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.
git clone --depth 1 https://github.com/bittencourtthulio/expxdevWrote 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/commands/bittencourtthulio/expxdev/prodx)<a href="https://agentmods.dev/commands/bittencourtthulio/expxdev/prodx"><img src="https://agentmods.dev/badge/commands/bittencourtthulio/expxdev/prodx/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/commands/bittencourtthulio/expxdev/prodx"><img src="https://agentmods.dev/badge/commands/bittencourtthulio/expxdev/prodx.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 | $0.00043 | $0.00550 |
| Opus 5.5 | $0.00017 | $0.00220 |
| Sonnet 5.5 | $0.00009 | $0.00110 |
| Haiku 4.5 | $0.00004 | $0.00055 |
Grade A, and why
prodx 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 today.
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.
What it actually says
Use a skill prodx.
Este é o comando de entrada. Ele não executa etapa nenhuma por conta própria: identifica o estado e encaminha.
1. Verifique o estado
Nesta ordem:
docs/produto/PRODUTO.mdexiste?docs/produto/INDICE.mdexiste?- Há pastas em
docs/produto/pedidos/comVEREDITO.mdausente ou comaprovado_por: PENDENTE?
2. Se o PRODUTO.md não existir
Conduza à criação. Explique em três linhas por que ele é necessário — sem ele a skill vira genérica e qualquer IA responderia igual — e execute o P1 seguindo references/01-produto.md.
Não peça permissão para criar o arquivo; conduza a conversa que levanta o conteúdo.
3. Se existir, mostre o painel
prodx — <nome do produto>
Signatario: <nome> <(provisorio)>
PEDIDOS ABERTOS
| PD-ID | titulo | estagio | aguardando |
|-------|--------|---------|------------|
INDICADORES
Pedidos registrados: <n>
Via triagem: <n> (<%>)
Via avaliacao completa: <n> (<%>)
Nao viraram trabalho: <n> (<%>)
O estágio de cada pedido vem da máquina de estados do SKILL.md, deduzido dos arquivos presentes na pasta.
4. Comente os indicadores
- Avaliação completa acima de 50% — diga que os gatilhos estão largos demais, aponte quais (normalmente G4 ou G8) e ofereça ajustá-los.
- "Não viraram trabalho" perto de zero — diga que o prodx está virando carimbo, e que este é o indicador honesto de utilidade da skill.
- Signatário provisório — lembre em uma linha que a confirmação está pendente.
5. Encaminhe
Se há pedido aguardando ação, diga qual comando roda: /prodx-triar, /prodx-avaliar, /prodx-existe ou /prodx-briefing.
Se há mais de um pedido aberto e o usuário não indicou qual, liste com o estágio e pergunte — não escolha por ele.
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.
- today First seen · 53 lines · 43 tokens per session scan A 13bb00527417
prodx is a command published in the GitHub repository bittencourtthulio/expxdev (3 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 550 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-07.
prodx compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| prodxbittencourtthulio/expxdev | Command | 3 | 1mo ago | MIT | A | 43 | Claude Code |
| memoryopensolon/soloncode | Command | 198 | 5d ago | MIT | A | 18 | Claude Code |
| dayreportFakeHank/ai-report-to-me | Command | 9 | 8mo ago | MIT | A | 0 | Claude Code |
| qtreportFakeHank/ai-report-to-me | Command | 9 | 8mo ago | MIT | A | 0 | Claude Code |
| modernize-transformfuxicodex/Fuxi | Command | 3.2k | 17d ago | none | A | 17 | Claude Code |
| searchcoltonbearden/carrel | Command | 2 | 3d ago | MIT | A | 29 | Claude Code |
| doctorfatihkan/badi | Command | 7 | 1mo ago | MIT | A | 0 | Claude Code |