Borrowing it
Nothing to install: this file belongs to ericxuzhesheng/Convertible-Bond-Pricing-Research. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ericxuzhesheng/Convertible-Bond-Pricing-Research/main/AGENTS.mdgit clone --depth 1 https://github.com/ericxuzhesheng/Convertible-Bond-Pricing-ResearchWrote 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/instructions/ericxuzhesheng/convertible-bond-pricing-research/agents-md)<a href="https://agentmods.dev/instructions/ericxuzhesheng/convertible-bond-pricing-research/agents-md"><img src="https://agentmods.dev/badge/instructions/ericxuzhesheng/convertible-bond-pricing-research/agents-md/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/instructions/ericxuzhesheng/convertible-bond-pricing-research/agents-md"><img src="https://agentmods.dev/badge/instructions/ericxuzhesheng/convertible-bond-pricing-research/agents-md.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 | $0.04780 | $0.04780 |
| Opus 5.5 | $0.01912 | $0.01912 |
| Sonnet 5.5 | $0.00956 | $0.00956 |
| Haiku 4.5 | $0.00478 | $0.00478 |
Grade A, and why
Convertible-Bond-Pricing-Research AGENTS.md 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 — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Agent Instructions for Convertible Bond Pricing Research
This file tells Codex how to navigate and work with this codebase.
Project Purpose
Absolute pricing research for Chinese A-share convertible bonds using three models:
- Black-Scholes (BS): closed-form, offensive anchor (equity/vol driven)
- ZL (project label): clause-stopping Monte Carlo policy baseline, defensive anchor
- Least-Squares Monte Carlo (LSM): vectorized continuation-value regression and voluntary early conversion
The pipeline goes: raw data → pricing → mispricing signal → long-short strategy.
Current verified local model cutoff: 2026-10-30; daily strategy-input cutoff: 2026-10-30. Factors, IC, strategies, 2026 weekly reports, figures and README were refreshed and validated on 2026-10-31 using the existing verified pricing baseline. Pricing and six-factor text tables dated 2026-08-28 are archived evidence, not results of the new weekly value strategy. Routine weekly work is strictly incremental for market data and pricing. Recalculate derived factors, IC, strategies, figures and README on every weekly update using the verified pricing baseline. A full-history pricing rebuild requires an explicit maintainer request.
Repository Layout
Convertible-Bond-Pricing-Research/
├── AGENTS.md ← you are here
├── README.md ← bilingual overview
├── backtest/ ← PRIMARY working directory
│ ├── data_pipeline.py ← Tushare data ingestion (run first)
│ ├── B-S_backtest.py ← BS model pricing + output
│ ├── Z-L_backtest_GPU_prod.py ← corrected clause-MC entrypoint (CPU)
│ ├── Z-L_backtest_CPU_prod.py ← GitHub CPU incremental entrypoint
│ ├── LSM_backtest.py ← vectorized strict-incremental LSM driver
│ ├── lsm_backend.py ← batched quadratic Longstaff-Schwartz engine
│ ├── Z-L_backtest_GPU.py ← disabled legacy entrypoint
│ ├── full_history_rebuild.py ← fail-closed full-history rebuild
│ ├── regenerate_plots.py ← 一键重生成 README 图表（无需重跑模型）
│ ├── weekly_update.bat ← 周更新主入口（数据→模型→图表→Git推送）
│ ├── setup_weekly_task.ps1 ← 一次性注册 Windows 任务计划程序
│ ├── logs/ ← weekly_update.bat 日志
│ ├── cb_*.csv ← wide-format data caches (rows=date, cols=bond)
│ ├── rf_yield_cache.csv ← risk-free yield curve (tenor format, not wide)
│ ├── bs_volatility_cache.csv ← 250-day rolling vol for BS
│ ├── BS_Model_*.csv / .xlsx ← BS model outputs
│ ├── ZL_Model_*.csv / .xlsx ← ZL model outputs
│ └── LSM_Model_*.csv / .xlsx ← LSM outputs + independent manifest
├── long-short strategy/
│ ├── weekly_value_strategy.py ← independent weekly mean-value + 2% net-margin strategy
│ ├── weekly_value_results/ ← separate daily research and frozen tracking outputs
│ └── BS_ZL_LSM_strategy.py ← legacy relative-ranking / monthly research
├── mispricing factor/
│ ├── B-S_mispricing_factor.py ← 6-factor BS composite
│ ├── Z-L_mispricing_factor.py ← 6-factor ZL composite
│ └── LSM_mispricing_factor.py ← 6-factor LSM composite
├── summary/
│ └── key_findings.md ← executive summary
└── report/ ← full research PDF
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 Changed · +13 lines · +250 tokens per session aa60901d21e9
- 9d ago Changed · +37 lines · +459 tokens per session fa27da149fce
- 10d ago Changed 35e72024ca3f
- 19d ago Changed · -6 tokens per session fb299eff6809
- 22d ago Changed · +11 lines · +184 tokens per session eb2229cd23a1
- 1mo ago Changed 6e1d1900db79
- 1mo ago Changed · +30 lines · +454 tokens per session 9fbcc827cb94
- 2mo ago First seen · 287 lines · 3,439 tokens per session scan A bb5d4af823f8
Convertible-Bond-Pricing-Research AGENTS.md is an instructions file published in the GitHub repository ericxuzhesheng/Convertible-Bond-Pricing-Research (9 stars, last pushed 6d ago), licensed MIT. It adds 4,780 tokens to every session, about $0.0191 per session on Opus 5.5. 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 2026-08-31.
Convertible-Bond-Pricing-Research AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Convertible-Bond-Pricing-Research AGENTS.mdericxuzhesheng/Convertible-Bond-Pricing-Research | Instructions file | 9 | 6d ago | MIT | A | 4,780 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |