audit-my-books

audit-my-books is a skill for Claude Code, Codex from akiotanaka847/qaio-desktop. It costs 100 tokens per session (1,843 once invoked), scanned A, original, MIT.

A bookkeeping health check that reviews existing accounting records and produces a ranked list of issues. It can also prepare responses to auditor or business-review requests, but creates drafts rather than filing or posting anything.

In plain words
What is it for?
Use it to find uncategorized transactions, reconciliation breaks, old accruals, cutoff candidates, draft journal entries, missing opening balances, and duplicate vendors. It can also organize responses and samples for audits or diligence.
Why use it?
It helps find unresolved bookkeeping problems before they delay a financial close, tax handoff, audit, or investor review. Issues are prioritized by dollar impact, with one suggested item to close first.

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 find uncategorized transactions, reconciliation breaks, old accruals, cutoff candidates, draft journal entries, missing opening balances, and duplicate vendors. It can also organize responses and samples for audits or diligence.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/akiotanaka847/qaio-desktop/audit-my-books
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 audit-my-books
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 audit-my-books

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/audit-my-books"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/audit-my-books.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,843 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 $0.00100 $0.01843
Opus 5 $0.00050 $0.00922
Sonnet 5 $0.00020 $0.00369
Haiku 4.5 $0.00010 $0.00184

Measured 11d ago against content hash 50a10ecce765, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

audit-my-books 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.

store/agents/bookkeeping/.agents/skills/audit-my-books/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit My Books

Books-in-shape health check. I sweep every flat-at-root index and living register, rank findings by dollar impact, and call out the single most useful thing to close this week. Sub-mode mode=audit-response handles auditor or diligence requests with documented random seeds. Drafts only — never posted, never filed.

When to use

  • "are the books clean" / "what's uncategorized" / "books health check" / "punch list".
  • Called by hand-off-to-my-tax-preparer as gating step - open items must close before handoff proceed.
  • mode=audit-response - "respond to this audit request" / "diligence wants samples for Q2" / "walk the auditor through revenue recognition".

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.

  • No external connections required. I work entirely from your existing books, recon files, accruals, and journal entries. For mode=audit-response, if you want me to mirror the document bundle to a shared folder, connect Google Drive (optional).

This skill never blocks on a missing connection. Document bundles default to local folders; Drive mirror is a nice-to-have.

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 finished bookkeeping context and chart of accounts — Required. Why: I anchor the sweep on your accounting method, suspense code, and registered accounts. 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 before I look for issues."
  • A current run history — Required. Why: I need at least one categorized run period to sweep against. If missing I ask: "Have you processed any statements yet? Drop your most recent bank or credit card statements and I'll work from there."
  • Your auditor or diligence request, in mode=audit-response — Required for that mode. Why: I can't sample or assemble without the actual ask. If missing I ask: "Paste or drop the request from the auditor or diligence team, ideally the full email or PDF with the items they want."

Read the full file on GitHub · 89 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. 11d ago First seen · 89 lines · 100 tokens per session scan A 50a10ecce765

Subscribe to this mod's changes

audit-my-books is a skill published in the GitHub repository akiotanaka847/qaio-desktop (2 stars, last pushed 8d ago), licensed MIT. It adds 100 tokens to every session and 1,843 once invoked, about $0.0005 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.