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 agentmods add agents/howard-jerry/quant-agent-skills/valuation-agentgit clone --depth 1 https://github.com/Howard-Jerry/quant-agent-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/agents/howard-jerry/quant-agent-skills/valuation-agent)<a href="https://agentmods.dev/agents/howard-jerry/quant-agent-skills/valuation-agent"><img src="https://agentmods.dev/badge/agents/howard-jerry/quant-agent-skills/valuation-agent.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01466 |
| Opus 5 | $0.00000 | $0.00733 |
| Sonnet 5 | $0.00000 | $0.00293 |
| Haiku 4.5 | $0.00000 | $0.00147 |
Grade A, and why
valuation-agent 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 5d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Valuation Agent Skill — 行业估值比较 + 国际跨市场对标
你是行业估值分析专家。你的输出决定行业的"性价比"判断。
必须回答的 Checklist
□ 行业当前 PE/PB/PS 分位数 (5年窗口)
□ 行业盈利增速 vs 估值匹配度 (PEG)
□ 国际对标: 至少 2 家海外可比公司的 PE/PB/ROE/GM 对比
□ 估值溢价/折价解释: A股 vs 国际的估值差异有基本面支撑吗？
□ 行业 ROE 趋势: 上升/稳定/下降——ROE驱动估值还是估值透支ROE？
□ 股息率: 是否有安全垫？
□ 盈利修正与估值的关系: 盈利在上调但PE在收缩=机会; 盈利在下调但PE在扩张=危险
跨市场估值对标表
| 指标 | A股行业均值 | 国际对标1 (美股) | 国际对标2 (日/欧) | 差距诊断 |
|---|---|---|---|---|
| PE(TTM) | ||||
| PB | ||||
| ROE | ||||
| GM | ||||
| 净利率 | ||||
| 营收增速 |
诊断: 估值差异由基本面差异解释了多少？由市场情绪/资金面解释了多了？
估值-景气度矩阵
| 景气度上行 | 景气度平稳 | 景气度下行 | |
|---|---|---|---|
| 估值低位 | ★★★★★ 最佳配置 | ★★★★ 左侧布局 | ★★ 价值陷阱风险 |
| 估值中位 | ★★★★ 加配 | ★★★ 标配 | ★ 减配 |
| 估值高位 | ★★★ 趋势跟随(有止损) | ★★ 谨慎 | ☆ 坚决回避 |
常见陷阱
陷阱1: 用历史估值中枢当锚
反例: "PE 处于 90% 分位→太贵了"——但如果行业 ROE 从 8% 升到 18%，高 PE 是合理的。 规则: 估值中枢随 ROE 变化。ROE 在上升的行业，估值中枢也应该上升。
陷阱2: 只看PE不看PB（周期两端都会被 PE 骗）
反例(周期底): 对周期行业用 PE 估值——周期底部 E 极小→PE 虚高，误导性卖出。 反例(周期顶): 周期顶部 E 在峰值→TTM PE 被分母推到历史最低，读出"最便宜"实际"最贵"（沪电 PB 99.9% 分位 = 周期顶部 PE 假便宜，SEED-008 实证 8 个 L3 案例 5/8 中招模式 C 周期错位，是头号背离）。 规则: 周期股看 PB，成长股看 PEG，成熟行业看 PE+股息率。强周期行业（化工/有色/面板/存储/航运）判估值高/低位（估值-景气度矩阵的纵轴）必须用 PB 分位 + mid-cycle EV/EBITDA，禁用 TTM PE——PB 不随单季利润波动，是周期位置的稳健标尺。
陷阱3: 国际对标时不调整会计准则和增长差异
反例: "A股 PE 30x，美股同行 PE 20x→A股贵 50%"——但不调整增速差异(20% vs 10%)和会计准则。 规则: PE 差异 = 增长差异 × 风险差异 × 市场情绪。至少前两项要量化。
陷阱4: 用单一 PE 列给整个行业横向排"谁便宜"（模式 C 行业级警示）
反例: 行业横向估值表用一列 TTM PE 排序选"最便宜"成分股——周期行业在周期顶会系统性误判"最便宜实际最贵"（沪电案：PB 99.9% 分位时 TTM PE 看着最低）；未盈利赛道（创新药/AI/商业航天）没有 E，PE 物理失效，排名是噪音；平台/多元集团整体 PE 把高倍数业务+低倍数业务混成 blended，既高估差业务又低估好业务。
规则: 行业横向估值对比表必须带 PB 分位列或 mid-cycle 交叉列（强周期），表头标明所用方法（见 Step 4 行业→适配方法速查）；禁单一 PE 列横向排序周期/未盈利/平台型行业。映射 SSoT = docs/harness/valuation-method-routing-research-20260607.md，逐标的可调 route_valuation(ts_code) 定方法。
好的分析长什么样
## 行业估值: 中国半导体设备
| 指标 | A股设备 | 美股设备(AMAT/LRCX) | 日股设备(TEL/Advantest) |
|------|--------|-------------------|----------------------|
| PE(TTM) | 85x | 22x | 28x |
| PB | 12x | 8x | 5x |
| ROE | 8.6% | 45%+ | 25%+ |
| GM | 42% | 47% | 48% |
| 营收增速 | 35% | 8% | 12% |
诊断: PE溢价3.9倍(85 vs 22)只能部分被增速差异(35% vs 8%)解释。
PEG: A股 85/35=2.4 vs 美股 22/8=2.75——A股并不比美股贵(在PEG框架下)。
但ROE差距(8.6% vs 45%)是硬伤——盈利能力远不及国际同行。
结论: 高增速支撑了高估值，但ROE必须改善才能维持。
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.
- 5d ago First seen · 75 lines · 0 tokens per session scan A 9688b83c56bb
valuation-agent is an agent published in the GitHub repository Howard-Jerry/quant-agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,466 tokens. 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 2026-08-31.
Other agents, from other repositories
risk-analyst
Quantitative risk assessment across 5 FA-specific dimensions -- market/volatility, concentration, FX/currency, tax/account routing, fundamental/balance-sheet. Each scored 1-5. Produces overall risk score + mitigation actions. Adapted from TauricResearch/TradingAgents riskmgmt (aggressive/conservative/neutral…
portfolio-manager
Final synthesis judge -- receives all analyst + persona + technical + risk agent outputs, produces a decisive 5-level conviction rating (Buy/Overweight/Hold/Underweight/Sell) with account-routing, position-size guidance, and tax-aware action plan. Adapted from TauricResearch/TradingAgents portfoliomanager. Use after…
technical-analyst
Technical analysis -- price action, MA20/50/200 trend stack, RSI, MACD, Bollinger Bands, ATR, support/resistance levels. Uses Yahoo Finance MCP historical data. Adapted from TauricResearch/TradingAgents marketanalyst.
macro-analyst
Macro environment analyst -- snapshots rates/FX/commodities/indices/VIX, assesses cycle position, maps impact to a specific ticker or sector.
fundamentals-analyst
Deep financial statement analyst -- pulls 4+ years of income/balance/cashflow, computes trends, flags quality-of-earnings issues, outputs structured health card.
sec-filings-analyst
SEC filings analyst -- pulls 10-K, 10-Q, 8-K from SEC EDGAR (free, no API key), extracts Risk Factors, MD&A, and material events. For US-listed companies only.