-risk-credit— 信用風險評分algo-risk-var— 市場風險 VaRgrad-governance— 公司治理學理- 本 skill — 風險管理整合框架,協調治理結構、風險胃納、文化、工具四層
何時使用
觸發條件
- 公司要導入 ERM 或重整現有風險管理
- 金管會公司治理評鑑、ESG 風險揭露
- 設立風險管理委員會或風險長(CRO)職位
- 三道防線重建(尤其 IPO 前或金融業)
- 家族企業職業化、大型專案風險治理
- 企業危機後的「風險治理體檢」
不適用
- 單一風險量化計算 → Asgard
algo-risk-* - 危機事件的即時溝通 → Asgard
pr-crisis-communication、pr-crisis-response - ESG 永續揭露 → 本 repo
biz-net-zero-transition、Asgardgrad-sustainability - 合約法律風險 → Asgard
law-contract、law-gdpr-pdpa
IRON LAW — ERM 三條鐵律
IRON LAW 1:ERM 不是風險清單,是決策品質
ERM 的終極目的不是列出 500 條風險 tracking,
而是讓每個重大決策都「在可承受範圍內追求適當報酬」。
沒連結到策略與決策的 ERM = 高級稽核,不是 ERM。
IRON LAW 2:風險胃納(Risk Appetite)是董事會的事
「公司願意承擔多少風險以追求報酬」必須由董事會定義。
管理層只能在胃納範圍內決策。
沒有明文胃納書的 ERM = 盲人開車,風險文化無從建立。
IRON LAW 3:三道防線各司其職、互不取代
第一道(業務單位)擁有並管理風險;
第二道(風險/合規)監督方法、協調政策;
第三道(內部稽核)獨立驗證前兩道有效性。
最常見的失敗:第二道取代第一道(風險部變成風險保母)
或 第三道與第二道合署(失去獨立性)。
Rationalization Table — 當 Claude 想「本案例外」時,先自問
| 可能想 | 但 Iron Law 仍適用,因為 |
|---|---|
| 「列出 50 條風險熱圖就算 ERM 上線」 | 熱圖只是中間產物;必須連回策略與重大決策,否則只是「高級稽核」 |
| 「管理層可以先訂一版風險胃納,董事會日後追認」 | 胃納書是董事會責任不可下放;必須標註「未經董事會通過 = 無治理效力」 |
| 「小公司讓風管部兼任內稽以節省人力」 | 第二道取代第三道 = 失去獨立性;即使人力合一,彙報線必須分離(內稽向審計委員會) |
框架一:COSO ERM 2017(五要素、二十原則)
COSO 2017 版將 ERM 與策略、績效深度整合。五大要素:
┌─────────────────────────────────────────────┐
│ 要素 5:資訊、溝通與報告 │
│ Risk Information Governance │
├─────────────────────────────────────────────┤
│ 要素 4:檢視與修訂 │
│ Review and Revision │
├─────────────────────────────────────────────┤
│ 要素 3:績效(核心) │
│ Performance — 風險辨識、評估、選擇回應 │
├─────────────────────────────────────────────┤
│ 要素 2:策略與目標設定 │
│ Strategy & Objective-Setting │
├─────────────────────────────────────────────┤
│ 要素 1:治理與文化 │
│ Governance & Culture │
└─────────────────────────────────────────────┘
What ships with it
6 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 · 425 lines · 251 tokens per session scan A 24195b3f89f2
"biz-erm" is a skill published in the GitHub repository charlieviettq/awesome-agent-skill (26 stars, last pushed 1mo ago), licensed MIT. It adds 251 tokens to every session and 5,606 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to biz-erm, differing in 9 lines, and is treated as a copy.
Other skills, from other repositories
compliance-tracker
Track regulatory compliance for construction projects. Monitor permits, certifications, inspections, and regulatory requirements with automated alerts and reporting.
safety-inspection-checklist
Digital safety inspection checklists for construction sites. Generate, conduct, and track safety inspections with automated reporting and compliance monitoring.
delay-analysis
Analyze construction schedule delays for claims and recovery. Perform time impact analysis, identify delay causes, calculate damages, and document for disputes.
change-order-manager
Manage construction change orders from request to approval. Track costs, schedule impacts, and maintain audit trail for dispute prevention.
claims-documentation
Document construction claims for disputes and recovery. Compile evidence, calculate damages, track notice requirements, and prepare claim packages.
contract-clause-extractor
Extract and analyze key clauses from construction contracts. Identify payment terms, change order procedures, dispute resolution, warranties, and risk allocation provisions.