Agent skill

Tax Fix

by filedcom in filedcom/opentax

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

AGPL-3.0Auto-check passedDevelopment

Install Tax Fix

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

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

GitHub CLI
$ gh skill install filedcom/opentax tax-fix --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-fix .claude/skills/tax-fix && 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-fix
GitHub stars
108
Token cost
~699 tokens
SKILL.md length
288 words
Files
3
Skills in repo
8
Repo updated
First seen
Licence
AGPL-3.0

At a glance

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

  • Works in 7 steps: Derive Paths → Load State → Identify Pending Root Causes → …
  • Tasks that involve Root cause analysis
  • SKILL.md covers Step 0 — Derive Paths, Step 1 — Load State, Step 2 — Identify Pending Root… and Step 3 — Spawn Parallel…, plus 4 more sections
  • Calls git

What it does

Tax Fix is an agent skill from filedcom/opentax. Autonomous bug-fix loop for any form:year. Reads failing benchmark cases, spawns parallel bug-fixer agents per root cause cluster, validates, commits net-positive fixes, and loops until all pass or stalled.

Its SKILL.md is about 700 tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `agents/bug-fixer.md` and `agents/validator.md`).

It sits in Development, covering Root cause analysis and Debugging. 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 Root cause analysis
  • Tasks that involve Debugging

Example prompts

  • “/tax-fix”

Workflow steps

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

  1. Derive Paths
  2. Load State
  3. Identify Pending Root Causes
  4. Spawn Parallel Bug-Fixer Agents
  5. Run Validator
  6. Evaluate Results
  7. Log and Loop

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

    Shell commands in SKILL.md call:

    • git

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

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    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 Fix loads about 699 tokens when it runs. Until then it costs about 54 tokens; SKILL.md has 288 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~54
When it runs · the whole SKILL.md, loaded when a task matches
~699

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). 288 words, ~699 tokens.

Download SKILL.mdSave it as .claude/skills/tax-fix/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
tax-fix
description
Autonomous bug-fix loop for any form:year. Reads failing benchmark cases, spawns parallel bug-fixer agents per root cause cluster, validates, commits net-positive fixes, and loops until all pass or stalled.

Tax Fix — Autonomous Bug Fix Loop

Form:Year: $ARGUMENTS (e.g. f1040:2025)

Step 0 — Derive Paths

Parse $ARGUMENTS as {form}:{year}. Derive:

  • Policy doc: forms/{form}/FORM.md
  • Cases dir: benchmark/cases/{form}/{year}/
  • State key: {form}:{year} in .state/bench/state.json under forms
  • Progress log: .state/bench/progress.md

Read forms/{form}/FORM.md and pass its contents to all spawned agents as context.

Step 1 — Load State

Read .state/bench/state.json. Navigate to forms.{form}:{year}.fix:

  • If "done" → print "All cases passing. Nothing to do." and stop.
  • If "stalled" → print stall message and stop.
  • Otherwise → set status to "running" and write state.json back.

Step 2 — Identify Pending Root Causes

From forms.{form}:{year}.fix.root_causes, collect all entries where status === "pending".

Step 3 — Spawn Parallel Bug-Fixer Agents

Group pending root causes by node_path. If multiple root causes touch the same node file, they must be handled by a single agent (pass all their root cause objects together). Different node files can be fixed in parallel.

For each group, spawn one agent in parallel using the Agent tool:

  • Agent file: .claude/skills/tax-fix/agents/bug-fixer.md
  • Pass as context: root cause object(s) + FORM.md contents + cases dir

Spawn all groups in a single message.

Step 4 — Run Validator

Spawn the validator agent (.claude/skills/tax-fix/agents/validator.md). Pass: form, year, cases dir.

Parse JSON output: { total, pass, fail, failing }.

Step 5 — Evaluate Results

Compare current pass count to forms.{form}:{year}.fix.benchmark_baseline:

  • Net positive: commit. Update baseline. Mark fixed root causes as "done". Reset no_improvement_count to 0.
    bash
    git add -A
    git commit -m "fix: {form} {year} benchmark — X→Y passing cases"
  • No improvement or regression: revert all uncommitted changes to prevent bad patches from accumulating:
    bash
    git checkout .
    Increment no_improvement_count. If ≥ 2 → set status: "stalled", stop.

