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.
npx agentmods add commands/michielinksee/bantou/correctgit clone --depth 1 https://github.com/michielinksee/bantouWrote 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.
[](https://agentmods.dev/commands/michielinksee/bantou/correct)<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>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.
| Model | Per session | Once 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 |
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.
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
- The correction is validated (correct category must be a valid 勘定科目)
- The original classification and the correction are logged
- The correction is stored in local memory (
~/.cockpit-mcp/memory.json) - 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:
- Edit
~/.cockpit-mcp/memory.jsondirectly - Or submit a new correction that overrides the previous one
Notes
- Including a reason with
--reasonhelps future auditing - Corrections with reasons are weighted higher in pattern matching
- The memory file can be backed up and shared across machines
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.
- 5d ago First seen · 69 lines · 13 tokens per session scan A b50dd449e2d7
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.
Other commands, from other repositories
ingest
Ingest financial data (bank/credit-card statements, CSV exports, receipts, or a plain-text description) into the book as validated double-entry transactions.
init
Initialise Countbean — connect to your hosted book (approving in the browser) or create a local one, plus a starter chart of accounts.
assess
Review the book and report what the numbers actually show — run rate, categories, changes, unusual entries, and gaps in the data.
connect
Connect Claude to your hosted Countbean book — approve it in your browser, or paste a key you already have.
report
Generate a financial report from the book — a styled HTML page and/or an Excel workbook (balance sheet, income statement, transactions).
status
Show the current state of your Countbean book — balances, net worth, account count, and recent changes.