claude-multi-agent-investing: Command for Claude Code

.claude/commands/research.md

research is a command for Claude Code from haiiibin/claude-multi-agent-investing. It costs 33 tokens per session (1,832 once invoked), scanned A, original, MIT.

A command for researching one stock ticker across several analysis perspectives, including how existing holdings may affect taxes in Canadian accounts.

In plain words
What is it for?
Use it to investigate a ticker such as AAPL, check where you already own it, and assess its fit across taxable, TFSA, and other registered accounts.
Why use it?
It brings company research, prior notes, portfolio holdings, and tax considerations into one review instead of checking them separately.

Command for Claude Code

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

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/commands/research.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 research

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/haiiibin/claude-multi-agent-investing/research"><img src="https://agentmods.dev/badge/commands/haiiibin/claude-multi-agent-investing/research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,832 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00033 $0.01832
Opus 5 $0.00016 $0.00916
Sonnet 5 $0.00007 $0.00366
Haiku 4.5 $0.00003 $0.00183

Measured 10d ago against content hash 60f3a4c53c2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

research 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/commands/research.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/research TICKER -- Deep Ticker Research (Tax-Aware)

Multi-agent deep-dive on a single ticker. Ticker from $ARGUMENTS. If no argument given, ask which ticker.

Ticker normalization (CLAUDE.md quirk): class-share tickers use - in yfinance, not .. Before any tool call, normalize BRK.BBRK-B, BF.BBF-B, etc. Echo user's original spelling in output.

Phase 1 -- Context load

Read portfolio/holdings.json. Find all positions in this ticker across accounts:

  • Which accounts already hold it?
  • Cost basis + shares in each account
  • Is it in watchlist? For which target account?

Memory search protocol (specific steps):

  1. Run Glob with pattern memory/mid_term/*{TICKER}*.md to find prior research/deep-dive artifacts on this ticker
  2. Run Glob with pattern memory/mid_term/*market-pulse*.md sorted by filename (dates embedded) -- take the most recent
  3. For each ticker match, check filename date. Keep only files < 14 days old; older artifacts are stale
  4. Read the top 1-2 most recent files (don't flood context with everything)
  5. Journal lookup -- Read memory/long_term/journal.md and grep entries mentioning {TICKER} in the last 90 days. These capture "why I passed last time" / "waiting for X" decisions that shouldn't be forgotten. Especially watch for thesis-change tags.
  6. Summarize key facts (current price anchor, last thesis, agent signals, any follow-up items, prior journal decisions)
  7. Prepend this summary to the context bundle sent to each persona -- they argue better with hard numbers already in hand
  8. If no recent matches exist, tell the user: "No recent research on this ticker -- consider running /deep-dive {TICKER} first for a fact-heavy session"
  9. If a /research was run within the last 3 days, warn the user: "Already analyzed 3 days ago -- re-running now may give echo results. Skip unless material new info."

Phase 2 -- Parallel persona analysis

Dispatch 5 sub-agents in parallel via Task tool in a single message:

Read the full file on GitHub · 141 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 · 141 lines · 33 tokens per session scan A 60f3a4c53c2d

Subscribe to this mod's changes

research is a command published in the GitHub repository haiiibin/claude-multi-agent-investing (2 stars, last pushed 19d ago), licensed MIT. It adds 33 tokens to every session and 1,832 once invoked, about $0.0002 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.