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 sox-control-designgit 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/sox-control-design)<a href="https://agentmods.dev/skills/vivy-yi/finance-skills/sox-control-design"><img src="https://agentmods.dev/badge/skills/vivy-yi/finance-skills/sox-control-design/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/sox-control-design"><img src="https://agentmods.dev/badge/skills/vivy-yi/finance-skills/sox-control-design.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 | $0.00091 | $0.01830 |
| Opus 5 | $0.00046 | $0.00915 |
| Sonnet 5 | $0.00018 | $0.00366 |
| Haiku 4.5 | $0.00009 | $0.00183 |
Grade A, and why
sox-control-design 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
加载上下文
首次使用时: 读取 ../../CLAUDE.md 获取场景级配置(SOX 控制框架/风险容忍度/证据标准)。
/sox-control-design — SOX 控制设计
Examples
→ 示例:用户说"新收入准则后,我们担心收入确认的内控有漏洞,需要重新审视",系统应调用本技能,识别风险点并设计新的控制。
→ 示例:用户说"IT 一般性控制之前没怎么管,SOX 外审提了意见,帮我设计一套",系统应调用本技能,按 ITGC 框架设计控制。
→ 示例:用户说"准备 IPO 前需要建立完整的内控体系,从哪里开始",系统应调用本技能,按 IPO 内控要求设计完整控制框架。
第一步:流程梳理与风险识别
流程描述:
□ 业务流程:[名称]
□ 涉及部门:[部门列表]
□ 流程起始:[触发事件]
□ 流程终点:[输出结果]
□ IT 系统支撑:[系统列表]
风险识别(梳理可能导致财务报告错报的环节):
□ 风险类型:
→ 完整性风险:应记录未记录(如收入未开票)
→ 准确性风险:记录金额错误(如价格输入错误)
→ 存在性风险:资产/负债不存在(如虚假采购)
→ 截止风险:记录期间错误(如跨期确认收入)
→ 分类风险:科目分类错误(如费用误归类)
→ 权利义务风险:交易无商业实质
□ 已识别风险:
| # | 风险描述 | 风险类型 | 影响科目 | 风险等级 |
|---|---------|---------|---------|---------|
| 1 | [描述] | [类型] | [科目] | [高/中/低] |
| 2 | [描述] | [类型] | [科目] | [高/中/低] |
□ 重大缺陷风险(如有):
→ 风险 [描述] — 是否为重大缺陷:[是/否]
第二步:控制点设计
预防性控制 vs 检查性控制:
□ 预防性控制(在错报发生前阻止):
→ 职责分离(SOD):如审批与执行分离
→ 访问控制:系统权限限制
→ 审批控制:多级审批流程
→ 验证核对:系统自动校验
□ 检查性控制(在错报发生后发现):
→ 对账:银行对账、账龄分析
→ 复核:管理层复核
→ 调节:科目调节
→ 盘点:实物盘点
控制点设计(为每个已识别风险设计控制):
| # | 对应风险 | 控制类型 | 控制描述 | 控制频率 | 责任人 |
|---|---------|---------|---------|---------|--------|
| 1 | [风险1] | [预防/检查] | [描述] | [实时/每日/月] | [岗位] |
| 2 | [风险2] | [预防/检查] | [描述] | [实时/每日/月] | [岗位] |
第三步:控制活动详细设计
控制活动规格:
□ 控制编号:[流程]-[序号]
□ 控制名称:[描述]
□ 控制类型:[预防性/检查性]
□ 控制频率:[实时/每日/每周/每月/每季度/每年]
□ 控制执行步骤:
1. [执行动作]
2. [执行动作]
3. [执行动作]
□ 自动化 vs 人工:
→ [人工控制/系统自动控制/混合]
→ 自动化控制依赖IT一般控制:[是/否]
□ 依赖的前置控制:
→ 控制 [编号] — [控制名称]
第四步:证据要求定义
控制证据清单:
□ 证据类型:
→ 纸质文档:[描述]
→ 电子记录:[系统名 + 查询路径]
→ 系统截图:[字段/报告名称]
→ 审批记录:[系统名/邮件/纸质]
□ 证据完整性要求:
→ 证据须包含:[日期/金额/执行人/复核人] 等字段
→ 异常情况处理:[描述,如签字/备注]
□ 证据保存要求:
→ 保存期限:[X] 年
→ 保存位置:[系统/档案室]
→ 格式要求:[纸质/电子/两者都要]
证据与控制的映射:
| 控制编号 | 控制名称 | 证据类型 | 保存位置 | 保存期限 |
|---------|---------|---------|---------|---------|
| [C-01] | [名称] | [类型] | [位置] | [X]年 |
第五步:生成控制设计文档
═══════════════════════════════════════
SOX 控制设计文档
流程:[业务流程名称]
设计日期:[YYYY-MM-DD]
设计师:[姓名]
═══════════════════════════════════════
【流程概览】
□ 流程名称:[名称]
□ 涉及系统:[系统列表]
□ 控制数量:[X] 个(预防性 [X] / 检查性 [X])
【风险-控制映射】
| 风险 | 风险等级 | 控制编号 | 控制名称 | 控制类型 |
|------|---------|---------|---------|---------|
| [风险1] | [高] | [C-01] | [名称] | [预防] |
| [风险2] | [中] | [C-02] | [名称] | [检查] |
【控制明细】
控制编号:[C-01]
控制名称:[名称]
控制类型:[预防性] | 控制频率:[每日]
控制步骤:
1. [步骤1]
2. [步骤2]
证据要求:
□ 类型:[纸质/电子]
□ 包含字段:[列表]
□ 保存期限:[X] 年
IT一般控制依赖:[✅ 是/否]
【职责分离矩阵】
□ 不相容职责:[审批] vs [执行] — 责任人 [A] vs [B]
□ SOD 合规检查:[✅ 通过 / ⚠️ 需关注]
═══════════════════════════════════════
置信度:[✅ 高 / ⚠️ 中 / 🔴 低]
设计状态:[✅ 可执行 / ⏳ 待IT确认 / 🔴 存重大缺陷]
═══════════════════════════════════════
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 · 206 lines · 91 tokens per session scan A a0a9b1b93aa5
sox-control-design is a skill published in the GitHub repository vivy-yi/finance-skills (29 stars, last pushed 3mo ago), licensed MIT. It adds 91 tokens to every session and 1,830 once invoked, about $0.0005 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
iso-13485-certification
Comprehensive toolkit for preparing ISO 13485 certification documentation for medical device Quality Management Systems. Use when users need help with ISO 13485 QMS documentation, including (1) conducting gap analysis of existing documentation, (2) creating Quality Manuals, (3) developing required procedures and work…
fda-database
Query openFDA API for drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII), for FDA regulatory data analysis and safety research.
see-invisibility
In D&D, See Invisibility lets you see creatures and objects that have been made invisible. The real-world version is revealing deliberate obscurity: finding the hidden costs in a pricing page, uncovering the actual terms buried in a EULA, identifying the obfuscated tracking in a codebase, or surfacing the real…
dietary-check
Audit a menu for allergen labelling, vegan and halal coverage, and common dietary requirements.
patentforge-provisional
Use this skill when the user wants to turn an invention idea into a structured invention disclosure, prior art search strategy, claim candidates, and provisional patent draft package. This skill is for patent drafting assistance only and must not provide legal advice or guarantee patentability.
healthcare-marketing-compliance
Skill "healthcare-marketing-compliance" from aimerdoux/wavex-os, covering healthcare marketing compliance specialist, your identity & memory, core mission, medical advertising compliance and pharmaceutical marketing standards.