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-triar)<a href="https://agentmods.dev/commands/bittencourtthulio/expxdev/prodx-triar"><img src="https://agentmods.dev/badge/commands/bittencourtthulio/expxdev/prodx-triar/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-triar"><img src="https://agentmods.dev/badge/commands/bittencourtthulio/expxdev/prodx-triar.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 | $0.00041 | $0.00467 |
| Opus 5.5 | $0.00016 | $0.00187 |
| Sonnet 5.5 | $0.00008 | $0.00093 |
| Haiku 4.5 | $0.00004 | $0.00047 |
Grade A, and why
prodx-triar 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, etapa P0, seguindo references/00-triagem.md.
O chamado está em $ARGUMENTS. Se vier vazio, peça o texto do chamado em uma linha e pare.
Roteiro
- Leia o pedido cru, sem reescrever.
- Rode os oito gatilhos, cada um com resposta sim ou não. Na dúvida, a resposta é sim.
- Conte:
- zero gatilhos → veredito direto, linha no
INDICE.md, destino (normalmente runx), fim. - um ou mais → crie
docs/produto/pedidos/<PD-ID>-<slug>/e siga para o P2.
- zero gatilhos → veredito direto, linha no
- Registre a linha no
INDICE.mdnos dois casos. A triagem nunca é silenciosa.
Tom
Seco. Modo didático não vale aqui — ninguém quer aula para aprovar a correção de um rótulo. Máximo cinco linhas de saída:
Triagem <PD-ID> — "<titulo>"
Gatilhos: <nenhum | G1, G2...>
Veredito: <veredito> (<motivo em poucas palavras>)
Destino: <runx | avaliacao completa>
Registrado no INDICE.md. Confirme com uma linha para seguir.
Regras
- Regra 3: a triagem nunca é pulada, e a avaliação completa nunca roda sem gatilho disparado.
- Regra 2: mesmo no caminho curto, a confirmação de uma linha do humano é necessária antes de seguir para o runx.
- Pedido que passa na triagem não gera pasta.
- Se o
INDICE.mdnão existir, crie-o deassets/TEMPLATE-INDICE.mdantes da primeira linha. - Se o pedido for vago demais para triar, não invente gatilho: peça o pedido concreto e não crie linha ainda.
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 · 37 lines · 0 tokens per session scan A 0d5ec1b930e7
prodx-triar is a command published in the GitHub repository bittencourtthulio/expxdev (3 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 467 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-triar compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| prodx-triarbittencourtthulio/expxdev | Command | 3 | 1mo ago | MIT | A | 41 | 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 |