money-setup

A setup command for money-map, which analyzes bank or card CSV exports without connecting to the bank, and creates categories and matching rules.

In plain words
What is it for?
Use it to prepare money-map for a sample export, confirm its column layout, create the rules file, and tailor starter merchant rules.
Why use it?
It removes the guesswork of mapping unfamiliar columns and deciding how transaction descriptions should be categorized.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/localplugins/plugins/money-setup
Clone the repo
git clone --depth 1 https://github.com/localplugins/plugins
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 207 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00023 $0.00207
Opus 5 $0.00012 $0.00103
Sonnet 5 $0.00005 $0.00041
Haiku 4.5 $0.00002 $0.00021

Measured yesterday against content hash 367c6fac0f34, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

money-setup 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 yesterday.

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.

money-map/commands/money-setup.md · 18 lines

What it actually says

Money Setup

Configure money-map. Arguments: $ARGUMENTS

Steps

  1. If a sample CSV is given, apply the statement-parsing skill to detect its column mapping and show it to the user to confirm.
  2. Create money/categories.json from this plugin's templates/categories.json if it doesn't exist. Never overwrite an existing one without confirming.
  3. Using the categorization skill, tailor the starter rules to what you see in the sample (add obvious merchant→category rules), and confirm with the user.
  4. Tell the user they can edit money/categories.json anytime and commit it to share rules with a team.
  5. Remind them: money-map reads only the files they provide and never connects to the internet or their bank.

Never access the network.

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. yesterday First seen · 18 lines · 23 tokens per session scan A 367c6fac0f34

Subscribe to this mod's changes

money-setup is a command published in the GitHub repository localplugins/plugins (5 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 207 once invoked, about $0.0001 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.