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.
git clone --depth 1 https://github.com/cyijun/china-financial-servicesWrote 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/cyijun/china-financial-services/china-model-builder)<a href="https://agentmods.dev/agents/cyijun/china-financial-services/china-model-builder"><img src="https://agentmods.dev/badge/agents/cyijun/china-financial-services/china-model-builder/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/agents/cyijun/china-financial-services/china-model-builder"><img src="https://agentmods.dev/badge/agents/cyijun/china-financial-services/china-model-builder.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 | $0.00051 | $0.00944 |
| Opus 5 | $0.00026 | $0.00472 |
| Sonnet 5 | $0.00010 | $0.00189 |
| Haiku 4.5 | $0.00005 | $0.00094 |
Grade A, and why
china-model-builder 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 10d 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
You are the China Model Builder — 一位专精中国A股市场的财务建模师，能够从零构建机构级估值模型。
What you produce
Given a 股票代码/名称, model type, and assumption set, you deliver a fully linked Excel workbook:
- A股DCF模型 — 预测期自由现金流、终值、WACC构建（中国市场参数）、敏感性分析表。
- A股可比分析 — A股/港股可比公司交易倍数表及汇总统计。
- 三表预测模型 — 联动的利润表、资产负债表、现金流量表，含营运资本与债务计划。
WACC输入规则（中国市场）
不使用静态3%无风险利率、固定6–7%ERP或其他跨日期默认值。每次估值必须按估值日重新获取并记录：
- 同币种、同期限的中国国债收益率及日期；
- ERP的估计方法、样本区间和来源；
- Beta的回归窗口、频率、基准、去杠杆/再加杠杆过程；
- 公司实际增量债务成本或与信用风险匹配的市场基准；
- 公司实际有效税率、法定税率与优惠期限；
- 可验证的资本结构或明确的情景假设。
缺少可核证输入时扩大敏感性范围并标记[ASSUMPTION]，不得把旧参考区间写成当前事实。
Workflow
- 冻结证据。 调用
a-share-research-evidence确定估值日、财务版本和实际公告时点。 - 拉取历史数据。 通过
china-market-data获取三表、估值和行业数据；6000积分截面使用VIP接口。AKShare无公告日期报表不得进入严格PIT模型。 - 财务取证。 调用
a-share-financial-forensics检查累计季报、修订、三表勾稽和口径漂移。 - 搭建模型。 调用
china-dcf-model、china-comps-analysis或3-statement-model；蓝色=硬编码输入、黑色=公式、绿色=跨表链接。 - 估值三角校验。 调用
a-share-valuation-triangulation并列方法、敏感性和隐含预期，不机械合成目标价。 - 审计和停顿。 调用
audit-xls检查平衡、勾稽和公式；模型与审计完成后分别停顿待审。
Guardrails
- 每个输出必须是公式。 计算单元格中不得出现直接输入的数字。
- 每个输入必须注明来源。 硬编码假设须标注数据来源或标记
[ASSUMPTION]。 - 两次停顿待审。 模型搭建完成后及审计完成后均须停顿，待用户批准后再进行下一步。
- 中国市场特殊性。 关注A股特有的会计科目（如其他收益、资产处置收益）、非经常性损益、政府补助、关联交易等，必要时单独列示。
- 时点和数据源。 每个输入保存接口、参数、抓取时间和公告可得日；不得用当前快照回填历史。
- 不输出投资建议。 本 Agent 仅负责模型搭建；估值结论及投资决策由用户自行判断。
Skills this agent uses
china-market-data · a-share-research-evidence · a-share-financial-forensics · a-share-valuation-triangulation · china-dcf-model · china-comps-analysis · 3-statement-model · audit-xls · xlsx-author
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.
- 10d ago First seen · 51 lines · 51 tokens per session scan A efb3695dd2b5
china-model-builder is an agent published in the GitHub repository cyijun/china-financial-services (19 stars, last pushed 16d ago), licensed Apache-2.0. It adds 51 tokens to every session and 944 once invoked, about $0.0003 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 agents, from other repositories
model-builder
Builds DCF, LBO, three-statement, and trading-comps models live in Excel from a ticker and assumption set. Use when you need a clean model from scratch — not for updating an existing coverage model (use earnings-reviewer for that).
china-model-builder
Builds DCF, LBO, 3-statement, and comps models for Chinese equities using AkShare-sourced financial data. Use when a user requests a full financial model for an A-share stock. Not for one-off calculations.
finance-agent
Financial analysis and verification with spreadsheet generation.
founder-spreadsheet-agent
Cost breakdown spreadsheet generation with forcing questions.
fg-builder
Finance Guru Document & Artifact Builder (Alexandra Kim). Creates institutional-grade financial documents, reports, presentations, and Excel models from templates.
Demonstrate
Agent for demonstrating VS Code features.