clean

A cleaning command that combines bank or card CSV exports into one consistently formatted, categorized file.

In plain words
What is it for?
Use it to produce an analysis-ready categorized.csv with shared columns such as date, description, amount, category, account, and source file.
Why use it?
It handles different date and amount formats while showing rows that could not be read or were unclear, rather than dropping them.

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/clean
Clone the repo
git clone --depth 1 https://github.com/localplugins/plugins
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 184 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 $0.00017 $0.00184
Opus 5 $0.00009 $0.00092
Sonnet 5 $0.00003 $0.00037
Haiku 4.5 $0.00002 $0.00018

Measured yesterday against content hash 8a4581e2fb50, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clean 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/clean.md · 17 lines

What it actually says

Clean

Produce one tidy dataset from raw exports. Arguments: $ARGUMENTS

Workflow

  1. Parse each input with the toolkit's parse_report (map columns via statement-parsing); dates and amounts are normalized through Decimal.
  2. Categorize with the rules in money/categories.json.
  3. Write a single categorized.csv to money/output/<name>/ with consistent columns (date, description, amount, category, account, source-file).
  4. Collect .skipped from every input — rows that couldn't be parsed (malformed amount/date) or were ambiguous (both debit and credit populated). List them for the user to fix — never drop or fabricate them silently.

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 · 17 lines · 17 tokens per session scan A 8a4581e2fb50

Subscribe to this mod's changes

clean is a command published in the GitHub repository localplugins/plugins (5 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 184 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.