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 akiotanaka847/qaio-desktop --skill categorize-my-transactionsgit clone --depth 1 https://github.com/akiotanaka847/qaio-desktopWrote 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/akiotanaka847/qaio-desktop/categorize-my-transactions)<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/categorize-my-transactions"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/categorize-my-transactions/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/akiotanaka847/qaio-desktop/categorize-my-transactions"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/categorize-my-transactions.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 | $0.00123 | $0.02248 |
| Opus 5 | $0.00062 | $0.01124 |
| Sonnet 5 | $0.00025 | $0.00450 |
| Haiku 4.5 | $0.00012 | $0.00225 |
Grade A, and why
categorize-my-transactions 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 11d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Categorize My Transactions
The ongoing companion to the statements pipeline: I take pending transactions from your QuickBooks or Xero queue, a CSV, or a pasted table, and produce a review-ready batch grouped into Ready, Needs Review, and Suspense. Two invariants: your chart of accounts is locked for the run, and anything below 0.90 confidence goes to Suspense rather than silent pushthrough.
Drafts only: I categorize, flag, and write the review batch. You or your accountant post to QuickBooks or Xero.
When to use
- "categorize these pending transactions" / "review QuickBooks Online's pending queue" / "clean up Xero's uncategorized tray".
- Fresh CSV of pending items dropped at agent root or
transactions/_inbox/. mode=rule-add- "make 'Stripe Fee' always go to 6700 going forward" / "lock 'AWS' to 6210 so you stop asking".- Called by
process-my-statementsat end-of-run for rows that came outuncategorized- optional handoff.
Connections I need
I run external work through Composio. Before this skill runs I check that the categories below are linked. Missing → I name the category, ask you to connect it from the Integrations tab, stop.
- QuickBooks Online or Xero (accounting) — preferred source for the live pending / uncategorized queue. Required if you want me to pull pending items directly.
- Stripe (billing) — optional, helps me categorize processor fees and payouts when they show up in the queue.
If no accounting tool is connected I fall back to a dropped CSV or pasted table. If you have nothing to share I stop and ask you to connect QuickBooks or Xero, or drop a CSV of pending items.
Information I need
I read your bookkeeping context first. For every required field that's missing I ask ONE plain-language question (best modality: connected app > file drop > URL > paste) and wait.
- A chart of accounts — Required. Why: I lock it during the run; every category I assign has to come from your chart of accounts, never invented. If missing I ask: "Do we have a chart of accounts yet? If not, let's draft one first, it only takes a few minutes."
- A finished bookkeeping context — Required. Why: I need your accounting method, suspense code, and registered accounts to categorize correctly. If missing I ask: "Have we set up the books yet? If not, run the setup once so I know your fiscal year, accounting method, and registered accounts."
- The pending transactions to review — Required. Why: I can't categorize what I can't see. If missing I ask: "Where are the pending transactions, in QuickBooks or Xero, in a CSV you can drop, or pasted into chat?"
- Vendor rules from a prior period — Optional. Why: lets me match new charges to known vendors and skip asking you the same question twice. If you don't have it I keep going and learn from this run.
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.
- 11d ago First seen · 103 lines · 123 tokens per session scan A 8d74c66ecfbc
categorize-my-transactions is a skill published in the GitHub repository akiotanaka847/qaio-desktop (2 stars, last pushed 7d ago), licensed MIT. It adds 123 tokens to every session and 2,248 once invoked, about $0.0006 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 skills, from other repositories
assess
A Japanese tax-filing assessment guide that asks about your income, family, and business situation to identify which tax returns you may need.
setup
A setup wizard for shinkoku, a Japanese tax-filing tool. It creates or updates the configuration file and initializes the tool’s database.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.
tax-advisor
A Japanese tax-advice skill based on 2025 tax rules. It answers tax-filing and tax-saving questions using documents in a reference folder rather than general guesses.
e-bookkeeping-compliance
A compliance checker for Japan's rules on keeping high-quality electronic accounting books. It checks whether accounting records and related documentation meet specified requirements for electronic storage.
incorporation
A guide for moving from working as an individual business owner to operating through a company in Japan. It covers company types, setup steps, officer pay, taxes, and social insurance.