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

.claude/commands/reconcile.md

reconcile is a command for Claude Code from haiiibin/claude-multi-agent-investing. It costs 49 tokens per session (1,756 once invoked), scanned A, original, MIT.

A command that compares recorded investment holdings with market records of dividends, stock splits, and spin-offs—events that change what you own without a direct trade.

In plain words
What is it for?
Use it to review corporate actions for held tickers and prepare corrections for confirmation against the broker statement.
Why use it?
It identifies differences between a holdings file and a broker statement before later investment analysis relies on outdated data.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: 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/reconcile.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 reconcile

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/haiiibin/claude-multi-agent-investing/reconcile"><img src="https://agentmods.dev/badge/commands/haiiibin/claude-multi-agent-investing/reconcile.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,756 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 $0.00049 $0.01756
Opus 5 $0.00024 $0.00878
Sonnet 5 $0.00010 $0.00351
Haiku 4.5 $0.00005 $0.00176

Measured 12d ago against content hash 538635ae6900, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

reconcile 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 12d 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/reconcile.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/reconcile -- Corporate Action Sync

/trade records what you did. /reconcile catches what the market did to your holdings while you weren't looking -- dividends, DRIP, splits, spinoffs. Without this, holdings.json silently drifts from broker reality and every downstream analysis becomes wrong.

Advisory only. User confirms against broker statement before the file is touched.

When to run

  • Monthly (dividends arrive monthly on Canadian banks, quarterly on US mega-cap)
  • Before any /allocate-cash or /rebalance if last run was > 30 days ago
  • After any announced split / spinoff / merger for a ticker you hold

Phase 1 -- Scope

Read holdings.json. For each account, note last_updated timestamp. Define the reconciliation window as [last_updated, today] per account.

Enumerate every unique ticker across all accounts.

Phase 2 -- Fetch corporate actions

The MCP server does NOT expose Ticker.actions directly (verified: 9 MCP tools, all get_*_info / get_historical_* variants). Use a Bash call into the MCP's own venv python:

# run via a Python env with yfinance available (e.g. the Yahoo Finance MCP venv)
python -c "
import yfinance as yf, json, sys, pandas as pd
ticker, since = sys.argv[1], sys.argv[2]  # since = YYYY-MM-DD
t = yf.Ticker(ticker)
df = t.actions  # DataFrame indexed by Date with Dividends, Stock Splits
df = df[df.index >= since]
out = [{'date': str(idx.date()), 'dividend': float(r.get('Dividends',0)), 'split': float(r.get('Stock Splits',0))}
       for idx, r in df.iterrows() if r.get('Dividends') or r.get('Stock Splits')]
print(json.dumps(out))
" {TICKER} {last_updated}

Per ticker event:

  • Non-zero Stock Splits → note ratio (e.g. 10.0 = 10:1 forward split).
  • Non-zero Dividends → per-share amount. Pull the ex-date price separately via mcp__yahoo-finance__get_historical_stock_prices for DRIP share-count math, and historical FX from CAD=X if a USD dividend lands in a CAD base-currency account (CRA rule).

Read the full file on GitHub · 138 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. 12d ago First seen · 138 lines · 49 tokens per session scan A 538635ae6900

Subscribe to this mod's changes

reconcile is a command published in the GitHub repository haiiibin/claude-multi-agent-investing (2 stars, last pushed 21d ago), licensed MIT. It adds 49 tokens to every session and 1,756 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.