agentmods.dev

fadacai-portfolio: Instructions file for Claude Code

CLAUDE.md

fadacai-portfolio CLAUDE.md is an instructions file for Claude Code, Codex from PatrickSUDO/fadacai-portfolio. It costs 13,173 tokens per session, scanned B, a copy of fadacai-portfolio AGENTS.md, MIT.

Project instructions for an investment research and portfolio-management workspace focused on US stocks and options. They set the language, report formats, research workflow, and optional second-opinion commands.

In plain words
What is it for?
Preparing briefings, stock analysis, portfolio reviews, and related research outputs, including optional Telegram or email delivery.
Why use it?
They give a coding agent the project’s working rules and recurring research process, reducing inconsistent language, formatting, and task handling.

Instructions file for Claude CodeCodex

Written for Claude Code and Codex: SessionStart hook event, but also runs codex exec. Also seen: reads .claude/ paths; mentions subagents; positional $N argument.

This is PatrickSUDO/fadacai-portfolio's own configuration. It tells Claude Code and Codex how to work on fadacai-portfolio itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything fadacai-portfolio configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/supatrick/laptop/mcp-servers/fmp-mcp/compose.yaml.

not rated 139repo +1 changed 2d ago B scan 13,173 tokens copy · 100% MIT
View source ↗ PatrickSUDO/fadacai-portfolio
Reuse

Borrowing it

Nothing to install: this file belongs to PatrickSUDO/fadacai-portfolio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/PatrickSUDO/fadacai-portfolio/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/PatrickSUDO/fadacai-portfolio

Made for: Claude Code, Codex.

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 fadacai-portfolio CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/patricksudo/fadacai-portfolio/claude-md/github.svg)](https://agentmods.dev/instructions/patricksudo/fadacai-portfolio/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/patricksudo/fadacai-portfolio/claude-md"><img src="https://agentmods.dev/badge/instructions/patricksudo/fadacai-portfolio/claude-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.

agentmods 80×15 button for fadacai-portfolio CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/patricksudo/fadacai-portfolio/claude-md"><img src="https://agentmods.dev/badge/instructions/patricksudo/fadacai-portfolio/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13,173 This file is loaded in full into every session.
When invoked 13,173 The same file — it is already loaded in full.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod 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 $0.13173 $0.13173
Opus 5 $0.06587 $0.06587
Sonnet 5 $0.02635 $0.02635
Haiku 4.5 $0.01317 $0.01317

Measured 2d ago against content hash db05e7bb9f2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

fadacai-portfolio CLAUDE.md scanned grade B with 1 finding 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 2d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

⚠️ **不要用 `subagent_type: "codex:codex-rescue"` 或 `/codex:rescue`**。實測（2026-06-07）那條路徑會載入 `~/.codex/config.toml` 的 `superpowers@openai-curated` plugin，強制「回應前必須 invoke skill」+ 全域 `model_reasoning_effort = "xhigh"`，把整個 turn
Origin

This is a copy

100% identical to fadacai-portfolio AGENTS.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 360 lines

How it starts

The opening of the file, as written. The whole thing — 360 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fundamental Allocation Study - Project Instructions

Project Overview

This is an investment research and portfolio management workspace. The user actively trades US stocks and options on a Level 2 options margin brokerage account (connected via the firstrade-server MCP as the reference broker integration).

Language & Format

  • All output in Traditional Chinese (繁體中文)
  • Thread/social media posts: plain text only, NO markdown, NO tables
  • Reports and analysis: markdown tables are fine

Workflow

  1. /briefing — quick daily check (~1 min); /briefing full (~3 min); /briefing deep (~5 min)
    • /briefing telegram — Telegram push tier (~2-3 min)：盤中推送專用，產出 briefing-out/ 兩個檔案
    • --send 旗標（任何 tier 可加）：執行完後推送 Telegram + email 副本
    • 例：/briefing telegram --send、/briefing full --send
    • launchd 每個交易日 CEST 17:00 自動執行 /briefing telegram --send（週五加 --codex）；runner 固定 --model sonnet（BRIEFING_MODEL 覆寫）、重試 5 次（2026-08-05 五修：API mid-stream 斷流連殺對策）。三次以上全滅 → 互動 session 手動 /briefing telegram --send 補發（dedup 防重複）
    • Setup 文件：docs/briefing-auto-send.md
  2. /portfolio-review — full deep report with live data via MCP
  3. /stock-analysis TICKER — individual stock deep dive
  4. /options-strategy TICKER STRATEGY — options calculation (supports multi-ticker comparison)
  5. /trade-journal log|review|summary|auto — trade records
  6. /mcp-health — test all MCP server connections
  7. /event-vol-scan [days] [TICKER ...] — 財報/CPI/FOMC 前末日 buy call / 雙買 straddle 機會掃描（引擎 tools/event_vol_scan.py；賣方策略不適用、仍守財報 ±48h 禁令）
  8. /trade-review [2w|4w|since YYYY-MM-DD] — 每兩週交易檢討（自我進化引擎）：歸因每筆成交是「系統決策」還是「脫離 plan 的自主決策」，算三個並列指標、驗影子訊號、更新 feedback/RULES-LEDGER.md 規則命中率，輸出「本期該改哪一條規則」。引擎 tools/trade_ledger.py；briefing 距上次 >14 天會提醒。每期加跑帳戶級四指標（期間報酬/CAGR/MDD/Sharpe + profit factor）：tools/account_metrics.py scan && report --live <即時總值>（淨值標記刮自 journal/briefing 快照，2026-06-01 起；FIFO 已實現含選擇權）
    • 交易 α（score）：進出對不對。β 對實際使用的基準回歸算（半導體對 SMH、其餘對 SPY）——用券商 β（對大盤測）套 SMH 會嚴重過度調整，結論會反過來
    • 持有 α（holding-alpha）：該不該繼續抱。滾動窗 + 建倉至今。沒有這項，純交易指標會獎勵頻繁進出、把「抱對」記為零貢獻；首測持有 α 量級大於交易 α
    • beta capture（beta-capture）：行情好的時候吃到沒有。拆基準上漲/下跌日各自回歸 β；up-β < down-β = 漲不上跌得凶。梯級停利 + 買梯會機械性壓低 up-capture，這是純 α 看不見的成本
  9. PMCC 收租候選掃描 — python3 tools/pmcc_scan.py（5 因子計分卡機械化，規則 feedback/pmcc-candidate-discipline.md；每次 /portfolio-review Section I.6 自動跑，找「想留但不看好大漲」的名字轉 poor man's covered call；判斷層留給 /options-strategy）

Read the full file on GitHub · 360 lines

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. 2d ago Changed · +7 lines · +970 tokens per session db05e7bb9f2f
  2. 9d ago First seen · 353 lines · 12,203 tokens per session scan B 5c2bd35ea11c

Subscribe to this mod's changes

fadacai-portfolio CLAUDE.md is an instructions file published in the GitHub repository PatrickSUDO/fadacai-portfolio (139 stars, last pushed 2d ago), licensed MIT. It adds 13,173 tokens to every session, about $0.0659 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). It is 100% identical to fadacai-portfolio AGENTS.md, differing in 0 lines, and is treated as a copy.

Finance and fintechResearch
Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens