Agent skill

Tax Cases

by filedcom in filedcom/opentax

Generate realistic benchmark cases from IRS-published sources (VITA exercises, Pub 17 examples, MeF test cases).

AGPL-3.0Auto-check passedTesting & QA

Install Tax Cases

skills CLI
$ npx skills add filedcom/opentax --skill tax-cases -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install filedcom/opentax tax-cases --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/filedcom/opentax.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/tax-cases .claude/skills/tax-cases && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
tax-cases
GitHub stars
108
Token cost
~923 tokens
SKILL.md length
419 words
Files
3
Skills in repo
8
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Generate realistic benchmark cases from IRS-published sources (VITA exercises, Pub 17 examples, MeF test cases).

  • Works in 7 steps: Derive Paths → Determine Source → Spawn IRS Sourcer Agent → …
  • Tasks that involve Test generation
  • SKILL.md covers Overview, Step 0 — Derive Paths, Step 1 — Determine Source and Step 2 — Spawn IRS Sourcer Agent, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Tax Cases is an agent skill from filedcom/opentax. Generate realistic benchmark cases from IRS-published sources (VITA exercises, Pub 17 examples, MeF test cases). Correct values come directly from IRS publications — no reference calculator involved.

Its SKILL.md is about 920 tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `agents/case-writer.md` and `agents/irs-sourcer.md`).

It sits in Testing & QA, covering Test generation. The repository describes itself as: Fully open-source US federal tax engine. Single binary cli. Runs on macOS, Linux, and Windows. Built for AI agents using AI agents. The licence is AGPL-3.0.

When your agent uses it

  • Tasks that involve Test generation

Example prompts

  • “/tax-cases”

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. Derive Paths
  2. Determine Source
  3. Spawn IRS Sourcer Agent
  4. Determine Next Case Number
  5. Spawn Case Writer Agents
  6. Verify Cases
  7. Report

What it can do on your machine

Read from SKILL.md and the folder at commit 0c6ae76. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Tax Cases loads about 923 tokens when it runs. Until then it costs about 52 tokens; SKILL.md has 419 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~52
When it runs · the whole SKILL.md, loaded when a task matches
~923

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from filedcom/opentax at commit 0c6ae76, republished under its AGPL-3.0 licence (© filedcom). 419 words, ~923 tokens.

Download SKILL.mdSave it as .claude/skills/tax-cases/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
tax-cases
description
Generate realistic benchmark cases from IRS-published sources (VITA exercises, Pub 17 examples, MeF test cases). Correct values come directly from IRS publications — no reference calculator involved.

Tax Cases — IRS-Sourced Benchmark Generator

Source: $ARGUMENTS (e.g. vita, pub17, mef, or a free-form description like "senior with SSA and 1099-R")

Overview

Generates new benchmark cases where the correct values are sourced directly from IRS publications. No computed ground truth — the IRS numbers are the ground truth.

Step 0 — Derive Paths

Parse $ARGUMENTS for an optional {form}:{year} prefix (e.g. f1040:2025 vita). Extract:

  • form — defaults to f1040 if not specified
  • year — defaults to 2025 if not specified
  • remaining tokens → source argument for Step 1

Cases directory: benchmark/cases/{form}/{year}/

Read docs/architecture/STRUCTURE.md to confirm paths are still current. If STRUCTURE.md differs, use those paths.

Step 1 — Determine Source

Parse $ARGUMENTS:

  • vita → VITA Pub 4491 training exercises (best coverage, verified by IRS)
  • pub17 → Publication 17 "Your Federal Income Tax" worked examples
  • mef → IRS MeF (Modernized e-File) software developer test cases
  • anything else → treat as a scenario description, use vita as primary source

If no argument, default to vita.

Step 2 — Spawn IRS Sourcer Agent

Spawn one agent using agents/irs-sourcer.md. Pass:

  • Source type / description: $ARGUMENTS
  • Output path: .state/bench/irs-cases-raw.json

Wait for completion. Verify the file exists and contains a cases array with at least one entry.

If sourcer finds no usable cases, stop and report which sources were tried.

Step 3 — Determine Next Case Number

Read the benchmark/cases/ directory. Find the highest existing case number (e.g. 97 → next is 98).

Show full SKILL.md (196 more words)Show less

Step 4 — Spawn Case Writer Agents

Read .state/bench/irs-cases-raw.json. For each raw case in the cases array, spawn one case-writer agent in parallel using agents/case-writer.md. Pass:

  • The raw case object (scenario description, form values, IRS-provided correct values, source citation)
  • The next available case number (increment per case: 98, 99, 100, …)
  • Cases directory: benchmark/cases/

Spawn ALL case-writer agents in a single message (parallel).

Wait for all to complete.

Step 5 — Verify Cases

For each newly created case directory, verify:

  1. input.json exists and is valid JSON with a forms array
  2. correct.json exists and has correct.line24_total_tax, correct.line35a_refund, correct.line37_amount_owed
  3. correct.json has a source field citing the IRS publication, exercise number, and page

Report any cases that failed verification. Do NOT run the benchmark — that's for /tax-fix after cases are added.

Step 6 — Report

Print a summary:

Cases added: N (cases 98–105)
Source: VITA Pub 4491 TY2025

New cases:
  98-[name]   Single, W-2 + interest   IRS VITA Ex. 3
  99-[name]   MFJ, retirement + SSA    IRS VITA Ex. 7
  ...

Next step: run /tax-fix to see how the engine performs on these cases.

Append to .state/bench/progress.md:

## Cases Added — [timestamp]
- Source: [source]
- Cases: [list with numbers and names]
- IRS citations: [list]

Key Constraints

  • Every correct value must be traceable to an IRS publication page/exercise — no computed values
  • If an IRS example is ambiguous or the publication doesn't give a specific line value, omit that field from correct (the benchmark only requires the three pass/fail fields)
  • Do NOT delete or modify existing cases
  • Do NOT run gen_correct.ts — it no longer exists

© filedcom, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files in .claude/skills/tax-cases of filedcom/opentax.

  • SKILL.md
  • agents/case-writer.md
  • agents/irs-sourcer.md

Open the folder on GitHubat commit 0c6ae76

Compare with similar skills

Tax Cases next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Tax Cases compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Tax Cases this skillfiledcom/opentax108—~923Automated safety check: PassAGPL-3.0
Emcaklofas/kicad-happy1.4k1 repos~2.8kAutomated safety check: PassMIT
Swig Testswig/swig6.3k—~2.3kAutomated safety check: PassCustom licence
Generate Test Cases342164796/generate-test-cases1191 repos~2.9kAutomated safety check: PassNone
Verify Cc Safety Netkenryu42/cc-safety-net1.6k—~2kAutomated safety check: PassMIT
Wioworkersio/skills190—~5.8kAutomated safety check: PassMIT

Similar skills

  • Emc

    aklofas/kicad-happy

    EMC pre-compliance risk analysis for KiCad PCB designs — 18 check categories, 44 rule IDs covering ground planes, decoupling, I/O filtering, switching harmonics, clock routing, differential pair…

    1.4k GitHub starsUsed in 1 repo~2.8k tokens
    Testing & QAAuto-check passed
  • Swig Test

    swig/swig

    Run SWIG test suite for specific languages. An agent skill from swig/swig.

    6.3k GitHub stars~2.3k tokensUpdated yesterday
    Testing & QAAuto-check passed
  • Generate Test Cases

    342164796/generate-test-cases

    自主学习型测试文档生成器。从需求文档(Markdown)生成测试用例 XMind 文件,支持持久化记忆和持续学习。当用户提到"生成测试用例"、"根据需求生成测试"时触发。

    119 GitHub starsUsed in 1 repo~2.9k tokens
    Testing & QAAuto-check passed
  • Verify Cc Safety Net

    kenryu42/cc-safety-net

    Launch and drive the real cc-safety-net CLI — the hook decision path, explain, status/doctor, logs, and the local policy GUI — against an isolated home, capturing evidence.

    1.6k GitHub stars~2k tokensUpdated today
    Testing & QAAuto-check passed
  • Wio

    workersio/skills

    Testing workflow skill for finding high-value test candidates, writing focused tests, generating realistic workloads, reviewing test value, and diagnosing test-suite health.

    190 GitHub stars~5.8k tokensUpdated 2 mo ago
    Testing & QAAuto-check passed
  • File Server

    microsoft/WindowsProtocolTestSuites

    Official

    ALWAYS LOAD THIS SKILL when working with FileServer, SMB, SMB2, SMB3, CIFS, file sharing, MS-SMB2, MS-FSCC, MS-FSA, MS-DFSC, MS-FSRVP, MS-RSVD, MS-SQOS, or any file server protocol test…

    567 GitHub stars~4.1k tokensUpdated 22 days ago
    Testing & QAAuto-check passed

More from filedcom/opentax

All 8 skills in this repo
  • Audit Harness

    filedcom/opentax

    Generic audit/fix loop. An agent skill from filedcom/opentax.

    108 GitHub stars~1.8k tokensUpdated yesterday
    Auto-check passed
  • Save Skill

    filedcom/opentax

    Helps users permanently set up the OpenTax skill on their AI platform so they don't have to load it every time.

    108 GitHub stars~724 tokensUpdated yesterday
    Auto-check passed
  • Tax Build

    filedcom/opentax

    Autonomous form builder. An agent skill from filedcom/opentax.

    108 GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Tax Fix

    filedcom/opentax

    Autonomous bug-fix loop for any form:year. An agent skill from filedcom/opentax.

    108 GitHub stars~699 tokensUpdated yesterday
    Auto-check passed
  • Tax Preparer

    filedcom/opentax

    Tax preparer agent that uses the opentax CLI to prepare, validate, and export federal tax returns.

    108 GitHub stars~1.7k tokensUpdated yesterday
    Auto-check passed
  • Tax Reviewer

    filedcom/opentax

    Tax return reviewer that audits a completed return against source documents using the opentax CLI.

    108 GitHub stars~2.6k tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Tax Cases

What does Tax Cases do?

Generate realistic benchmark cases from IRS-published sources (VITA exercises, Pub 17 examples, MeF test cases). Tax Cases is an agent skill from filedcom/opentax. Generate realistic benchmark cases from IRS-published sources (VITA exercises, Pub 17 examples, MeF test cases).

When should I use Tax Cases?

Tax Cases fits situations like: tasks that involve Test generation.

How do I install Tax Cases in Claude Code?

Run `npx skills add filedcom/opentax --skill tax-cases -a claude-code`. Or copy the skill folder (.claude/skills/tax-cases in filedcom/opentax) into .claude/skills/tax-cases in your project. Claude Code loads it when a task matches its description.

How do I install Tax Cases in Codex?

Run `npx skills add filedcom/opentax --skill tax-cases -a codex`. Or copy the skill folder (.claude/skills/tax-cases in filedcom/opentax) into .agents/skills/tax-cases in your project. Codex loads it when a task matches its description.

Can I use Tax Cases in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add filedcom/opentax --skill tax-cases -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tax-cases, .gemini/skills/tax-cases, .github/skills/tax-cases and .opencode/skills/tax-cases in your project.

What does Tax Cases need to run?

SKILL.md names no scripts, command-line tools or credentials: Tax Cases is instructions for the agent only.

Does Tax Cases access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Tax Cases safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Tax Cases use?

Tax Cases is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Tax Cases use?

About 923 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Tax Cases?

Skills that share tags, products or a category with Tax Cases: Emc (aklofas/kicad-happy, 1.4k stars), Swig Test (swig/swig, 6.3k stars), Generate Test Cases (342164796/generate-test-cases, 119 stars) and Verify Cc Safety Net (kenryu42/cc-safety-net, 1.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Tax Cases?

filedcom (a GitHub organization) maintains it in filedcom/opentax, which has 108 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on October 7, 2026.

Source: filedcom/opentax on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.