fund-guy-skill AGENTS.md

fund-guy-skill AGENTS.md is an instructions file for Codex, OpenCode from wbh604/fund-guy-skill. It costs 702 tokens per session, scanned A, original, MIT.

A set of instructions for auditing a fund manager's investment decisions using public fund data. It produces an interactive HTML report and emphasizes separating managers' tenures and documenting missing information.

In plain words
What is it for?
Use it to analyze a fund by fetching data, checking transactions and holdings, comparing relevant periods, and building a report. The input is a fund code.
Why use it?
It helps prevent a manager from being judged on a predecessor's results and prevents unsupported figures from entering the analysis.

Instructions file for CodexOpenCode

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.

agentmods
npx agentmods add instructions/wbh604/fund-guy-skill/agents-md
Clone the repo
git clone --depth 1 https://github.com/wbh604/fund-guy-skill

Made for: Codex, OpenCode.

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 fund-guy-skill AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/wbh604/fund-guy-skill/agents-md.svg)](https://agentmods.dev/instructions/wbh604/fund-guy-skill/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/wbh604/fund-guy-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/wbh604/fund-guy-skill/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 702 This file is loaded in full into every session.
When invoked 702 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00702 $0.00702
Opus 5 $0.00351 $0.00351
Sonnet 5 $0.00140 $0.00140
Haiku 4.5 $0.00070 $0.00070

Measured yesterday against content hash e0440ca40a47, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fund-guy-skill 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 yesterday.

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.

AGENTS.md · 47 lines

What it actually says

Fund Guy Skill · Agent 指南

这是一个基金经理行为审计 skill:输入基金代码,逐笔验证经理的买卖决策,产出单文件交互报告。 评的是行为,不是净值。

核心文档(按顺序)

  1. skills/fund-manager-alpha/SKILL.md —— 完整方法论:18 条硬规则、三层取数模型、评分公式。任何分析任务先读它
  2. skills/fund-manager-alpha/references/ —— 算法细节(House Consensus/任期切割/经理尽调)
  3. DESIGN.md —— 设计决策记录(为什么这么做)

快速执行

pip install -r requirements.txt
python run.py <基金代码>               # 完整管线:取数 → 分析 → 出报告
python run.py <基金代码> --no-browser  # 无 GUI 环境

产出 assets/fund-<code>.html。请用浏览器直接打开这个本地文件,不要丢到 htmlpreview.github.io / gist 在线预览(那些页面经常不跑脚本,分数和 K 线会显示成空的)。scripts/ 下是一次真实运行(163417)的参考实现, 接口失效时按 SKILL 的三层取数模型自行补数,不要死修脚本。

不可违反的三条

  1. 先做任期切割 —— 前任业绩混入现任评价 = 分析作废
  2. 绝不编数 —— 拿不到就写"未获取",没有出处的数字不进报告
  3. 定性判断由 Agent 做 —— 公告全文解读、Mandate 约束抽取仍没有脚本。造神九项能用本品公告/任期/持仓筛的已自动出结论(三级证据制);季报原文、亲属任职、招募书全文对照仍标未获取。行业用东财/港股公开分类自动取,禁止手写某只基金的对照表;窗口、费率、风格指数、同门对照、K 线 fund 事件全部按所选基金重算

目录速查

skills/fund-manager-alpha/   # 方法论主文档 + references
scripts/                     # 参考实现(fetch → analyze → build)
commands/                    # Claude Code 斜杠命令(analyze-fund/quick-check/find-similar)
.claude-plugin/              # Claude Code 插件清单
.cursor/skills/              # Cursor 项目技能入口
.agents/skills/              # Codex 项目技能入口
assets/                      # 报告模板 + 演示产物(演示版已对经理姓名照片打码)
run.py                       # 一键入口

边界

  • 输出不构成投资建议;报告必须带免责声明和数据来源标注
  • 演示/公开发布必须打码经理姓名与照片(build_fund_report.pyMASK 开关)
  • 原始数据落 .cache/(已 gitignore),不得提交
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. yesterday Changed · +46 tokens per session e0440ca40a47
  2. 5d ago First seen · 47 lines · 656 tokens per session scan A 0470980c9ccc

Subscribe to this mod's changes

fund-guy-skill AGENTS.md is an instructions file published in the GitHub repository wbh604/fund-guy-skill (503 stars, last pushed yesterday), licensed MIT. It adds 702 tokens to every session, about $0.0035 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.

Related

Other instructions, from other repositories