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 CPUtester5465/countbean-plugin --skill countbean-accountinggit clone --depth 1 https://github.com/CPUtester5465/countbean-pluginWrote 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/cputester5465/countbean-plugin/countbean-accounting)<a href="https://agentmods.dev/skills/cputester5465/countbean-plugin/countbean-accounting"><img src="https://agentmods.dev/badge/skills/cputester5465/countbean-plugin/countbean-accounting/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/cputester5465/countbean-plugin/countbean-accounting"><img src="https://agentmods.dev/badge/skills/cputester5465/countbean-plugin/countbean-accounting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00054 | $0.01320 |
| Opus 5 | $0.00027 | $0.00660 |
| Sonnet 5 | $0.00011 | $0.00264 |
| Haiku 4.5 | $0.00005 | $0.00132 |
Grade A, and why
countbean-accounting 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 9d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing correct books in a Countbean book
A Countbean book is a Beancount ledger. Every write goes through the MCP server, which runs
bean-check and only commits valid, balancing entries. Your job is to produce correct Beancount
syntax so writes are accepted the first time.
The five account types
Every account starts with one of these roots. Sign convention matters:
| Root | Normal balance | Goes up when… |
|---|---|---|
Assets |
positive (debit) | money comes in (cash, bank, receivables) |
Liabilities |
negative (credit) | you owe more (credit card, loans) |
Equity |
negative (credit) | opening balances, retained earnings |
Income |
negative (credit) | you earn (income is recorded as a negative number) |
Expenses |
positive (debit) | you spend |
Accounts are Colon:Separated:Title-Case, each segment starting with a capital letter or digit,
e.g. Assets:Checking, Expenses:Food:Groceries, Income:Consulting, Liabilities:Visa.
The one rule: postings must sum to zero
Each transaction has ≥2 postings that net to zero. You can leave one posting's amount blank and Beancount infers it.
2026-08-01 * "Blue Bottle" "Oat latte"
Expenses:Coffee 6.50 USD
Assets:Checking -6.50 USD
Income example — note the negative on the Income leg:
2026-08-01 * "Stripe" "Invoice #204"
Assets:Checking 1800.00 USD
Income:Consulting ; inferred as -1800.00 USD
Paying a credit card (transfer between two of your accounts, no income/expense):
2026-08-02 * "Payment — Visa"
Liabilities:Visa 300.00 USD
Assets:Checking -300.00 USD
Flags
*= cleared/confirmed. Use for anything you're sure about.!= pending/needs review. Use when a category is a guess or a match is uncertain — this surfaces it in Fava and in reports instead of silently guessing wrong.
Opening accounts
Open an account before it's first used (the server routes open directives automatically):
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.
- 9d ago First seen · 125 lines · 54 tokens per session scan A b0b097967c1a
countbean-accounting is a skill published in the GitHub repository CPUtester5465/countbean-plugin (45 stars, last pushed 13d ago), licensed MIT. It adds 54 tokens to every session and 1,320 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
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…
bukio-cli
Drive bukio-cli — agent-first double-entry bookkeeping for SMEs across eleven jurisdictions. Book invoices, archive the originals, keep the books balanced.
ledger
Use for ANY monetary, accounting, ledger, journal, balance, P&L, fee, FX, invoice, tax, cost-basis, or valuation work. Exact Money.from (never floats or parseFloat), double-entry via JournalEntry + validateEntry + Ledger.apply, MCP moneycompute / ledgerpost, canon citations, Zero-Skip + Canonical Financial Artifact.…
ledger-audit
Whole-repo financial audit. Use for ledger-audit, financial audit, or /ledger-audit. Scan for non-kernel money math, reconstruct flows as JournalEntry sequences, prove with validateEntry + Ledger.apply + runTrace + auditHash.
ledger-verify
Verify a diff, file, or snippet against ledger invariants. Use when asked to ledger-verify, check for floats, find unbalanced entries, prove a journal, or before committing money code. Enforces Money.from, validateEntry, Ledger.apply, citations. CLI: npx ledger-verify --scan .
full-engagement-pipeline
Default for throw-work: dump a folder, "do the accounting", "sort my books", year end, prepare financial statements / MPERS pack without naming a stage. One intake then books; resumes from engagementstate.json. Depth-scoped done.