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

.claude/commands/allocate-cash.md

allocate-cash is a command for Claude Code from haiiibin/claude-multi-agent-investing. It costs 37 tokens per session (2,435 once invoked), scanned A, original, MIT.

A command that creates a portfolio-level plan for investing available cash. It reviews current holdings, cash, watchlist notes, recent investment decisions, and market conditions.

In plain words
What is it for?
Building a tiered cash-deployment plan, keeping a cash reserve, checking watchlist price targets, and routing purchases with tax considerations.
Why use it?
It helps decide how much cash to invest, what exposures may be missing, and which account should hold each purchase.

Command for Claude Code

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

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 →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python tools/benchmark.py spy-sectors.

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/allocate-cash.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 allocate-cash

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/haiiibin/claude-multi-agent-investing/allocate-cash"><img src="https://agentmods.dev/badge/commands/haiiibin/claude-multi-agent-investing/allocate-cash.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,435 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 $0.00037 $0.02435
Opus 5 $0.00018 $0.01218
Sonnet 5 $0.00007 $0.00487
Haiku 4.5 $0.00004 $0.00244

Measured 11d ago against content hash e192988f442d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

allocate-cash 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 11d 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/allocate-cash.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/allocate-cash -- Cash Deployment Strategy

Portfolio construction exercise: given cash + current exposures + regime, what to buy and where. Not a single-ticker recommendation.

Input

  • Default: read holdings.json (cash fields + holdings)
  • $ARGUMENTS can override: e.g., deploy 60% of cash, hold 40% reserve or explicit cash amounts

If input is ambiguous, ask ONE targeted question, then proceed.

Phase 1 -- Audit

Journal pre-scan: Read memory/long_term/journal.md (if exists). Filter last 30 days. Extract:

  • "waiting for {TICKER} at {price}" entries → if current price has crossed trigger, surface as automatic Tier 1 candidate
  • "passed on {TICKER}" entries → note why, don't re-recommend without new evidence
  • "thesis-change on {TICKER}" entries → surface as candidate to trim
  • Prepend a 3-bullet summary to Phase 4 candidate generation context

Watchlist sanity check: for each entry in holdings.json watchlist[]:

  1. Pull get_stock_info(ticker).currentPrice
  2. Parse the note field for direction keywords: < $X / > $X / below X / above X
  3. If note says "waiting for < $X" but current > X × 1.5 (target is 50%+ under current), emit ⚠️ {ticker}: target $X is {gap}% below current $Y -- check if target is stale (split? old thesis?)
  4. Same for inverse: note says > $X but current is already well above
  5. Don't block; just surface. User fixes the note or removes the entry.

This catches dead watchlist entries from stock splits or thesis drift (e.g. GOOGL target < $180 after the 20:1 split in 2022 when the note was written pre-split).

Read holdings.json. Compute:

Totals: MV per account (native + base currency), cash per account/currency, cash % of portfolio.

Concentration -- aggregate by TICKER across accounts (not by row). Same ticker in 2 accounts = 1 position. Report top 5 aggregate positions.

Data integrity check: for each holding, sanity-check cost_basis vs 5y price range. Flag if >2× 5y_high or <0.5× 5y_low → likely stale from split (see CLAUDE.md). Do not compute P&L on flagged positions.

Read the full file on GitHub · 167 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. 11d ago First seen · 167 lines · 37 tokens per session scan A e192988f442d

Subscribe to this mod's changes

allocate-cash is a command published in the GitHub repository haiiibin/claude-multi-agent-investing (2 stars, last pushed 20d ago), licensed MIT. It adds 37 tokens to every session and 2,435 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.