tray-multicd

tray-multicd is a skill for Claude Code from tray-tecnologia/tray-api-ai-plugin. It costs 204 tokens per session (12,118 once invoked), scanned A, original, MIT.

Uma integração com a API de centros de distribuição da Tray, uma plataforma de comércio eletrónico. Centros de distribuição são locais onde produtos são armazenados e enviados.

In plain words
What is it for?
Serve para listar, consultar, criar, atualizar e excluir centros de distribuição, além de consultar e gerir stock por centro, produto ou variante.
Why use it?
Evita gerir separadamente os locais de distribuição e o stock disponível em cada um.

Skill for Claude Code

Written for Claude Code: when-to-use in frontmatter. Also seen: mentions Claude Code.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node skills/tray-dev/scripts/search_docs.mjs --topic=multicd "<termo da pergunta>".

Part of the tray-api plugin — 36 skills, 3 commands, 5 agents, 1 MCP server shipped together

Good fit Serve para listar, consultar, criar, atualizar e excluir centros de distribuição, além de consultar e gerir stock por centro, produto ou variante.

Compare 6 skills from other repositories ↓
Install

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.

Clone the repo
git clone --depth 1 https://github.com/tray-tecnologia/tray-api-ai-plugin
agentmods
npx agentmods add skills/tray-tecnologia/tray-api-ai-plugin/multicd

Made for: Claude Code.

Or install tray-api, the plugin that ships this one along with the rest of its 36 skills, 3 commands, 5 agents, 1 MCP server.

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 tray-multicd

README.md
[![agentmods](https://agentmods.dev/badge/skills/tray-tecnologia/tray-api-ai-plugin/multicd/github.svg)](https://agentmods.dev/skills/tray-tecnologia/tray-api-ai-plugin/multicd)
Your own site
<a href="https://agentmods.dev/skills/tray-tecnologia/tray-api-ai-plugin/multicd"><img src="https://agentmods.dev/badge/skills/tray-tecnologia/tray-api-ai-plugin/multicd/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.

agentmods 80×15 button for tray-multicd

Your own site · 80×15
<a href="https://agentmods.dev/skills/tray-tecnologia/tray-api-ai-plugin/multicd"><img src="https://agentmods.dev/badge/skills/tray-tecnologia/tray-api-ai-plugin/multicd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 204 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 12,118 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 8 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Tool Misuse · line 417
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • medium Agent Snooping · line 43
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Data Exfiltration · line 290
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 372
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 598
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 669
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Server-Side Request Forgery · line 705
    Request target host is built from a dynamic or untrusted value. If the host is attacker-influenced, this enables SSRF to arbitrary internal or metadata endpoints.
    Fix: Do not build request URLs from untrusted input. Validate the host against an allowlist and reject internal/metadata addresses before issuing the request.
  • medium Data Exfiltration · line 718
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
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 $0.00204 $0.12118
Opus 5 $0.00102 $0.06059
Sonnet 5 $0.00041 $0.02424
Haiku 4.5 $0.00020 $0.01212

Measured 8d ago against content hash 55ad7000cfbc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

tray-multicd scanned grade A with 1 finding 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.

The scan reads SKILL.md. This mod also ships 16 executable files (examples/cd-atualizar.curl.sh, examples/cd-atualizar.node.mjs, examples/cd-consultar.curl.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**Exemplo (curl):**
skills/multicd/SKILL.md · 834 lines

How it starts

The opening of the file, as written. The whole thing — 834 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 a ferramenta abaixo, pare e chame agora.

1. Buscar documentação atualizada (sempre)

node skills/tray-dev/scripts/search_docs.mjs --topic=multicd "<termo da pergunta>"
  • <TOPIC_SLUG>: ver tabela em skills/tray-dev/SKILL.md.
  • Use os trechos retornados como fonte primária; este SKILL.md é resumo denso.

2. Revisar campos (este recurso ainda NÃO tem validate.mjs)

Nota: o recurso multicd ainda não possui scripts/validate.mjs local. A chamada OBRIGATÓRIA a search_docs.mjs acima continua valendo. Como não há validador automático, você é responsável por revisar manualmente cada campo obrigatório contra a doc retornada por search_docs.mjs e contra os schemas de referência em skills/multicd/schemas/ (distribution_center.create.json, distribution_center.update.json) antes de retornar qualquer código. Confira em especial: chave de recurso DistributionCenter no body de CD; wrapper DistributionCenterProduct x DistributionCenterVariant na atualização de estoque (item com variações usa Variant); e zip_code normalizado para 8 dígitos numéricos sem traço.

Antes de responder

Execute estas verificações antes de gerar qualquer payload ou código:

  1. Confirme o método HTTP e o endpoint correto para a operação solicitada (CRUD em /multicd/distribution-centers, consulta de estoque em /multicd/stock/detailed/product/:id ou /variant/:id, e atualização de estoque em /multicd/distribution-centers/:id/stock).
  2. Identifique os campos obrigatórios listados neste documento — name, zip_code, address, city e state nunca podem faltar na criação de CD, e stock na atualização de estoque; não omita nenhum.
  3. Verifique que access_token não aparece como literal string no código gerado — use sempre TRAY_ACCESS_TOKEN e TRAY_API_ADDRESS por variável de ambiente, e sempre como query parameter (?access_token={token}).
  4. Confirme que esta é a skill correta para o recurso: Multi-CD pressupõe o recurso ativo na loja e estoque distribuído por depósito; se for estoque único, leia when_not_to_use e redirecione para tray-produtos/tray-variacoes.

Read the full file on GitHub · 834 lines

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 · 834 lines · 204 tokens per session scan A 55ad7000cfbc

Subscribe to this mod's changes

tray-multicd is a skill published in the GitHub repository tray-tecnologia/tray-api-ai-plugin (15 stars, last pushed 27d ago), licensed MIT. It adds 204 tokens to every session and 12,118 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.