irpf-brasil

irpf-brasil is a skill for Claude Code, Codex from AlissonSantos1/brasil-legal-skills. It costs 63 tokens per session (1,882 once invoked), scanned A, original, MIT.

A guided assistant for Brazil’s IRPF personal income-tax return, the annual declaration submitted to Receita Federal. It checks whether you need to file, reviews the pre-filled return, and helps examine income, deductions, assets, refunds, and possible audit issues.

In plain words
What is it for?
Use it to prepare an IRPF declaration, review a pre-filled return, check deductions and assets, estimate tax or a refund, and examine issues related to capital gains, stock trades, or the tax net.
Why use it?
Tax returns can contain missing or incorrect information, and the filing requirements depend on several types of income, assets, and transactions. This walks through the relevant questions and flags items to verify in the official program.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to prepare an IRPF declaration, review a pre-filled return, check deductions and assets, estimate tax or a refund, and examine issues related to capital gains, stock trades, or the tax net.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alissonsantos1/brasil-legal-skills/irpf
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 AlissonSantos1/brasil-legal-skills --skill irpf
Clone the repo
git clone --depth 1 https://github.com/AlissonSantos1/brasil-legal-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 irpf-brasil

README.md
[![agentmods](https://agentmods.dev/badge/skills/alissonsantos1/brasil-legal-skills/irpf/github.svg)](https://agentmods.dev/skills/alissonsantos1/brasil-legal-skills/irpf)
Your own site
<a href="https://agentmods.dev/skills/alissonsantos1/brasil-legal-skills/irpf"><img src="https://agentmods.dev/badge/skills/alissonsantos1/brasil-legal-skills/irpf/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 irpf-brasil

Your own site · 80×15
<a href="https://agentmods.dev/skills/alissonsantos1/brasil-legal-skills/irpf"><img src="https://agentmods.dev/badge/skills/alissonsantos1/brasil-legal-skills/irpf.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,882 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 $0.00063 $0.01882
Opus 5 $0.00032 $0.00941
Sonnet 5 $0.00013 $0.00376
Haiku 4.5 $0.00006 $0.00188

Measured 12d ago against content hash 343600442907, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

irpf-brasil 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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/calcular_imposto.py, scripts/dbk_parser.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

irpf/SKILL.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🧾 IRPF 2026 — Declaração Guiada

⚠️ Orientação educativa. Não substitui contador habilitado no CRC. Os valores calculados são estimativas — valide no programa oficial da Receita Federal.


Fluxo Guiado de Declaração

Ao iniciar o tema IRPF, siga sempre este roteiro interativo:

ETAPA 1 — Verificar obrigatoriedade

Perguntar ao usuário:

  • Recebeu rendimentos tributáveis acima de R$ 35.584,00 em 2025?
  • Recebeu rendimentos isentos/não tributáveis acima de R$ 200.000,00?
  • Realizou operações na Bolsa de Valores (B3)?
  • Teve ganho de capital na venda de bens?
  • Passou a residir no Brasil em 2025?
  • Tinha bens acima de R$ 800.000,00 em 31/12/2025?
  • Obteve receita bruta rural acima de R$ 177.920,00?

→ Se SIM em qualquer item: obrigado a declarar.

ETAPA 2 — Pré-preenchida

Perguntar:

"Você acessou a declaração pré-preenchida no Portal e-CAC ou app Meu Imposto de Renda? Se sim, o que já veio preenchido? Me informe os dados e vou avaliar se estão corretos, se falta algo ou se há algo que você pode adicionar."

Ao receber os dados pré-preenchidos:

  • Verificar se rendimentos batem com holerites/informes
  • Alertar sobre deduções que podem estar faltando
  • Identificar bens não declarados
  • Verificar dependentes

ETAPA 3 — Rendimentos

Orientar o usuário a informar:

  • Rendimentos tributáveis: salário, pró-labore, aluguéis, pensão recebida
  • Rendimentos isentos: FGTS, indenização rescisória, lucros e dividendos, poupança
  • Rendimentos sujeitos a tributação exclusiva: 13°, PLR, prêmios
  • Atenção 2026: apostas esportivas (Lei 14.790/2023) devem ser declaradas

ETAPA 4 — Deduções

Verificar e orientar sobre cada dedução:

Dedução por dependentes

  • R$ 2.275,08 por dependente/ano
  • Perguntar: "Tem filhos, cônjuge, pais ou outros dependentes?"

Despesas médicas (sem limite)

  • Médicos, dentistas, psicólogos, fisioterapeutas, hospitais
  • Plano de saúde — próprio e dependentes
  • Perguntar: "Guarda todos os recibos e notas fiscais?"

Read the full file on GitHub · 172 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 172 lines · 63 tokens per session scan A 343600442907

Subscribe to this mod's changes

irpf-brasil is a skill published in the GitHub repository AlissonSantos1/brasil-legal-skills (8 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 1,882 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 2026-08-31.

Related

Other skills, from other repositories

contingencia-report

Gera relatórios estruturados de contingência jurídica para uso em balanços, auditoria e compliance. Use quando o usuário precisar classificar processos por probabilidade de perda (provável/possível/remota) conforme CPC art. 95-96 e IAS 37 / CPC 25, calcular impacto financeiro no passivo contingente, ou preparar…

autodevx/legal-skills · 107 tokens

Classificação de Risco e Provisão (CPC 25)

Classifica o risco de cada processo judicial como Provável, Possível ou Remoto conforme CPC 25 e calcula o valor de provisão contábil recomendado, com memória de cálculo auditável para reporte ao financeiro e auditoria externa.

autodevx/legal-skills · 63 tokens

Revisão de Fatura Jurídica (Billing Guidelines)

Revisa faturas de escritórios externos contra as billing guidelines da organização, identificando linhas não conformes (horas excessivas, atividades não faturáveis, profissionais não aprovados) e calculando o valor a glosar com justificativa por linha.

autodevx/legal-skills · 64 tokens

banco-mcp

Skill abrangente pra trabalhar com dados financeiros via Banco MCP — analisar gastos, gerar extratos, fluxo de caixa, fatura de cartão, carteira de investimentos. Use sempre que o usuário perguntar sobre dinheiro, gastos, banco, cartão, investimentos, fatura, saldo, extrato, transações, ou variantes. Orquestra as 13…

douglac/banco-mcp · 96 tokens

bipa

Use Bipa CLI to make Pix payments, check balances, analyze transaction history, and decode BR codes for AI agents. MUST use this skill whenever the user mentions paying someone via Pix, checking their balance, reviewing transactions, scanning a Pix QR code, setting up Bipa CLI, or asks the agent to handle any…

bipa-app/bipa-cli · 139 tokens

pj-vs-clt-calculator

Brazilian CLT vs PJ (Pessoa Jurídica) salary equivalence calculator. Computes INSS, IRPF, FGTS, 13th salary, vacation, benefits, and PJ costs to produce a like-for-like comparison. Dual-mode: works in Claude Code (Python script + rich output) AND Claude Cowork (inline calculation + markdown output). Two operation…

trycomp-io/comp-skills · 171 tokens