Step 6 — Log and Loop

Append to .state/bench/progress.md:

## [{form}:{year}] Round N — [timestamp]
- Baseline: X pass / Y fail
- After fix: A pass / B fail
- Fixed clusters: [list]

If fail === 0 → set status: "done", stop. Otherwise loop to Step 2.

Key Constraints

  • Only commit if net-positive (more passes, zero new failures)
  • Never revert working fixes
  • If a bug-fixer reports it cannot safely fix, leave cluster as "pending"

© 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-fix of filedcom/opentax.

  • SKILL.md
  • agents/bug-fixer.md
  • agents/validator.md

Open the folder on GitHubat commit 0c6ae76

Compare with similar skills

Tax Fix 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 Fix compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Tax Fix this skillfiledcom/opentax108—~699Automated safety check: PassAGPL-3.0
OpenLogi macOS Permissions TriageAprilNEA/OpenLogi23k—~2.5kAutomated safety check: NotesApache-2.0
Bug Finder for daisyUIsaadeghi/daisyui43k—~2.3kAutomated safety check: PassMIT
Root Cause Debugginggarrytan/gstack136k—~1.4kAutomated safety check: PassMIT
Graph-Based Bug Tracingtirth8205/code-review-graph32k1 repos~287Automated safety check: PassMIT
Systematic DebuggingChrisWiles/claude-code-showcase6.1k3 repos~1.2kAutomated safety check: PassNone

Similar skills

  • Decides whether an OpenLogi device problem on macOS is a privacy-permission (TCC) problem, using agent log lines, and says which identity needs which grant.

    23k GitHub stars~2.5k tokensUpdated 4 days ago
    DevelopmentAuto-check: notes
  • Bug Finder for daisyUI

    saadeghi/daisyui

    Investigates suspected bugs in the daisyUI monorepo through read-only analysis, then writes a decision-ready fix plan in tmp/bugs without changing any product code.

    43k GitHub stars~2.3k tokensUpdated 8 days ago
    DevelopmentAuto-check passed
  • Root Cause Debugging

    garrytan/gstack

    Investigates bugs, errors and stack traces in phases and requires a root-cause hypothesis to be confirmed before any fix is written.

    136k GitHub stars~1.4k tokensUpdated today
    DevelopmentAuto-check passed
  • Graph-Based Bug Tracing

    tirth8205/code-review-graph

    Traces a bug through a code knowledge graph, following callers, callees and execution flow before opening source files, within a small token budget.

    32k GitHub starsUsed in 1 repo~287 tokens
    DevelopmentAuto-check passed
  • Systematic Debugging

    ChrisWiles/claude-code-showcase

    Applies a four-phase debugging routine that finds the root cause of a bug or failing test before any fix is written.

    6.1k GitHub starsUsed in 3 repos~1.2k tokens
    DevelopmentAuto-check passed
  • Debugging and Error Recovery

    addyosmani/agent-skills

    Applies a stop-the-line rule and a step-by-step triage when tests fail, builds break or something stops working, aiming at the root cause instead of guesses.

    103k GitHub starsUsed in 1 repo~2.6k tokens
    DevelopmentAuto-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 Cases

    filedcom/opentax

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

    108 GitHub stars~923 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 Fix

What does Tax Fix do?

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

When should I use Tax Fix?

Tax Fix fits situations like: tasks that involve Root cause analysis; tasks that involve Debugging.

How do I install Tax Fix in Claude Code?

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

How do I install Tax Fix in Codex?

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

Can I use Tax Fix 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-fix -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-fix, .gemini/skills/tax-fix, .github/skills/tax-fix and .opencode/skills/tax-fix in your project.

What does Tax Fix need to run?

Going by SKILL.md and its folder, Tax Fix needs the command-line tools its instructions call (git).

Does Tax Fix access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Tax Fix 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 Fix use?

Tax Fix 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 Fix use?

About 699 tokens (SKILL.md is roughly 2.8k 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 Fix?

Skills that share tags, products or a category with Tax Fix: OpenLogi macOS Permissions Triage (AprilNEA/OpenLogi, 23k stars), Bug Finder for daisyUI (saadeghi/daisyui, 43k stars), Root Cause Debugging (garrytan/gstack, 136k stars) and Graph-Based Bug Tracing (tirth8205/code-review-graph, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Tax Fix?

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.