hand-off-to-my-tax-preparer

hand-off-to-my-tax-preparer is a skill for Claude Code, Codex from akiotanaka847/qaio-desktop. It costs 156 tokens per session (2,577 once invoked), scanned A, original, MIT.

A year-end folder of financial records for a tax preparer, such as a CPA. It is assembled only after an audit finds no open bookkeeping issues and remains a draft handoff rather than a tax filing.

In plain words
What is it for?
Use it to assemble a trial balance, account reconciliations, fixed-asset and depreciation schedules, 1099 information, research-and-development classifications, and possible tax adjustments.
Why use it?
It gathers the supporting schedules and reconciliations in one place so your preparer can review the company's year-end numbers.

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 assemble a trial balance, account reconciliations, fixed-asset and depreciation schedules, 1099 information, research-and-development classifications, and possible tax adjustments.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/akiotanaka847/qaio-desktop/hand-off-to-my-tax-preparer
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 hand-off-to-my-tax-preparer
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 hand-off-to-my-tax-preparer

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/hand-off-to-my-tax-preparer"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/hand-off-to-my-tax-preparer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 156 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,577 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 $0.00156 $0.02577
Opus 5 $0.00078 $0.01288
Sonnet 5 $0.00031 $0.00515
Haiku 4.5 $0.00016 $0.00258

Measured 12d ago against content hash 844dcd23cff7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

hand-off-to-my-tax-preparer 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 12d 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/hand-off-to-my-tax-preparer/SKILL.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hand Off to My Tax Preparer

Year-end tax handoff package. Gated by audit-my-books — books must be clean first. Once clean, I assemble the full tax tie-out under handoffs/tax-{year}/, optionally mirror it to Google Drive, and draft the email to your preparer with the folder link. Never filed, never sent.

When to use

  • "close the year for the tax preparer" / "prep the tax tie-out" / "hand off to our CPA" / "year-end package for tax".
  • Run once per fiscal year, after final month's close-my-month completes.

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.

  • Google Drive (files) — optional, lets me mirror the entire handoff folder into a shared location your tax preparer can view. If not connected I keep the package local.
  • Gmail or Outlook (inbox) — optional, lets me create a draft email to your tax preparer with the package link. I never send. If not connected I write the email text to a draft file instead.

If you want both the Drive mirror and the email draft and neither is connected, I name both categories and ask you to link the one you'd rather 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.

  • The fiscal year you're handing off — Required. Why: defines the date range for trial balance and supporting schedules. If missing I ask: "Which tax year are we handing off, the most recently completed one?"
  • Tax preparer name and email — Required. Why: drops into the cover memo and the email draft. If missing I ask: "Who's filing your return this year, name and email so I can address the package to them?"
  • Whether you're claiming the R&D credit — Required. Why: if yes, I include the R&D classification in the package. If missing I ask: "Are you planning to claim the federal R&D credit this year, yes, no, or undecided?"
  • A capitalized fixed-asset list — Optional. Why: drives the depreciation schedule. If you don't have any capitalized assets I skip that section. If missing I ask: "Do you have any capitalized fixed assets (laptops bought as assets, equipment, leasehold improvements)? If you don't have it I keep going without a depreciation schedule."
  • Clean monthly closes through year-end — Required. Why: the handoff is gated on books being clean; open recon breaks and uncategorized items have to close first. If missing I ask: "Have we closed every month of the fiscal year yet? If not, let's finish those first, otherwise the handoff has too many open items."

Read the full file on GitHub · 183 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. 12d ago First seen · 183 lines · 156 tokens per session scan A 844dcd23cff7

Subscribe to this mod's changes

hand-off-to-my-tax-preparer is a skill published in the GitHub repository akiotanaka847/qaio-desktop (2 stars, last pushed 8d ago), licensed MIT. It adds 156 tokens to every session and 2,577 once invoked, about $0.0008 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.