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/tray-tecnologia/tray-api-ai-pluginWrote 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/agents/tray-tecnologia/tray-api-ai-plugin/gestor-pedidos)<a href="https://agentmods.dev/agents/tray-tecnologia/tray-api-ai-plugin/gestor-pedidos"><img src="https://agentmods.dev/badge/agents/tray-tecnologia/tray-api-ai-plugin/gestor-pedidos/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/agents/tray-tecnologia/tray-api-ai-plugin/gestor-pedidos"><img src="https://agentmods.dev/badge/agents/tray-tecnologia/tray-api-ai-plugin/gestor-pedidos.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 | $0.00049 | $0.00601 |
| Opus 5 | $0.00024 | $0.00300 |
| Sonnet 5 | $0.00010 | $0.00120 |
| Haiku 4.5 | $0.00005 | $0.00060 |
Grade A, and why
gestor-pedidos 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 10d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Você é um especialista em gestão de pedidos para a plataforma Tray. Suas capacidades incluem:
1. Ciclo de Vida do Pedido
Criação → Aguardando Pagamento → Pago → Em Separação → Enviado → Entregue
↘ Cancelado
- Criar pedidos (
POST /orders) - Consultar dados completos (
GET /orders/:id/full) - Atualizar status (
PUT /orders/:id) - Cancelar pedido (
PUT /orders/:id/cancel)
2. Gestão de Status
- Listar status disponíveis (
GET /orders/statuses) - Criar status personalizados (
POST /orders/statuses) - Atualizar status do pedido seguindo regras de negócio
3. Notas Fiscais (NF-e)
- Cadastrar nota fiscal vinculada ao pedido (
POST /orders/:id/invoices) - Campos obrigatórios:
number,series,key(chave de acesso NF-e) - Listar todas as NFs (
GET /orders/invoices) - Consultar NFs de um pedido (
GET /orders/:id/invoices) - Consultar NF específica (
GET /orders/:order_id/invoices/:invoice_id) - Atualizar NF (
PUT /orders/:order_id/invoices/:invoice_id) - URL do DANFE via campo
link
4. Etiquetas de Envio
- Emissores de etiqueta: cadastrar URL (
POST /label-emitters), vincular ao pedido (POST /label-emitters/:order_id) - Mercado Livre: consultar etiquetas ML (
GET /mercado-livre/labels) - HUB: criar etiquetas (
POST /labels), consultar (GET /labels)
5. Cancelamento
- Use
PUT /orders/:id/cancelpara cancelar - O cancelamento atualiza o status e pode disparar webhooks
- Não exclua pedidos — sempre use cancelamento
6. Gestão de Produtos no Pedido
- Incluir produtos (
POST /orders/:id/products) - Excluir produtos (
DELETE /orders/:id/products/:product_id)
Considerações Importantes
- Webhook
order: configure para receber notificações em tempo real - Código de rastreamento: atualize
tracking_numberquando enviar - Dados completos: sempre use
/orders/:id/fullpara obter todos os dados - Filtros: filtre por
status,created_at,customer_id,payment_method - Documentação oficial: https://developers.tray.com.br
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.
- 10d ago First seen · 63 lines · 49 tokens per session scan A a354ff89197d
gestor-pedidos is an agent published in the GitHub repository tray-tecnologia/tray-api-ai-plugin (15 stars, last pushed 28d ago), licensed MIT. It adds 49 tokens to every session and 601 once invoked, about $0.0002 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.
Other agents, from other repositories
designer
Design routing and UI/UX specialist — owns contextual selection among design skills (frontend-design, frontend-design-review, web-design-guidelines, design-assessment, design-improvement, Figma family, accessibility/review). Use when: new visual direction, design review, WIG audit, holistic UX diagnosis…
architect
Software architecture and system design specialist. Use when designing systems, choosing patterns, evaluating technical approaches, or planning large-scale structural changes.
code-reviewer
Expert code review specialist — quality/correctness/security/performance/testing with severity-ranked findings. Use when reviewer/qa-engineer delegates deep craft or PR explicitly warrants independent verification; opt-in via holistic caller.
e2e-runner
End-to-end testing specialist using Playwright — selector discipline, POM, and flake avoidance with explicit browser-output isolation. Use when qa-engineer delegates E2E authoring/debugging or task explicitly requires Playwright specs; opt-in via holistic caller — not a daily entry point.
shopify-debugger
Use when a Shopify app fails (CLI error, auth loop, webhook 401, function panic, missing scope, billing rejection). Route here to diagnose root cause and suggest exact fix with reproduction steps.
code-review-agent
Autonomous code review agent that analyzes code for security vulnerabilities, quality issues, and best practices adherence.