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 vivy-yi/finance-skills --skill process-compliance-auditgit clone --depth 1 https://github.com/vivy-yi/finance-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/vivy-yi/finance-skills/process-compliance-audit)<a href="https://agentmods.dev/skills/vivy-yi/finance-skills/process-compliance-audit"><img src="https://agentmods.dev/badge/skills/vivy-yi/finance-skills/process-compliance-audit/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/vivy-yi/finance-skills/process-compliance-audit"><img src="https://agentmods.dev/badge/skills/vivy-yi/finance-skills/process-compliance-audit.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 | $0.00072 | $0.01212 |
| Opus 5 | $0.00036 | $0.00606 |
| Sonnet 5 | $0.00014 | $0.00242 |
| Haiku 4.5 | $0.00007 | $0.00121 |
Grade A, and why
process-compliance-audit 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 7d 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
加载上下文
首次使用时: 读取 ../../CLAUDE.md 获取高风险领域定义/审计标准。
/process-compliance-audit — 流程合规性审计
适用流程模块
□ 采购与付款循环
□ 销售与收款循环
□ 资金管理循环
□ 存货管理循环
□ 固定资产管理循环
□ 人力资源与薪酬循环
□ 关联交易循环
□ 税务合规
第一步:了解业务流程与控制环境
□ 访谈关键人员:
□ 财务负责人:[姓名/岗位]
□ 业务负责人:[姓名/岗位]
□ 关键岗位人员:[姓名/岗位]
□ 业务流程描述:
□ 主要业务流程:[描述]
□ 关键控制节点:[...]
□ IT 系统支持:[系统名称]
□ 控制环境评估:
□ 管理层对内控的重视程度:[高/中/低]
□ 职责分离落实情况:[良好/部分落实/缺失]
□ 人员胜任能力:[良好/部分不足/不足]
第二步:穿行测试(Walk-through)
□ 选择测试交易:
□ 测试期间:[YYYY-QX]
□ 交易类型:[描述]
□ 样本数量:[X] 笔
□ 穿行路线追踪:
□ 交易触发 → 审批记录 → 系统录入 → 账务处理 → 期末结账
□ 发现:
□ 控制设计是否存在缺陷:[✅ 无 / ⚠️ 有设计缺陷]
□ 缺陷描述:[...]
□ 控制是否被一贯执行:[✅ 是 / ⚠️ 部分执行]
□ 异常执行描述:[...]
第三步:控制测试(Control Testing)
□ 抽样方法:[统计抽样/判断抽样]
□ 抽样数量:[X] 笔
□ 抽样期间:[YYYY-QX]
□ 测试结果:
□ 样本总数:[X] 笔
□ 通过:[X] 笔
□ 失败:[X] 笔
□ 测试通过率:[X]%
□ 失败样本详情:
□ [失败 1] — 缺陷类型 [设计/运行] — 描述 [...]
□ [失败 2] — 缺陷类型 [设计/运行] — 描述 [...]
第四步:审计发现编制
□ 发现数量:
□ 🔴 Major(重大缺陷):[X] 项
□ ⚠️ Moderate(中度缺陷):[X] 项
□ ✅ Low(轻度):[X] 项
□ 主要发现摘要:
□ [发现 1]
- 影响:可能导致 [重大错报/中等错报/效率损失]
- 涉及金额估算:[X] 万元(如适用)
- 整改责任人:[姓名/岗位]
- 建议整改措施:[...]
- 整改期限:[YYYY-MM-DD]
□ 管理层确认:[✅ 已确认事实 / ⚠️ 有异议 — 异议内容:...]
输出格式
═══════════════════════════════════════
流程合规性审计报告
被审计单位:[X]
审计流程:[X]
审计期间:[YYYY-QX]
═══════════════════════════════════════
【一、业务流程描述】
[描述关键业务流程和控制点]
【二、穿行测试结果】
□ 测试笔数:[X]
□ 控制设计缺陷:[✅ 无 / ⚠️ X 项]
□ 控制运行缺陷:[✅ 无 / ⚠️ X 项]
【三、控制测试结果】
□ 抽样方法:[统计/判断]
□ 抽样数量:[X] 笔
□ 通过率:[X]%
【四、审计发现】
🔴 Major(重大缺陷):
1. [发现描述] — 影响 [财务/合规/运营] — 金额 [X 万] — 责任人 [X] — 期限 [YYYY-MM-DD]
⚠️ Moderate(中度缺陷):
1. [发现描述] — 影响 [...] — 责任人 [X] — 期限 [YYYY-MM-DD]
✅ Low(轻度):
1. [改进建议]
【五、整体内控评价】
□ 整体评价:[✅ 良好 / ⚠️ 存在缺陷 / 🔴 重大缺陷]
□ 主要风险点:[...]
□ 建议优先整改项:[...]
═══════════════════════════════════════
审计人员:[姓名]
编制日期:[YYYY-MM-DD]
被审计单位确认:[✅ 已确认 / ⚠️ 有异议]
═══════════════════════════════════════
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.
- 7d ago First seen · 162 lines · 72 tokens per session scan A 5661664b2767
process-compliance-audit is a skill published in the GitHub repository vivy-yi/finance-skills (28 stars, last pushed 2mo ago), licensed MIT. It adds 72 tokens to every session and 1,212 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 2026-09-03.
Other skills, from other repositories
tdd
A Test-Driven Development guide. TDD means writing a failing test first, adding the smallest implementation that passes it, and then improving the code while keeping the tests passing.
debugging
A structured method for finding and fixing software bugs. It starts by writing a test that reproduces the failure, then investigates its underlying cause before making a small fix.
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment.
solo-build
This skill is self-contained — follow the task loop, TDD rules, and completion flow below instead of delegating to external build/execution skills (superpowers, etc.).
backend-development
Backend API design, database architecture, microservices patterns, and test-driven development. Use for designing APIs, database schemas, or backend system architecture.
tdd-workflow
Test-Driven Development workflow — red-green-refactor cycle.