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.
git 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/commands/cputester5465/countbean-plugin/report)<a href="https://agentmods.dev/commands/cputester5465/countbean-plugin/report"><img src="https://agentmods.dev/badge/commands/cputester5465/countbean-plugin/report/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/commands/cputester5465/countbean-plugin/report"><img src="https://agentmods.dev/badge/commands/cputester5465/countbean-plugin/report.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 | $0.00026 | $0.00531 |
| Opus 5.5 | $0.00010 | $0.00212 |
| Sonnet 5.5 | $0.00005 | $0.00106 |
| Haiku 4.5 | $0.00003 | $0.00053 |
Grade A, and why
report 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 26d 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
Generate a report from the user's Countbean book. Arguments: $ARGUMENTS
(first token = format: html, excel/xlsx, or both — default both; second token = optional
as-of date YYYY-MM-DD, default today; third token = optional first day of the income statement
YYYY-MM-DD, default 1 January of the as-of year).
-
Confirm the book has data by calling
book_status. If it's empty, tell the user to/countbean:ingestsome data first, and stop. -
Generate the requested format(s) by calling
generate_report:- HTML →
generate_report(format="html", as_of=<date or "">, period_start=<date or "">) - Excel →
generate_report(format="xlsx", as_of=<date or "">, period_start=<date or "">) both→ call it twice.
- HTML →
-
Each call returns a file path (under the book's
reports/folder). Report the exact path(s) to the user.- For the HTML report, offer to open it in the browser, and if the user is on a desktop,
you may run
!open "" 2>/dev/null || xdg-open "" 2>/dev/null`` to open it. - For the Excel report, tell them it has four sheets: Balance sheet, Income statement,
Transactions, and To check (the entries flagged
!, waiting for an answer). - The income statement covers the period only (year to date unless a start was given); the balance sheet is cumulative, and carries earlier years' profit as an Equity row "Retained earnings (before )". Amounts with no price into the book's currency are listed as "not converted" and are in no total — if there are any, say so and name them.
- For the HTML report, offer to open it in the browser, and if the user is on a desktop,
you may run
-
Give a short written summary of the headline numbers (net worth, net income for the period) drawn from
book_statusso they get the gist without opening the file.
Keep it concise. Do not recompute the numbers yourself — the server's report is the source of truth.
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.
- 26d ago Changed b60b807c5356
- 28d ago Changed · +5 lines 684660566f01
- 1mo ago First seen · 29 lines · 26 tokens per session scan A 4c8907363c3d
report is a command published in the GitHub repository CPUtester5465/countbean-plugin (34 stars, last pushed 18d ago), licensed MIT. It adds 26 tokens to every session and 531 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 2026-08-30.
Other commands, from other repositories
import
A command that imports CSV files exported by Japanese accounting software and automatically classifies their transactions. CSV is a plain-text table format commonly used to move data between programs.
audit
Scan for non-kernel money math. Rebuild critical flows as JournalEntrys. Replay and prove. Complements /ledger-verify.
reconcile
Assumptions → Money.from → cited, balanced JournalEntry → Ledger.apply. Output entries + proof.
report
A command that creates a monthly closing report for a client company. Monthly closing is the accounting process of summarizing and reviewing a month's transactions.
budget
Grant budget spreadsheet generation with forcing questions and task integration.
workbook
List, read, create, or template-populate deal-scoped OloLand workbooks for analysis handoff.