cowork-tax-prep-organizer

cowork-tax-prep-organizer is a skill for Claude Code, Codex from OneWave-AI/claude-skills. It costs 54 tokens per session (782 once invoked), scanned A, original, MIT.

A document-organizing workflow that finds tax records in folders and downloads, identifies them by contents, and prepares a package for a certified public accountant. It organizes paperwork but does not calculate taxes or give tax advice.

In plain words
What is it for?
Use it to collect and organize forms such as W-2s, 1099s, 1098s, K-1s, receipts, payment confirmations, and prior tax returns. It can flag duplicates, documents from the wrong tax year, and items to ask your accountant about.
Why use it?
It replaces manual searching and sorting with a checklist of expected forms, a clean copy of the documents, and a list of missing or questionable items.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: model in frontmatter.

Good fit Use it to collect and organize forms such as W-2s, 1099s, 1098s, K-1s, receipts, payment confirmations, and prior tax returns. It can flag duplicates, documents from the wrong tax year, and items to ask your accountant about.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/onewave-ai/claude-skills/cowork-tax-prep-organizer
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 OneWave-AI/claude-skills --skill cowork-tax-prep-organizer
Clone the repo
git clone --depth 1 https://github.com/OneWave-AI/claude-skills

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 cowork-tax-prep-organizer

README.md
[![agentmods](https://agentmods.dev/badge/skills/onewave-ai/claude-skills/cowork-tax-prep-organizer/github.svg)](https://agentmods.dev/skills/onewave-ai/claude-skills/cowork-tax-prep-organizer)
Your own site
<a href="https://agentmods.dev/skills/onewave-ai/claude-skills/cowork-tax-prep-organizer"><img src="https://agentmods.dev/badge/skills/onewave-ai/claude-skills/cowork-tax-prep-organizer/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 cowork-tax-prep-organizer

Your own site · 80×15
<a href="https://agentmods.dev/skills/onewave-ai/claude-skills/cowork-tax-prep-organizer"><img src="https://agentmods.dev/badge/skills/onewave-ai/claude-skills/cowork-tax-prep-organizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 782 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00054 $0.00782
Opus 5 $0.00027 $0.00391
Sonnet 5 $0.00011 $0.00156
Haiku 4.5 $0.00005 $0.00078

Measured 12d ago against content hash bcc5905c460b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

cowork-tax-prep-organizer 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.

cowork-tax-prep-organizer/SKILL.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cowork Tax Prep Organizer

Do the part of tax season that actually eats the weekend: finding, identifying, and organizing the documents. Input: one or more folders (Downloads, a documents dump, last year's tax folder for reference). Output: an organized package a CPA can work from and a precise list of what is still missing. This skill organizes; it does not compute taxes or give tax advice.

Workflow

  1. Build the personal checklist. From last year's return or folder (if provided) and a few questions (W-2 employment? contract income? brokerage accounts? mortgage? dependents? business entity?), build the expected-documents list: W-2s, 1099-NEC/MISC/INT/DIV/B/R, 1098s, K-1s, property tax bills, charitable receipts, estimated-payment confirmations, prior-year return.
  2. Sweep. Walk the folders and identify every tax-relevant document by content, not just filename -- payers, form types, tax year. Match each to the checklist. Flag wrong-year documents (the 2024 1099 hiding in the 2025 pile) and duplicates (the same W-2 downloaded three times).
  3. Organize. On approval, copy -- never move -- into a clean structure: tax-2025/income/, deductions/, investments/, business/, prior-year/, with names like 1099-nec-acme-corp-2025.pdf. Write INDEX.md mapping checklist to files.
  4. Chase list. Output what is expected but missing, with where it likely lives ("Interest income appeared last year from Chase -- no 1099-INT found; check the bank's tax documents page, typically posted by Jan 31"). Sort by what blocks filing vs. nice-to-have.
  5. Ask-your-CPA list. Flag items a preparer should look at -- not conclusions: home-office-looking expenses for the self-employed, a brokerage form showing wash-sale codes, K-1 arrived vs. expected, estimated payments that do not sum to the notes. Phrase each as a question for the professional.

Rules

  • Never compute tax liability, deductions, or refunds. Identify, organize, and question -- the CPA concludes.
  • Copy, never move. Source folders stay intact.
  • Tax year discipline: every document is tagged with its year, and wrong-year files are quarantined in the report, not the package.
  • "MISSING" means "not found in the provided folders" -- state what was searched.
  • Treat everything as sensitive: no SSNs, account numbers, or dollar amounts in console output or digests; specifics live only in the package files.
  • If both spouses' or multiple entities' documents are mixed, separate them explicitly and confirm the split before organizing.

Read the full file on GitHub · 39 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 · 39 lines · 54 tokens per session scan A bcc5905c460b

Subscribe to this mod's changes

cowork-tax-prep-organizer is a skill published in the GitHub repository OneWave-AI/claude-skills (291 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 782 once invoked, about $0.0003 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 2026-08-30.