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.
curl -O https://raw.githubusercontent.com/dsvi-b/corretor-enem/master/AGENTS.mdgit clone --depth 1 https://github.com/dsvi-b/corretor-enemWrote 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/instructions/dsvi-b/corretor-enem/agents-md)<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>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 | $0.01212 | $0.01212 |
| Opus 5 | $0.00606 | $0.00606 |
| Sonnet 5 | $0.00242 | $0.00242 |
| Haiku 4.5 | $0.00121 | $0.00121 |
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.
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
- Carregar a metodologia: ler
CORRETOR.md(fluxo de correção, formato de saída, regras). É o arquivo canônico. - Ler a regra do ano (
referencia/regras_por_ano.md) antes de pontuar — o ano vigente (2025) manda sobre o corpus. - 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. - Seguir o fluxo de
CORRETOR.md(8 passos: regra do ano → obter redação → modo → C1–C5 → sanity-check → calibrar central → faixa/confiança → calibrar comcorpus.db→ fechar laudo). - Calibrar com exemplos reais via
scripts/amostra.py(banco de 11.147 redações pré-2025 emdataset/corpus.db) e aplicar as ressalvas dos microdados 2025 emreferencia/regras_por_ano.md. - 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.
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.
- 6d ago First seen · 97 lines · 1,212 tokens per session scan A 72bce85b3cdc
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.
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.
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.
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).
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).
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.
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.