log-an-expense

log-an-expense is a skill for Claude Code, Codex from akiotanaka847/qaio-desktop. It costs 139 tokens per session (2,395 once invoked), scanned A, original, MIT.

A draft accounting entry made from one forwarded receipt, such as an image, PDF, or email. It identifies the seller, date, amount, and line items, then assigns the expense to an account from your chart of accounts, the list of categories used in your books.

In plain words
What is it for?
Use it to record reimbursements, personal-card purchases, cash expenses, or other costs missing from bank and card feeds, individually or in batches.
Why use it?
It turns receipts into structured expense records and keeps uncertain classifications visible in Suspense instead of guessing. The resulting journal entry remains a draft for review.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to record reimbursements, personal-card purchases, cash expenses, or other costs missing from bank and card feeds, individually or in batches.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/akiotanaka847/qaio-desktop/log-an-expense
Install

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.

Any agent
npx skills add akiotanaka847/qaio-desktop --skill log-an-expense
Clone the repo
git clone --depth 1 https://github.com/akiotanaka847/qaio-desktop

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for log-an-expense

README.md
[![agentmods](https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/log-an-expense/github.svg)](https://agentmods.dev/skills/akiotanaka847/qaio-desktop/log-an-expense)
Your own site
<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/log-an-expense"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/log-an-expense/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.

agentmods 80×15 button for log-an-expense

Your own site · 80×15
<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/log-an-expense"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/log-an-expense.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 139 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,395 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00139 $0.02395
Opus 5 $0.00069 $0.01197
Sonnet 5 $0.00028 $0.00479
Haiku 4.5 $0.00014 $0.00239

Measured 10d ago against content hash f975bc305daa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

log-an-expense 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 10d 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.

store/agents/bookkeeping/.agents/skills/log-an-expense/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Log an Expense

One receipt in, one categorized expense and one balanced journal entry out. For founder reimbursements, out-of-pocket vendor payments, or any expense that didn't show up in the bank or card feed. Every receipt either produces a balanced journal entry with the account code validated against your chart of accounts, or lands in Suspense with the image attached.

Drafts only: the journal entry is written at status: "draft". I never auto-post to QuickBooks or Xero.

When to use

  • User forwards single receipt (image, PDF, email) or says "book this receipt" / "categorize this reimbursement".
  • Expense absent from bank / card feed (reimbursed on personal card, ACH paid from another entity, cash).
  • mode=batch - "process these 20 receipts for Q1" / "book founder's reimbursement batch" - produces one summary journal entry crediting Founder Loan Payable (or Accrued Reimbursements if same-period).

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.

  • Gmail or Outlook (inbox) — optional, lets me pull a forwarded receipt and its attachments straight from your email. If not connected, you can drop the file into chat or into the receipts inbox folder.
  • QuickBooks Online or Xero (accounting) — optional, used only if you want me to look up vendor history. The journal entry itself stays draft on disk; I never post.

This skill never blocks on a missing connection. You can always drop the receipt as a file.

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: every category I assign has to come from your chart of accounts. If missing I ask: "Do we have a chart of accounts yet? If not, let's draft one first."
  • A finished bookkeeping context — Required. Why: I need your accounting method and registered accounts to book the credit side correctly. If missing I ask: "Have we set up the books yet? If not, run the setup first."
  • The receipt itself — Required. Why: vendor, date, and total are extracted from it. If missing I ask: "Can you forward the receipt, drop the PDF or image, or paste the vendor / date / amount?"
  • How the expense was paid — Required. Why: drives the credit line (corp card vs. founder loan vs. cash). If missing I ask: "How was this paid, on a corporate card (which one?), a personal card you'll get reimbursed for, cash, or an ACH from another entity?"
  • A registered Founder Loan Payable account — Optional. Why: needed only if the receipt was paid out-of-pocket. If you don't have it I ask once and add it to your chart of accounts.

Read the full file on GitHub · 117 lines

Changes

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.

  1. 10d ago First seen · 117 lines · 139 tokens per session scan A f975bc305daa

Subscribe to this mod's changes

log-an-expense is a skill published in the GitHub repository akiotanaka847/qaio-desktop (2 stars, last pushed 7d ago), licensed MIT. It adds 139 tokens to every session and 2,395 once invoked, about $0.0007 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.