correct

correct is a command for Claude Code from michielinksee/bantou. It costs 13 tokens per session (490 once invoked), scanned A, original, MIT.

A command for correcting an incorrectly classified accounting transaction and saving the correction for future matching transactions.

In plain words
What is it for?
Use it to change a transaction to the correct category, optionally record why, and apply the learned correction to future matching transactions across client companies.
Why use it?
It prevents the same vendor or transaction pattern from being repeatedly assigned the wrong accounting category.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the bantou plugin — 5 skills, 6 commands, 1 MCP server shipped together

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/michielinksee/bantou/correct
Clone the repo
git clone --depth 1 https://github.com/michielinksee/bantou

Made for: Claude Code.

Or install bantou, the plugin that ships this one along with the rest of its 5 skills, 6 commands, 1 MCP server.

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 correct

README.md
[![agentmods](https://agentmods.dev/badge/commands/michielinksee/bantou/correct.svg)](https://agentmods.dev/commands/michielinksee/bantou/correct)
Your own site
<a href="https://agentmods.dev/commands/michielinksee/bantou/correct"><img src="https://agentmods.dev/badge/commands/michielinksee/bantou/correct.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 490 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 5.1 $0.00013 $0.00490
Opus 5 $0.00006 $0.00245
Sonnet 5 $0.00003 $0.00098
Haiku 4.5 $0.00001 $0.00049

Measured 5d ago against content hash b50dd449e2d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

correct 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 5d 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.

packages/claude-for-jp-accounting/commands/correct.md · 69 lines

What it actually says

/bantou:correct

Submit a correction for a misclassified transaction. The correction is permanently stored in memory and applied to all future matches.

Usage

/jp-accounting:correct <transaction> --to <correct-category> [--reason <reason>]

Examples

/jp-accounting:correct "スタバ 渋谷店 ¥580" --to 会議費
/jp-accounting:correct "Zoom月額" --to 通信費 --reason "ビデオ会議サービスは通信費で統一"
/jp-accounting:correct "Amazon ¥12,000" --to 消耗品費 --reason "事務用品購入"

Input

  • transaction — The transaction description to correct (quoted string)
  • --to — The correct 勘定科目 (accounting category)
  • --reason — Optional reason for the correction (recommended)

What happens

  1. The correction is validated (correct category must be a valid 勘定科目)
  2. The original classification and the correction are logged
  3. The correction is stored in local memory (~/.cockpit-mcp/memory.json)
  4. All future transactions matching this vendor/pattern will use the corrected classification automatically

Correction scope

  • Corrections apply firm-wide across all client companies
  • The pattern extracted from the transaction description is normalized (e.g., branch names may be stripped for broader matching)
  • If a correction conflicts with a previous one, the user is prompted to resolve the conflict

Viewing corrections

To see all stored corrections, use the memory recall feature:

/jp-accounting:classify [vendor-name]

The classification output will show if a Memory hit was used and which correction it came from.

Undoing corrections

Corrections are permanent by default. To remove a correction:

  1. Edit ~/.cockpit-mcp/memory.json directly
  2. Or submit a new correction that overrides the previous one

Notes

  • Including a reason with --reason helps future auditing
  • Corrections with reasons are weighted higher in pattern matching
  • The memory file can be backed up and shared across machines
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. 5d ago First seen · 69 lines · 13 tokens per session scan A b50dd449e2d7

Subscribe to this mod's changes

correct is a command published in the GitHub repository michielinksee/bantou (2 stars, last pushed 14d ago), licensed MIT. It adds 13 tokens to every session and 490 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.