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 reimbursement-reviewgit 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/reimbursement-review)<a href="https://agentmods.dev/skills/vivy-yi/finance-skills/reimbursement-review"><img src="https://agentmods.dev/badge/skills/vivy-yi/finance-skills/reimbursement-review/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/reimbursement-review"><img src="https://agentmods.dev/badge/skills/vivy-yi/finance-skills/reimbursement-review.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 | $0.00100 | $0.02272 |
| Opus 5 | $0.00050 | $0.01136 |
| Sonnet 5 | $0.00020 | $0.00454 |
| Haiku 4.5 | $0.00010 | $0.00227 |
Grade A, and why
reimbursement-review 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 — 258 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（公司信息/数据源/升级矩阵/审核维度）。
/reimbursement-review — 报销审核主技能
Examples
→ 示例：用户说"员工报销单据不齐全，缺少发票，帮我判断能不能特批"，系统应调用本技能，评估不齐全单据的特批可能性。
→ 示例：用户说"帮我们审一下这个月的员工报销，看看有没有异常模式"，系统应调用本技能，执行月度报销异常模式审查。
→ 示例：用户说"有个员工报销金额特别大，需要部门负责人和财务一起审吗"，系统应调用本技能，确认大额报销的多级审批要求。
审核前置条件
已完成的原子检查（须前置执行）：
1. invoice-verification — 发票验真（必选）
2. policy-compliance-check — 费用标准合规检查（必选）
3. triple-match-automation — 三单匹配（如为采购类费用则必选）
六项必检项
必检项一：发票合规性
检查内容：
- 发票真伪验真（通过 TAX 平台）
- 票面信息与报销内容一致
- 发票状态（正常/作废/红冲/失控）
输出： invoice-verification 的查验报告
必检项二：费用标准合规
检查内容：
- 对照 CLAUDE.md 中的费用标准配置
- 计算城市系数 × 职级系数 × 天数后的标准上限
- 比对实际报销金额是否超标准
输出： policy-compliance-check 的合规报告
必检项三：预算占用
检查内容：
- 从 [FK] 费控平台查询对应成本中心/项目的预算余额
- 确认预算余额 ≥ 本次报销金额
- 检查是否存在其他待报销金额（预算重复占用）
判断逻辑：
预算余额 ≥ 报销金额 → ✅ 预算充足
预算余额 < 报销金额，但余额 > 0 → ⚠️ 超支，流转特批
预算余额 < 0 → ❌ 驳回，提示须申请预算调整
必检项四：审批完整性
检查内容：
- 从 [OA] 读取本次报销关联的审批记录
- 确认已通过规定层级的审批流
- 检查审批节点是否完整（无跳审批/无代审批）
特殊情形：
紧急出差（无法事前申请）：
→ 要求员工事后补申请
→ 审核"事后补申请记录"是否存在
→ 如无 → ❌ 驳回，提示须先完成补申请
金额触发更高审批层级：
→ 核对本次报销金额是否触发了更高层级审批
→ 如应审未审 → ⚠️ 驳回，要求补充更高层级审批
必检项五：三单匹配（采购类费用）
检查内容： 仅对采购类费用执行（办公采购/设备采购/服务采购）
执行： triple-match-automation Skill
判断：
采购类 + 三单匹配通过 → ✅ 此项通过
采购类 + 三单不匹配 → ❌ 驳回
非采购类 → ✅ 跳过此检查
必检项六：期间归属
检查内容：
- 发票日期与报销提交日期的间隔
- 确认费用归属会计期间是否正确
判断逻辑：
报销提交距发票开具 ≤ 30 天 → ✅ 正常
报销提交距发票开具 30-90 天 → ⚠️ 超期提示，要求说明原因
报销提交距发票开具 > 90 天 → ❌ 驳回，提示超过报销时限
跨季度报销 → 🔴 升级财务专员，确认是否影响当期损益
综合结论生成
结论判定规则
通过（✅）：
全部必检项结论均为"通过"或"跳过（不适用）"
→ 输出：通过，可进入付款流程
→ 自动通知申请人 + 出纳
需补正（⚠️）：
至少一项必检项为"⚠️ 需补正"
且无任何"❌ 驳回"或"🔴 升级"
→ 输出：需补正，列出补正事项清单
→ 自动通知申请人补正内容
→ 补正完成后重新触发审核
驳回（❌）：
至少一项必检项为"❌ 驳回"
→ 输出：驳回，列出驳回原因
→ 通知申请人驳回原因 + 重新提交的路径
→ 记录本次驳回原因（统计用）
升级（🔴）：
至少一项必检项为"🔴 升级"
→ 不自行判断，流转至财务专员
→ 输出：升级说明 + 接收人
→ 自动通知财务专员
最终输出模板
═══════════════════════════════════════════════════════
费用报销审核报告
═══════════════════════════════════════════════════════
报销单号：[OA 单号]
申请人：[姓名] 部门：[部门] 职级：[职级]
费用类型：[差旅/招待/采购/办公/其他]
报销金额：[X,XXX.XX] 元
提交日期：[YYYY-MM-DD]
报销期间：[对应会计期间]
═══════════════════════════════════════════════════════
【必检项一：发票合规性】
发票代码：[代码] 发票号码：[号码]
查验结果：[✅ 一致 / ❌ 异常]
结论：[✅ 通过 / ❌ 驳回 / 🔴 升级]
【必检项二：费用标准合规】
住宿：[实际 X 元] vs 上限 [Y 元] → [✅ / ⚠️ / ❌]
餐饮：[实际 X 元] vs 上限 [Y 元] → [✅ / ⚠️ / ❌]
交通：[实际 X 元] vs 上限 [Y 元] → [✅ / ⚠️ / ❌]
