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 stage-classificationgit 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/stage-classification)<a href="https://agentmods.dev/skills/vivy-yi/finance-skills/stage-classification"><img src="https://agentmods.dev/badge/skills/vivy-yi/finance-skills/stage-classification/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/stage-classification"><img src="https://agentmods.dev/badge/skills/vivy-yi/finance-skills/stage-classification.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 | $0.00095 | $0.01482 |
| Opus 5 | $0.00048 | $0.00741 |
| Sonnet 5 | $0.00019 | $0.00296 |
| Haiku 4.5 | $0.00010 | $0.00148 |
Grade A, and why
stage-classification 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.
What it actually says
加载上下文
首次使用时: 读取 ../../CLAUDE.md 获取 Stage 转移标准/SICR 触发条件/转回规则。
/stage-classification — IFRS 9 三阶段分类
第一步:收集敞口信用信息
□ 对每个客户/交易收集:
□ 客户名称:[...]
□ 产品类型:[对公贷款/零售贷款/信用卡/债券投资/表外]
□ 账面余额:[X] 万元
□ 当前评级:[AAA/AA/A/BBB/BB/B/C/D]
□ 到期日:[YYYY-MM-DD]
□ 逾期天数:[X] 天(如有)
□ 抵押品:[无 / 有 — 类型/评估价值/折价率]
□ 初始确认日:[YYYY-MM-DD]
□ Watch List 状态:[是/否]
□ 数据完整性检查:
□ 评级缺失客户:[X] 个 — [✅ 已补全 / ⚠️ 须处理]
□ 抵押品信息缺失:[X] 个 — [✅ 已补全 / ⚠️ 须处理]
第二步:Stage 3 判断(先排除法)
□ Stage 3 客观减值证据(任一触发即 Stage 3):
□ 🔴 逾期 90 天以上
□ 债务人重大财务困难(审计/评级下调至 D 级)
□ 债务人获得贷款优惠(债务重组条款变更)
□ 债权人已处置抵押品
□ 债务人进入破产/清算程序
□ 其他客观证据:濒临违约的合同条款变更
□ Stage 3 判断结果:
□ Stage 3 敞口:[X] 万元([X] 个)
□ 主要触发原因:[...]
□ 是否已逾期但尚未识别:[✅ 是 / ⚠️ 否]
第三步:Stage 2 SICR 判断(排除 Stage 3 后)
□ SICR 触发条件(来自 CLAUDE.md):
□ 🔴 逾期 30-89 天
□ ⚠️ PD 评级下降 [X] 个等级(vs 初始确认日评级)
□ ⚠️ 进入 Watch List / Early Alert
□ ⚠️ 负面公开信息(法律诉讼/监管调查/舆情负面)
□ ⚠️ 宏观高风险行业暴露(参考 CLAUDE.md 行业清单)
□ PD 下降计算:
□ 初始评级:[X]
□ 当前评级:[X]
□ 评级下降:[X] 级 — [✅ 触发 SICR / ⚠️ 未触发]
□ Stage 2 判断结果:
□ Stage 2 敞口:[X] 万元([X] 个)
□ 主要触发原因:[...]
第四步:Stage 1 判断(其余敞口)
□ Stage 1 条件:
□ 无 Stage 3 条件
□ 无 Stage 2 SICR 条件
□ 初始确认即 Stage 1(除非后续触发 Stage 2/3)
□ 低信用风险豁免(来自 CLAUDE.md):
□ 适用条件:外部评级 [A-及以上] + 到期日 < [X] 个月
□ 是否适用豁免:[是/否]
□ 豁免依据:[评级文件]
□ Stage 1 判断结果:
□ Stage 1 敞口:[X] 万元([X] 个)
□ 豁免低信用风险:[X] 个([X] 万元)
第五步:Stage 转移记录与转回判断
□ 转移记录:
□ 期初 Stage 1 → 期末仍 Stage 1:[X] 万元
□ 期初 Stage 1 → 期末 Stage 2:[X] 万元([X] 个)
□ 期初 Stage 2 → 期末 Stage 3:[X] 万元([X] 个)
□ 期初 Stage 2 → 期末转回 Stage 1:[X] 万元([X] 个)
□ 转回判断(Stage 2 → Stage 1):
□ 转回条件:连续 [X] 期正常还款 + 当前评级处于投资级
□ 本期可转回客户:[X] 个 — [✅ 已转回 / ⚠️ 待验证]
□ 转移原因摘要:
□ [原因 1]:[X] 个客户 / [X] 万元
□ [原因 2]:[X] 个客户 / [X] 万元
输出格式
═══════════════════════════════════════
Stage 分类汇总表
评估截止日:[YYYY-MM-DD]
═══════════════════════════════════════
【Stage 分布】
| Stage | 敞口(万)| 客户数 | 占比 |
|--------|-----------|--------|--------|
| Stage 1 | [X] | [X] | [X]% |
| Stage 2 | [X] | [X] | [X]% |
| Stage 3 | [X] | [X] | [X]% |
| **合计** | **[X]** | **[X]** | **100%** |
【重大转移】
Stage 2 新迁入:
□ [客户名] — [X] 万元 — 触发原因 [逾期 30 天 / PD 下降 / Watch List]
□ ...
Stage 3 新迁入:
□ [客户名] — [X] 万元 — 触发原因 [...]
□ ...
【转回记录】
Stage 2 → Stage 1 转回:
□ [客户名] — [X] 万元 — 连续 [X] 期正常还款,已确认
□ ...
═══════════════════════════════════════
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 · 160 lines · 95 tokens per session scan A e40cc98637c4
stage-classification is a skill published in the GitHub repository vivy-yi/finance-skills (29 stars, last pushed 3mo ago), licensed MIT. It adds 95 tokens to every session and 1,482 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
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…