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.
npx skills add trycomp-io/comp-skills --skill pj-vs-clt-calculatorgit clone --depth 1 https://github.com/trycomp-io/comp-skillsWrote 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.
[](https://agentmods.dev/skills/trycomp-io/comp-skills/pj-vs-clt-calculator)<a href="https://agentmods.dev/skills/trycomp-io/comp-skills/pj-vs-clt-calculator"><img src="https://agentmods.dev/badge/skills/trycomp-io/comp-skills/pj-vs-clt-calculator/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.
<a href="https://agentmods.dev/skills/trycomp-io/comp-skills/pj-vs-clt-calculator"><img src="https://agentmods.dev/badge/skills/trycomp-io/comp-skills/pj-vs-clt-calculator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00171 | $0.03511 |
| Opus 5 | $0.00086 | $0.01755 |
| Sonnet 5 | $0.00034 | $0.00702 |
| Haiku 4.5 | $0.00017 | $0.00351 |
Grade A, and why
pj-vs-clt-calculator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dual-mode operation (Code + Cowork)
HTML through the design system (required). Whenever this skill produces HTML, load the
comp-html-guidelinesskill first and apply the CompDS design system. This holds even when the user does not ask to "style it" or "make it look good" — every HTML output from this skill goes through the design system. It does not change the methodology below; it only governs the HTML's visual layer.
Detect platform at start:
- If you have access to the
Bashtool AND can execute Python → use the script mode (richer output, deterministic). - If not (e.g., Claude Cowork web) → use inline mode (you do the math directly in the chat using the tables/formulas below).
Both modes produce the same answer. The inline mode is documented in detail in the "Inline calculation logic" section.
Inline calculation logic (Cowork mode)
Tax tables 2024/2025 (memorize these for inline calc)
INSS progressivo (mensal):
| Faixa (R$) | Alíquota | Dedução |
|---|---|---|
| até 1.412,00 | 7,5% | 0 |
| 1.412,01 – 2.666,68 | 9% | 21,18 |
| 2.666,69 – 4.000,03 | 12% | 101,18 |
| 4.000,04 – 7.786,02 | 14% | 181,18 |
- Teto: R$ 7.786,02 → contribuição máxima R$ 908,85
- Fórmula:
(salario × alíquota) - dedução. Se salário > teto, INSS = 908,85.
IRPF progressivo (base = salário - INSS):
| Base (R$) | Alíquota | Dedução |
|---|---|---|
| até 2.259,20 | 0% | 0 |
| 2.259,21 – 2.826,65 | 7,5% | 169,44 |
| 2.826,66 – 3.751,05 | 15% | 381,44 |
| 3.751,06 – 4.664,68 | 22,5% | 662,77 |
| acima 4.664,68 | 27,5% | 896,00 |
- Fórmula:
max(0, (base × alíquota) - dedução).
Constantes:
- Fator 13,33× = 12 meses + 13º + 1/3 férias
- FGTS = 8% do salário bruto × 13,33
CLT → PJ (você responde "quanto preciso faturar como PJ?")
Passos:
- Calcular salário líquido CLT:
salário_bruto - INSS - IRPF - Anualizar líquido:
líquido × 13,33 - Somar benefícios anuais (VR/VA × 12 + bônus anual + outros)
- Somar FGTS anual (se
--include-fgts):salário × 13,33 × 0,08 - Total alvo anual CLT = soma dos passos 2-4
- Calcular faturamento PJ alvo via busca binária:
- Variáveis: alíquota PJ (%), nº faturas (12 ou 13), contabilidade mensal, outros custos
- Net anual PJ =
faturamento_anual - (faturamento_anual × alíquota%) - (contabilidade + outros) × 12 - Encontrar
faturamento_mensaltal que Net anual PJ ≈ Total alvo anual CLT (diferença < R$ 1)
- Output: faturamento mensal e anual PJ, com decomposição
What ships with it
7 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.
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.
- 10d ago First seen · 268 lines · 171 tokens per session scan A 378516c88b67
pj-vs-clt-calculator is a skill published in the GitHub repository trycomp-io/comp-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 171 tokens to every session and 3,511 once invoked, about $0.0009 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.
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…
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.
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.
irpf-brasil
Use para declaração de IRPF guiada passo a passo, análise de pré-preenchida, cálculo de imposto, deduções, bens e direitos, rendimentos, restituição, malha fina, carnê-leão. Conduz o usuário como se estivesse declarando de verdade.
design-compensation-structure
Use when building or redesigning a salary band structure, total rewards framework, or compensation philosophy for an organization.
fiscaliste
Fiscaliste IA pour la fiscalité personnelle des particuliers français : optimisation et déclaration de l'impôt sur le revenu, IFI, revenus du capital, revenus fonciers, equity salarial, crypto-actifs et PER. Couvre le calcul de l'IR (barème, quotient familial, décote, PAS, CEHR, revenus exceptionnels), la déclaration…