copy-thief: Instructions file for Codex

AGENTS.md

copy-thief AGENTS.md is an instructions file for Codex, OpenCode from thalesholleben/copy-thief. It costs 490 tokens per session, scanned A, original, MIT.

Repository instructions for copy-thief, a Claude Code skill for writing advertising copy in Brazilian Portuguese. The repository is a knowledge base and workflow, not a buildable application.

In plain words
What is it for?
It guides agents through diagnosing a copy request, choosing an approved structure, writing landing pages, advertorials, and video scripts, and checking the final result.
Why use it?
It prevents an agent from writing copy before understanding the project, sources, format, and approval process. It also sets rules against inventing testimonials, numbers, or other proof.

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 thalesholleben/copy-thief's own configuration. It tells Codex and OpenCode how to work on copy-thief 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 copy-thief configures →

Reuse

Borrowing it

Nothing to install: this file belongs to thalesholleben/copy-thief. 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/thalesholleben/copy-thief/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/thalesholleben/copy-thief

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 copy-thief AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/thalesholleben/copy-thief/agents-md.svg)](https://agentmods.dev/instructions/thalesholleben/copy-thief/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/thalesholleben/copy-thief/agents-md"><img src="https://agentmods.dev/badge/instructions/thalesholleben/copy-thief/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 490 This file is loaded in full into every session.
When invoked 490 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 $0.00490 $0.00490
Opus 5 $0.00245 $0.00245
Sonnet 5 $0.00098 $0.00098
Haiku 4.5 $0.00049 $0.00049

Measured 8d ago against content hash 6b70406ea2a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

copy-thief 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 8d 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 · 41 lines

What it actually says

AGENTS.md

Este repositório é uma skill do Claude Code (e compatível com qualquer agente que leia arquivos de instrução). Ele não tem build nem testes: é uma base de conhecimento + workflow para escrever copy de alta conversão para tráfego frio de Ads (Meta e Google), em PT-BR.

Ponto de entrada

SKILL.md é a fonte da verdade operacional. Contém o frontmatter (name, description) que aciona a skill e o workflow obrigatório: diagnóstico → estrutura aprovada pelo usuário → copy. Leia SKILL.md antes de qualquer coisa.

Mapa do repositório

  • SKILL.md — roteador + workflow obrigatório.
  • reference/ — base de conhecimento (ler sob demanda; ver tabela em SKILL.md).
  • templates/ — esqueletos de página: lp-structure.md, advertorial-structure.md, vsl-script.md.
  • intake/form.html — formulário de briefing client-side (o usuário preenche e cola o resultado).
  • examples/swipe-file.md — exemplos anotados.
  • checklists/briefing.md e qa-review.md.

Regras que não podem ser quebradas

  1. Nunca pule o workflow. Não gere copy completa sem antes diagnosticar e ter a estrutura aprovada pelo usuário.
  2. Nunca fabrique prova (depoimentos, números, autoridade, resultados). Use placeholders explícitos como [INSERIR DEPOIMENTO REAL].
  3. Pontuação: nunca use travessão nem hífen isolado - como pontuação. Hífen dentro de palavra é permitido. Detalhes em SKILL.md.
  4. Idioma de saída: PT-BR, mercado brasileiro.

Como rodar / instalar

Copie ou aponte esta pasta para ~/.claude/skills/copy-thief. Não há dependências, install ou build. O intake/form.html abre direto no navegador.

O que ignorar

.firecrawl/ (material bruto raspado das fontes) não é versionado e não é necessário: a síntese própria está em reference/.

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. 8d ago First seen · 41 lines · 490 tokens per session scan A 6b70406ea2a4

Subscribe to this mod's changes

copy-thief AGENTS.md is an instructions file published in the GitHub repository thalesholleben/copy-thief (17 stars, last pushed 2mo ago), licensed MIT. It adds 490 tokens to every session, about $0.0024 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 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 · 5,153 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