audiencia-classifier

audiencia-classifier is a skill for Claude Code, Codex from autodevx/legal-skills. It costs 104 tokens per session (1,672 once invoked), scanned A, original, MIT.

A classifier for Brazilian court-hearing notices, including notices from official gazettes and court systems such as PJe, eSAJ, and PROJUDI. It categorizes the hearing type and whether it is in person, virtual, or hybrid.

In plain words
What is it for?
Use it to classify notices as initial, settlement, evidence-gathering, or judgment hearings and extract relevant details.
Why use it?
These notices arrive as unstructured text, making it easy to miss the hearing’s purpose or format.

Skill for Claude CodeCodex

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

Good fit Use it to classify notices as initial, settlement, evidence-gathering, or judgment hearings and extract relevant details.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/autodevx/legal-skills/audiencia-classifier"><img src="https://agentmods.dev/badge/skills/autodevx/legal-skills/audiencia-classifier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,672 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 $0.00104 $0.01672
Opus 5 $0.00052 $0.00836
Sonnet 5 $0.00021 $0.00334
Haiku 4.5 $0.00010 $0.00167

Measured 11d ago against content hash 494ed379b0b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

audiencia-classifier 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 11d 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.

skills/audiencia-classifier/SKILL.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Classificador de Audiências Judiciais

Contexto

Publicações de audiência em diários oficiais e sistemas processuais (PJe, eSAJ, PROJUDI) chegam em texto livre, sem estrutura padronizada. Esta skill classifica automaticamente cada publicação extraindo tipo, modalidade e metadados relevantes.

Taxonomia de classificação

Eixo 1: Tipo de audiência

Tipo Sinônimos / Indicadores no texto Finalidade
INICIAL "audiência inicial", "audiência inaugural", "primeira audiência", "art. 334 CPC" Tentativa de conciliação/mediação antes da instrução (CPC art. 334)
CONCILIAÇÃO "audiência de conciliação", "audiência de mediação", "tentativa de acordo", "CEJUSC" Sessão dedicada exclusivamente a acordo
INSTRUÇÃO "audiência de instrução", "AIJ", "instrução e julgamento", "oitiva de testemunhas", "depoimento pessoal" Coleta de provas orais (CPC art. 358+)
JULGAMENTO "audiência de julgamento", "sessão de julgamento", "leitura de sentença" Pronunciamento de decisão
UNA "audiência una", "audiência de instrução e julgamento" Instrução + julgamento na mesma sessão (comum em JECs e Justiça do Trabalho)
JUSTIFICAÇÃO "audiência de justificação", "justificação prévia" Produção antecipada de prova para tutela provisória
CUSTÓDIA "audiência de custódia" Criminal — apresentação do preso ao juiz (art. 310 CPP / Res. CNJ 213/2015)
ADMOESTAÇÃO "audiência admonitória", "admoestação" Intimação pessoal do devedor para cumprimento

Eixo 2: Modalidade

Modalidade Indicadores no texto
PRESENCIAL "sala de audiência", "comparecer na vara", "sede do fórum", endereço físico mencionado
VIRTUAL "videoconferência", "plataforma", "Microsoft Teams", "Zoom", "Google Meet", "Cisco Webex", "link de acesso", "sala virtual"
HÍBRIDA menção simultânea de sala física E link virtual; "modalidade híbrida"
NÃO IDENTIFICADA quando o texto não permite determinar a modalidade

Read the full file on GitHub · 151 lines

Files

What ships with it

1 file 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. 11d ago First seen · 151 lines · 104 tokens per session scan A 494ed379b0b1

Subscribe to this mod's changes

audiencia-classifier is a skill published in the GitHub repository autodevx/legal-skills (12 stars, last pushed 1mo ago), licensed MIT. It adds 104 tokens to every session and 1,672 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

Legal Intake Triage

Use when an inbound business request reaches the legal team — an email, ticket, form submission, or chat ask — to produce a structured intake triage that classifies the request, captures urgency as stated, surfaces conflict-check and confidentiality questions, and proposes a routing recommendation for the legal team…

zgbrenner/agentcounsel · 65 tokens

Templated Legal Response

Use when drafting a response to a routine, recurring legal inquiry from a configured template, with a built-in escalation gate that stops the templated path when the matter shows characteristics that require individualized counsel review.

zgbrenner/agentcounsel · 46 tokens

Legal Meeting Briefing

Use when preparing a structured briefing for a meeting with legal relevance — assembling background, participants, agenda, key documents, open issues, legal considerations, talking points, and a follow-up action-item tracker from the materials provided.

zgbrenner/agentcounsel · 49 tokens

Signature Routing Checklist

Use when a document is believed final and ready to sign — to run a pre-signature completeness checklist, identify signers and signing order, flag blockers, and produce a routing plan for attorney review before the document is sent for execution.

zgbrenner/agentcounsel · 51 tokens

previdencia-brasil

Use para INSS, aposentadoria, benefícios previdenciários, cálculo de contribuição, regras de transição 2026, auxílio-doença, salário-maternidade, pensão por morte. Ativa em "aposentadoria", "INSS", "quando posso me aposentar", "auxílio-doença", "salário-maternidade", "BPC", "contribuição INSS".

AlissonSantos1/brasil-legal-skills · 88 tokens

trabalhista-brasil

Use para CLT, cálculo de salário líquido, rescisão, férias, FGTS, horas extras, CLT vs PJ, aposentadoria, INSS, processos trabalhistas, orientação sobre provas e direitos. Ativa em "calcular salário", "rescisão", "CLT ou PJ", "quanto ganho por hora", "INSS", "aposentadoria", "processo trabalhista", "horas extras".

AlissonSantos1/brasil-legal-skills · 95 tokens