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 instructions/wbh604/fund-guy-skill/agents-mdgit clone --depth 1 https://github.com/wbh604/fund-guy-skillWrote 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/wbh604/fund-guy-skill/agents-md)<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>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 | $0.00702 | $0.00702 |
| Opus 5 | $0.00351 | $0.00351 |
| Sonnet 5 | $0.00140 | $0.00140 |
| Haiku 4.5 | $0.00070 | $0.00070 |
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.
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)
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skills/fund-manager-alpha/references/—— 算法细节(House Consensus/任期切割/经理尽调)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
- 先做任期切割 —— 前任业绩混入现任评价 = 分析作废
- 绝不编数 —— 拿不到就写"未获取",没有出处的数字不进报告
- 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.py的MASK开关) - 原始数据落
.cache/(已 gitignore),不得提交
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.
- yesterday Changed · +46 tokens per session e0440ca40a47
- 5d ago First seen · 47 lines · 656 tokens per session scan A 0470980c9ccc
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.
Other instructions, from other repositories
ClawRouter CLAUDE.md
Claude Code instructions for BlockRunAI/ClawRouter, covering clawrouter, commands, project structure, key dependencies and conventions.
InvestSkill GEMINI.md
Gemini CLI instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
LLM-TradeBot copilot-instructions.md
Copilot instructions for EthanAlgoX/LLM-TradeBot, covering repository instructions, core rules, validation and ai asset governance.
Convertible-Bond-Pricing-Research CLAUDE.md
Instructions for ericxuzhesheng/Convertible-Bond-Pricing-Research, covering claude.md — convertible bond pricing research, current published state and routine commands.
bukio-cli AGENTS.md
AGENTS.md instructions for erikvankempen/bukio-cli, covering agents.md — bukio-cli agent manual, 1. house rules (non-negotiable), 2. environment, 3. command quick reference and 3.1 jurisdiction profiles (16 markets).
swiss-snb-mcp CLAUDE.md
Claude Code instructions for malkreide/swiss-snb-mcp, covering claude.md, teil 1 — konventionen (portfolio-weit), vor der arbeit, tests and wenn etwas rot ist.