china-dcf-model

china-dcf-model is a skill for Claude Code from cyijun/china-financial-services. It costs 76 tokens per session (1,374 once invoked), scanned A, original, Apache-2.0.

A documented discounted-cash-flow model for valuing non-financial A-share companies. A discounted-cash-flow model estimates today’s value from expected future cash flows and makes its assumptions, valuation date, and adjustments explicit.

In plain words
What is it for?
Use it to build or update FCFF or FCFE valuations, calculate WACC, forecast operating cash flows, model terminal value, reconcile cash and debt, and test sensitivity to key assumptions.
Why use it?
It helps produce a reviewable valuation with consistent financial definitions, recorded data sources, scenarios, sensitivity checks, and a bridge from company value to shareholder value.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the china-model-builder plugin — 6 skills, 1 agent shipped together

Good fit Use it to build or update FCFF or FCFE valuations, calculate WACC, forecast operating cash flows, model terminal value, reconcile cash and debt, and test sensitivity to key assumptions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cyijun/china-financial-services/china-dcf-model
Install

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.

Any agent
npx skills add cyijun/china-financial-services --skill china-dcf-model
Clone the repo
git clone --depth 1 https://github.com/cyijun/china-financial-services

Made for: Claude Code.

Or install china-model-builder, the plugin that ships this one along with the rest of its 6 skills, 1 agent.

Wrote 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.

agentmods badge for china-dcf-model

README.md
[![agentmods](https://agentmods.dev/badge/skills/cyijun/china-financial-services/china-dcf-model/github.svg)](https://agentmods.dev/skills/cyijun/china-financial-services/china-dcf-model)
Your own site
<a href="https://agentmods.dev/skills/cyijun/china-financial-services/china-dcf-model"><img src="https://agentmods.dev/badge/skills/cyijun/china-financial-services/china-dcf-model/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.

agentmods 80×15 button for china-dcf-model

Your own site · 80×15
<a href="https://agentmods.dev/skills/cyijun/china-financial-services/china-dcf-model"><img src="https://agentmods.dev/badge/skills/cyijun/china-financial-services/china-dcf-model.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,374 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00076 $0.01374
Opus 5 $0.00038 $0.00687
Sonnet 5 $0.00015 $0.00275
Haiku 4.5 $0.00008 $0.00137

Measured 11d ago against content hash 21644d9e244d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

china-dcf-model 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 11d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/dcf_model.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/china-model-builder/skills/china-dcf-model/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

A股DCF模型

前置条件

  1. 调用a-share-research-evidence冻结估值日、股价日、实际披露时点和财务版本。
  2. china-market-data取得原始三表、股本、行情和估值数据;历史估值不得用当前修订值回填。
  3. 调用a-share-financial-forensics统一合并范围、币种、累计/单季和一次性项目。
  4. 银行、保险、券商等受监管金融机构不使用普通FCFF;改用剩余收益、DDM或PB-ROE并说明理由。

建模工作流

  1. 选择FCFF或FCFE并保持现金流、折现率和价值桥口径一致。
  2. 从收入量价、毛利、费用、税率、折旧、资本开支和营运资本建立历史到预测桥;每个硬编码输入带来源或[ASSUMPTION]
  3. 基础、压力、乐观情景由经营驱动形成,不赋主观精确概率。
  4. WACC按估值日构建:
    • 无风险利率通过china-market-datachina_yield_curve取得同币种、匹配期限的中国国债收益率,记录实际观测日、期限、曲线类型、provider和interface;yc_cb无权限时,标准到期期限可降级到AKShare bond_china_yield
    • ERP记录估计方法、样本区间和来源;
    • Beta记录回归频率、窗口、基准及去杠杆/再加杠杆过程;
    • 债务成本优先实际增量融资成本或信用风险匹配的市场收益率;
    • 权重使用股权市值与有息债务毛额,现金只进入企业价值到股权价值桥;
    • 税率使用可持续有效税率,并披露优惠到期风险。
  5. 终值同时用永续增长和退出倍数交叉检查。永续增长不得高于与现金流币种一致的长期名义经济增长而不解释。
  6. 企业价值桥单列现金、有息债务、租赁、少数股东、非经营资产、联营投资、养老金及稀释股本。
  7. 输出WACC×永续增长、关键经营驱动和价值桥敏感性;中心格必须等于基础情景。
  8. 调用a-share-valuation-triangulation并列其他方法和反向隐含预期。

可执行计算

scripts/dcf_model.py config.json --output dcf-report.json生成可复核FCFF计算。配置必须包含valuation_date、非空sourcesrevenue_base、逐年forecast_yearscapitalterminal_growthbridgesensitivity;脚本不提供行业默认增长率、Beta、ERP或终值假设。它会计算CAPM股权成本、税后债务成本、市场价值权重WACC、逐年NOPAT/D&A/Capex/营运资本变化、终值、价值桥和敏感性中心格检查。

capital.risk_free_rate使用小数,数据路由的yield使用百分数。配置必须同时提供capital.risk_free_rate_evidence

{
  "risk_free_rate": 0.016832,
  "risk_free_rate_evidence": {
    "observation_date": "20260820",
    "term_years": 10,
    "currency": "CNY",
    "provider": "akshare",
    "interface": "bond_china_yield",
    "curve_type": "maturity",
    "source_value": 1.6832,
    "source_unit": "percent"
  }
}

脚本核对1.6832% → 0.016832、观测日不晚于估值日、期限为正且币种为CNY;不接受没有证据的裸无风险利率。

该脚本输出JSON计算底稿,不替代工作簿样式、公式重算引擎或原始数据验证;如果再由xlsx-author落入工作簿,仍需audit-xls验收。

工作簿契约

  • 至少包含SourcesInputsHistoricalsForecastDCFSensitivityChecks
  • 蓝色为硬编码输入、黑色为本表公式、绿色为跨表链接;计算单元格不直接输入结果。
  • Checks至少覆盖三表勾稽、现金流桥、折现期、终值占比、价值桥、每股价值和敏感性中心格。
  • 使用xlsx-author生成文件,并调用audit-xls检查公式、错误值和结构。只有实际执行了重算引擎才能声明公式已重算;否则标记formula_execution_unverified

Read the full file on GitHub · 76 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 11d ago First seen · 76 lines · 76 tokens per session scan A 21644d9e244d

Subscribe to this mod's changes

china-dcf-model is a skill published in the GitHub repository cyijun/china-financial-services (19 stars, last pushed 17d ago), licensed Apache-2.0. It adds 76 tokens to every session and 1,374 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 2026-08-30.