Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/tray-tecnologia/tray-api-ai-pluginnpx agentmods add skills/tray-tecnologia/tray-api-ai-plugin/autorizacaoWrote 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/skills/tray-tecnologia/tray-api-ai-plugin/autorizacao)<a href="https://agentmods.dev/skills/tray-tecnologia/tray-api-ai-plugin/autorizacao"><img src="https://agentmods.dev/badge/skills/tray-tecnologia/tray-api-ai-plugin/autorizacao/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/skills/tray-tecnologia/tray-api-ai-plugin/autorizacao"><img src="https://agentmods.dev/badge/skills/tray-tecnologia/tray-api-ai-plugin/autorizacao.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 | $0.00080 | $0.02214 |
| Opus 5 | $0.00040 | $0.01107 |
| Sonnet 5 | $0.00016 | $0.00443 |
| Haiku 4.5 | $0.00008 | $0.00221 |
Grade A, and why
tray-autorizacao 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 12d 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MANDATORY: Tool Calls Required Before Answering
Estas chamadas são OBRIGATÓRIAS, não opcionais. Execute-as antes de gerar qualquer código ou payload. Se você está respondendo sem ter chamado as duas ferramentas abaixo, pare e chame agora.
1. Buscar documentação atualizada (sempre)
node skills/tray-dev/scripts/search_docs.mjs --topic=autorizacao "<termo da pergunta>"
<TOPIC_SLUG>: ver tabela emskills/tray-dev/SKILL.md.- Use os trechos retornados como fonte primária; este SKILL.md é resumo.
2. Validar payload localmente (antes de retornar código)
node skills/autorizacao/scripts/validate.mjs --schema=<SCHEMA_NAME> '<payload_json>'
- Schemas disponíveis:
auth-request,auth-refresh. Use--list-schemaspara confirmar. - Exit codes:
0válido ·1inválido ·2erro de uso. - Para output programático:
--json. - Corrija todos os erros antes de retornar o código (até 3 tentativas).
Antes de responder
Execute estas verificações antes de gerar qualquer payload ou código:
- Confirme o método HTTP e endpoint correto para a operação solicitada.
- Identifique os campos obrigatórios listados neste documento — não omita nenhum.
- Verifique que
access_tokennão aparece como literal string no código gerado. - Confirme que esta é a skill correta para o recurso (leia
when_not_to_useno frontmatter).
Autorização — API Tray
Documentação oficial: https://developers.tray.com.br/#autorizacao
Fluxo OAuth 2.0 (3 etapas)
Etapa 1 — Redirecionamento
Redirecione o lojista para a tela de autorização da Tray:
https://{dominio_loja}/auth.php?response_type=code&consumer_key={consumer_key}&callback={callback_url}
Parâmetros:
response_type— semprecodeconsumer_key— chave do aplicativo (obtida ao criar o app na Tray)callback— URL de retorno do seu aplicativo
Etapa 2 — Callback
Após o lojista autorizar, a Tray redireciona para sua callback com os parâmetros:
| Parâmetro | Descrição |
|---|---|
code |
Código de autorização (uso único) |
adm_user |
Identificador do usuário administrativo |
store |
URL da loja |
api_address |
Endereço base da API para esta loja — já inclui o sufixo /web_api (ex.: urldaloja.com.br/web_api). |
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- examples/auth-gerar-token.curl.sh 968 B runs code
- examples/auth-gerar-token.node.mjs 1.2 KB runs code
- examples/auth-renovar-token.curl.sh 615 B runs code
- examples/auth-renovar-token.node.mjs 880 B runs code
- schemas/auth-refresh.json 616 B
- schemas/auth-request.json 739 B
- scripts/validate.mjs 679 B runs code
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.
- 12d ago First seen · 221 lines · 80 tokens per session scan A e6337ac8b90a
tray-autorizacao is a skill published in the GitHub repository tray-tecnologia/tray-api-ai-plugin (15 stars, last pushed 1mo ago), licensed MIT. It adds 80 tokens to every session and 2,214 once invoked, about $0.0004 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 skills, from other repositories
Contract Testing with Pact
Consumer-driven contract testing skill using Pact, covering consumer tests, provider verification, Pact Broker integration, and CI/CD workflows.
API Rate Limiting Testing
Testing API rate limiting implementations including throttling behavior, burst handling, rate limit headers, and distributed rate limiting patterns.
API Versioning Testing
Testing API versioning strategies including URL path, header, and query parameter versioning with backward compatibility validation.
Contract-First Testing
Contract-first testing approach using Pact, Spring Cloud Contract, or Dredd for ensuring API consumer-provider compatibility.
slack-cli
Interact with the official Slack CLI to create, run, deploy, and manage Slack apps, environments, manifests, and triggers. Use when the user asks about Slack app development workflows, not workspace chat automation.
helius
Skill "helius" from helius-labs/core-ai, covering helius — build on solana, prerequisites, 1. helius mcp server, 2. mcp router surface and 3. api key.