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

.claude/commands/deep-dive.md

deep-dive is a command for Claude Code from haiiibin/claude-multi-agent-investing. It costs 33 tokens per session (1,466 once invoked), scanned A, original, MIT.

A stock-research command for gathering detailed information about one company identified by its ticker symbol, including financial results, regulatory filings, news, the wider economy, and competitors.

In plain words
What is it for?
Use it for an in-depth review of a stock such as Apple (AAPL), especially before opening or materially changing a position.
Why use it?
It brings relevant facts together before you decide whether to buy, sell, or change a holding. It also checks existing portfolio records and recent research so work is not repeated.

Command for Claude Code

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

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/deep-dive.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 deep-dive

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/haiiibin/claude-multi-agent-investing/deep-dive"><img src="https://agentmods.dev/badge/commands/haiiibin/claude-multi-agent-investing/deep-dive.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 1,466 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 $0.01466
Opus 5 $0.00016 $0.00733
Sonnet 5 $0.00007 $0.00293
Haiku 4.5 $0.00003 $0.00147

Measured 9d ago against content hash c740081d9983, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

deep-dive 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 9d 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/deep-dive.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/deep-dive TICKER -- Intelligence Gathering

Deepest single-ticker analysis in the system. Use when you're seriously considering opening or materially changing a position. Takes ~3-5 minutes.

/research is for quick multi-persona debate. /deep-dive is for information gathering -- get all the facts on the table before forming an opinion.

Ticker from $ARGUMENTS. If missing, ask.

Ticker normalization (CLAUDE.md quirk): normalize BRK.BBRK-B, BF.BBF-B before tool calls. Echo user's spelling in output.

Phase 1 -- Context (read-only, fast)

  1. Portfolio context: Read portfolio/holdings.json. Aggregate by ticker across ALL accounts (same ticker in 2 accounts = one position for exposure calculation). Note: already held? In which accounts? Total shares? Weighted avg cost? In watchlist?

  2. Memory lookup (specific steps):

    • Glob pattern memory/mid_term/*{TICKER}*.md -- find prior artifacts
    • Filter to files < 90 days old by filename date
    • If found, Read the most recent 1-2 files and summarize key prior findings
    • Use this to avoid re-gathering same facts (e.g., if 10-K already extracted 30 days ago, only pull 10-Q delta)
    • If a /deep-dive was run within 14 days, ask user if they want incremental update or full redo -- don't silently duplicate
    • Journal lookup -- Read memory/long_term/journal.md (if exists) and grep entries mentioning {TICKER} within last 120 days. Surface: "passed on this ticker 60 days ago at $X because Y" / "flagged thesis-change on this ticker 30 days ago". A deep-dive that ignores user's prior documented stance is wasted effort.

Phase 2 -- Parallel intelligence dispatch

Dispatch 4 sub-agents in parallel via Task tool in a single message:

  1. fundamentals-analyst -- 4 years of statements, quality-of-earnings check
  2. news-analyst -- last 30 days news, sentiment, actionable events
  3. sec-filings-analyst -- latest 10-K risk factors, 10-Q changes, recent 8-Ks, insider activity (US-listed only; skip if Canadian)
  4. macro-analyst -- current regime + specific impact on this ticker / sector

Read the full file on GitHub · 130 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. 9d ago First seen · 130 lines · 33 tokens per session scan A c740081d9983

Subscribe to this mod's changes

deep-dive is a command published in the GitHub repository haiiibin/claude-multi-agent-investing (2 stars, last pushed 18d ago), licensed MIT. It adds 33 tokens to every session and 1,466 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.