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 skills add michielinksee/bantou --skill correction-memorygit 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/skills/michielinksee/bantou/correction-memory)<a href="https://agentmods.dev/skills/michielinksee/bantou/correction-memory"><img src="https://agentmods.dev/badge/skills/michielinksee/bantou/correction-memory/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.
<a href="https://agentmods.dev/skills/michielinksee/bantou/correction-memory"><img src="https://agentmods.dev/badge/skills/michielinksee/bantou/correction-memory.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00029 | $0.00647 |
| Opus 5.5 | $0.00012 | $0.00259 |
| Sonnet 5.5 | $0.00006 | $0.00129 |
| Haiku 4.5 | $0.00003 | $0.00065 |
Grade A, and why
correction-memory 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Correction Memory
Persistent memory system that learns from tax accountant corrections. Every correction is permanently stored and never repeated. This is the core differentiator of the plugin — it gets smarter with every use.
When to use
Invoke this skill when:
- A tax accountant corrects a classification ("this should be 交際費, not 会議費")
- The user wants to check what past corrections exist for a vendor
- The system needs to recall learned patterns during classification
How it works
Correction flow
- Tax accountant reviews a classification result
- If incorrect, they submit a correction with:
- Original classification
- Correct classification (勘定科目 + 税区分)
- Reason for correction (optional but valuable)
- The correction is stored in local memory permanently
- All future transactions matching the same pattern use the corrected classification automatically (Memory hit in Stage 1)
Pattern matching
Corrections are stored as vendor/description patterns. When a new transaction arrives, the memory is queried for matches:
- Exact vendor name match ("スタバ 渋谷店" matches "スタバ 渋谷店")
- Normalized vendor match ("スタバ" matches any Starbucks location)
- Description keyword match (configurable per correction)
Cross-client application
Corrections apply across all client companies in the firm. If a tax accountant corrects "Zoom" from 通信費 to 支払手数料 for Client A, that correction automatically applies to Clients B, C, etc.
This is intentional — accounting conventions are firm-level decisions, not per-client. Individual client overrides are supported but rare.
Storage location
Memory is stored locally at ~/.cockpit-mcp/memory.json. This is
fully local — no data is sent to any cloud service.
The memory file is human-readable JSON and can be manually edited, backed up, or transferred between machines.
Cost reduction over time
As Memory accumulates corrections, the proportion of transactions handled by Stage 1 (free, instant) increases while Stage 2 (API call, costs tokens) decreases. Typical trajectory:
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.
- 2mo ago First seen · 82 lines · 29 tokens per session scan A d6cba21182bd
correction-memory is a skill published in the GitHub repository michielinksee/bantou (2 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 647 once invoked, about $0.0001 per session on Opus 5.5. 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 skills, from other repositories
accounting-audit-system-builder
Routes an accounting or audit request to the right module skill, from software selection through monthly closing, asking only what is missing. Use for books of accounts or audit files.
bookkeeping
Use when a small business needs audit-ready books — a chart of accounts, posting a transaction to the right account and side, clearing an uncategorized bank feed, cash vs accrual, or a ledger that won't tie to the bank. NOT interpreting the numbers — runway, burn, P&L cadence (that is finance-ops), NOT issuing…
countbean-accounting
Rules for writing correct double-entry Beancount transactions when managing a Countbean cloud book — account naming, how to balance postings, categorisation, and safe ingestion. Use whenever recording, importing, or correcting financial data in a Countbean book.
jaz-cli
Use this skill when running Clio CLI commands, building shell scripts with Clio, debugging auth issues, understanding --json output, paginating results, or chaining multi-step accounting workflows from the terminal. Covers auth precedence, output formats, entity resolution, and common workflow patterns. Also use when…
jaz-recipes
Use this skill when modeling complex multi-step accounting transactions: anything that spans multiple periods, involves changing amounts, or requires linked entries. Covers 16 IFRS-compliant recipes (prepaid amortization, deferred revenue, loans, IFRS 16 leases, hire purchase, fixed deposits, asset disposal, FX…
jangbu-jongso
A Korean tax-document checklist generator for individuals, freelancers, sole-company owners, mixed earners, and certain business owners.