结论：[✅ 通过 / ⚠️ 需补正 / ❌ 驳回 / 🔴 升级]
【必检项三：预算占用】
成本中心：[代码] 项目：[代码]
预算余额：[X,XXX.XX] 元 可用：[X,XXX.XX] 元
结论：[✅ 充足 / ⚠️ 超支 / ❌ 不足]
【必检项四：审批完整性】
审批流：[出差申请 → 部门负责人 → 财务]（共 X 级）
审批状态：全部通过（最后审批：[日期]）
结论：[✅ 完整 / ⚠️ 补签 / ❌ 缺失]
【必检项五：三单匹配】（仅采购类）
合同：[XXX 号] 金额：[X,XXX.XX] 元
发票金额：[X,XXX.XX] 元 差异率：[X.X]%
结论：[✅ 匹配 / ⚠️ 轻微差异 / ❌ 显著差异]
【必检项六：期间归属】
发票日期：[YYYY-MM-DD]
距报销日：[X] 天
结论：[✅ 正常 / ⚠️ 超期提示 / ❌ 超期驳回 / 🔴 跨期升级]
═══════════════════════════════════════════════════════
最终结论：[✅ 通过 / ⚠️ 需补正 / ❌ 驳回 / 🔴 升级]
═══════════════════════════════════════════════════════
[通过：]
→ 进入付款排队
→ 付款方式：[对公转账/企业账户直接扣款]
→ 预计付款日：[系统按付款日程自动排期]
[需补正：]
→ 补正事项：
1. [补正项一]
2. [补正项二]
→ 补正截止：[提交日期 + 7 个工作日]
→ 超期未补正：系统自动驳回
[驳回：]
→ 驳回原因：[列出所有驳回项]
→ 重新提交路径：[重新提交 / 换开发票 / 申请特批]
[升级：]
→ 升级原因：[具体升级项]
→ 接收人：[财务专员姓名/职位]
→ 升级时间：[自动记录]
═══════════════════════════════════════════════════════
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 · 258 lines · 100 tokens per session scan A 4ea5d80a7233
reimbursement-review is a skill published in the GitHub repository vivy-yi/finance-skills (29 stars, last pushed 3mo ago), licensed MIT. It adds 100 tokens to every session and 2,272 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 2026-08-30.
Other skills, from other repositories
wealth-structure
A framework for thinking about wealth through ownership, responsibility, leverage, and avoiding risks that could end your progress.
alpha-vantage
Access real-time and historical stock market data, forex rates, cryptocurrency prices, commodities, economic indicators, and 50+ technical indicators via the Alpha Vantage API. Use when fetching stock prices (OHLCV), company fundamentals (income statement, balance sheet, cash flow), earnings, options data, market…
hedgefundmonitor
Query the OFR (Office of Financial Research) Hedge Fund Monitor API for hedge fund data including SEC Form PF aggregated statistics, CFTC Traders in Financial Futures, FICC Sponsored Repo volumes, and FRB SCOOS dealer financing terms. Access time series data on hedge fund size, leverage, counterparties, liquidity…
edgartools
Python library for accessing, analyzing, and extracting data from SEC EDGAR filings. Use when working with SEC filings, financial statements (income statement, balance sheet, cash flow), XBRL financial data, insider trading (Form 4), institutional holdings (13F), company financials, annual/quarterly reports (10-K…
asc-ppp-pricing
Set territory-specific pricing for subscriptions and in-app purchases using current asc setup, pricing summary, price import, and price schedule commands. Use when adjusting prices by country or implementing localized PPP strategies.
fred-economic-data
Query FRED (Federal Reserve Economic Data) API for 800,000+ economic time series from 100+ sources. Access GDP, unemployment, inflation, interest rates, exchange rates, housing, and regional data. Use for macroeconomic analysis, financial research, policy studies, economic forecasting, and academic research requiring…