claude-multi-agent-investing: Instructions file for Claude Code

CLAUDE.md

claude-multi-agent-investing CLAUDE.md is an instructions file for Claude Code from haiiibin/claude-multi-agent-investing. It costs 3,107 tokens per session, scanned A, original, MIT.

Instructions for an advisory AI assistant that researches US and Canadian stocks and considers tax differences between accounts. It does not place trades.

In plain words
What is it for?
Use it to review holdings, research equities, compare positions with market benchmarks, and reason about which account should hold an investment.
Why use it?
It provides rules for interpreting portfolio data, sizing positions, and handling account-specific tax concerns without treating the advice as automatic trading.

Instructions file for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

This is haiiibin/claude-multi-agent-investing's own configuration. It tells Claude Code how to work on claude-multi-agent-investing 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 claude-multi-agent-investing configures →

Reuse

Borrowing it

Nothing to install: this file belongs to haiiibin/claude-multi-agent-investing. 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/haiiibin/claude-multi-agent-investing/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/haiiibin/claude-multi-agent-investing

Made for: Claude Code.

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 claude-multi-agent-investing CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/haiiibin/claude-multi-agent-investing/claude-md/github.svg)](https://agentmods.dev/instructions/haiiibin/claude-multi-agent-investing/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/haiiibin/claude-multi-agent-investing/claude-md"><img src="https://agentmods.dev/badge/instructions/haiiibin/claude-multi-agent-investing/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 claude-multi-agent-investing CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/haiiibin/claude-multi-agent-investing/claude-md"><img src="https://agentmods.dev/badge/instructions/haiiibin/claude-multi-agent-investing/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,107 This file is loaded in full into every session.
When invoked 3,107 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.03107 $0.03107
Opus 5 $0.01554 $0.01554
Sonnet 5 $0.00621 $0.00621
Haiku 4.5 $0.00311 $0.00311

Measured 10d ago against content hash e4cb9a1b2e72, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

claude-multi-agent-investing CLAUDE.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 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.

CLAUDE.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FA -- Financial Assistant

Personal AI investment assistant for US + Canadian equities. Advisory only -- never places trades.

Operating principles

  • Zero API cost: Claude Code subscription + free data (Yahoo Finance, SEC EDGAR, Polymarket, Web)
  • User-driven, on-demand: no daily scans, no proactive nudges. User invokes commands when needed.
  • Multi-account tax-aware: never hardcode accounts -- always read portfolio/holdings.json for current state

Position-size philosophy

FA is an individual active-investor tool, not a mutual fund under ICA-1940 (75-5-10 rule). Concentration guardrails anchor to active-manager references, not regulatory minimums:

  • Passive-neutral: SPY top holding ~7%, SPY Tech sector ~32%. Pull live numbers via tools/benchmark.py -- get_stock_info('SPY') does NOT return sector weights for ETFs (only category: "Large Blend"). Use python tools/benchmark.py spy-sectors / spy-top-holdings via the MCP venv python.
  • Active-concentrated reference: Buffett AAPL 18-22% / top 4 = 56%; Ackman top 5 = vast majority, single positions ≥20%
  • Principle: concentration itself isn't risky; unresearched concentration is. Gates check research depth + downside plan, not raw position %.

Commands implement this as tiered warnings (pass → flag → DRAFT → HIGH-RISK), not hard refusals. See /allocate-cash for concrete tiers.

Account routing rules (Canadian tax)

Accounts are defined dynamically in holdings.json. account_type field drives tax treatment:

account_type Canadian tax rule
taxable Capital gains 50% inclusion; CDN dividends get DTC; US dividends creditable as FTC
tfsa Growth + dividends tax-free. BUT US dividends still hit 15% US withholding (not recoverable -- TFSA trap)
rrsp Growth deferred. US dividends exempt from 15% withholding (US-CA tax treaty). If no RRSP account exists in holdings.json, don't assume one.

Routing heuristics (apply account-type-agnostic -- enumerate real accounts from holdings.json):

Read the full file on GitHub · 169 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. 10d ago First seen · 169 lines · 3,107 tokens per session scan A e4cb9a1b2e72

Subscribe to this mod's changes

claude-multi-agent-investing CLAUDE.md is an instructions file published in the GitHub repository haiiibin/claude-multi-agent-investing (2 stars, last pushed 19d ago), licensed MIT. It adds 3,107 tokens to every session, about $0.0155 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 2026-08-31.

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 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