corretor-enem: Instructions file for Codex

AGENTS.md

corretor-enem AGENTS.md is an instructions file for Codex, OpenCode from dsvi-b/corretor-enem. It costs 1,212 tokens per session, scanned A, original, MIT.

Cross-tool project instructions for an ENEM essay grading system, where ENEM is Brazil’s national high-school exam and scores range from 0 to 1,000.

In plain words
What is it for?
Use them to trigger and organize essay corrections, infer or confirm missing topics, and apply the five official competencies.
Why use it?
They define when the agent should start an evaluation, which methodology and yearly rules to load, and where to find the essay and topic.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions Claude Code; mentions AGENTS.md.

This is dsvi-b/corretor-enem's own configuration. It tells Codex and OpenCode how to work on corretor-enem itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything corretor-enem configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dsvi-b/corretor-enem. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dsvi-b/corretor-enem/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/dsvi-b/corretor-enem

Made for: Codex, OpenCode.

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 corretor-enem AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dsvi-b/corretor-enem/agents-md.svg)](https://agentmods.dev/instructions/dsvi-b/corretor-enem/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/dsvi-b/corretor-enem/agents-md"><img src="https://agentmods.dev/badge/instructions/dsvi-b/corretor-enem/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,212 This file is loaded in full into every session.
When invoked 1,212 The same file — it is already loaded in full.
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 $0.01212 $0.01212
Opus 5 $0.00606 $0.00606
Sonnet 5 $0.00242 $0.00242
Haiku 4.5 $0.00121 $0.00121

Measured 6d ago against content hash 72bce85b3cdc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

corretor-enem AGENTS.md 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 6d 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.

AGENTS.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Corretor de Redação ENEM

Base de conhecimento + metodologia para corrigir redação dissertativo-argumentativa do ENEM nas 5 competências oficiais (0–200 cada, 0–1000 total). Agnóstico de ferramenta: roda em qualquer coding agent. Sem API externa, sem ML.

AGENTS.md é o ponto de entrada cross-agent (padrão lido por Codex, Cursor, Gemini, etc.). A metodologia completa vive em CORRETOR.md — carregar sob demanda quando o usuário pedir correção.

Quando agir

Sempre que o usuário pedir para corrigir / avaliar / dar nota numa redação do ENEM, soltar um texto de redação na pasta redacoes/, perguntar "quanto tiraria nisso", pedir feedback de competência, ou simular correção ENEM — mesmo sem a palavra "corrigir" ("vê minha redação", "tá boa essa?", "qual nota disso" também acionam).

Como agir

  1. Carregar a metodologia: ler CORRETOR.md (fluxo de correção, formato de saída, regras). É o arquivo canônico.
  2. Ler a regra do ano (referencia/regras_por_ano.md) antes de pontuar — o ano vigente (2025) manda sobre o corpus.
  3. Obter a redação de redacoes/ (.txt/.md mais recente ou o indicado) ou da conversa. Pegar também o tema — se não informado, inferir e confirmar.
  4. Seguir o fluxo de CORRETOR.md (8 passos: regra do ano → obter redação → modo → C1–C5 → sanity-check → calibrar central → faixa/confiança → calibrar com corpus.db → fechar laudo).
  5. Calibrar com exemplos reais via scripts/amostra.py (banco de 11.147 redações pré-2025 em dataset/corpus.db) e aplicar as ressalvas dos microdados 2025 em referencia/regras_por_ano.md.
  6. Se o usuário fornecer nota oficial, preservar o resultado, comparar por competência e registrar onde a estimativa errou. Nota oficial é soberana no exame, mas microdados mostram variância interavaliador; não tratá-la como medida pedagógica sem ruído nem descartá-la como mero acaso. Se houver trajetória AV1–AV4, mostrar cada instância; AV4 é banca de três avaliadores, não quarto corretor individual.

Read the full file on GitHub · 97 lines

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. 6d ago First seen · 97 lines · 1,212 tokens per session scan A 72bce85b3cdc

Subscribe to this mod's changes

corretor-enem AGENTS.md is an instructions file published in the GitHub repository dsvi-b/corretor-enem (2 stars, last pushed 1mo ago), licensed MIT. It adds 1,212 tokens to every session, about $0.0061 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 instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens