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/pagamentosWrote 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/pagamentos)<a href="https://agentmods.dev/skills/tray-tecnologia/tray-api-ai-plugin/pagamentos"><img src="https://agentmods.dev/badge/skills/tray-tecnologia/tray-api-ai-plugin/pagamentos/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/pagamentos"><img src="https://agentmods.dev/badge/skills/tray-tecnologia/tray-api-ai-plugin/pagamentos.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 13 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 19 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.
- high Tool Misuse · line 416 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.
- high Tool Misuse · line 686 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 45 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 Server-Side Request Forgery · line 195 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 Server-Side Request Forgery · line 321 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 Server-Side Request Forgery · line 247 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 Server-Side Request Forgery · line 392 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 Server-Side Request Forgery · line 450 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 Server-Side Request Forgery · line 502 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 Server-Side Request Forgery · line 554 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 299 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 371 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.
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 | $0.00176 | $0.12029 |
| Opus 5 | $0.00088 | $0.06014 |
| Sonnet 5 | $0.00035 | $0.02406 |
| Haiku 4.5 | $0.00018 | $0.01203 |
Grade A, and why
tray-pagamentos 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Exemplo (curl):** How it starts
The opening of the file, as written. The whole thing — 824 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=pagamentos "<termo da pergunta>"
<TOPIC_SLUG>: ver tabela emskills/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
pagamentosainda não possuiscripts/validate.mjslocal. A chamada OBRIGATÓRIAS asearch_docs.mjsacima continua valendo. Como não há validador automático, você é responsável por revisar manualmente cada campo obrigatório (order_id,payment_method,payment_type,amount) contra a doc retornada porsearch_docs.mjse contra os schemas de referência emskills/pagamentos/schemas/(payment.create.json,payment.update.json) antes de retornar qualquer código. Confira em especial: chave de recursoPaymentpresente no body,payment_typedentro do enum (credit_card/boleto/pix/transfer/deposit),amountcomo decimal com ponto (299.90, nunca299,90), einstallments/installment_valuecoerentes commax_installments/min_installment_valuede/payments/settings.
Antes de responder
Execute estas verificações antes de gerar qualquer payload ou código:
- Confirme o método HTTP e o endpoint correto para a operação solicitada (CRUD
em
/payments, leitura de opções em/payments/options, leitura de configurações em/payments/settings). - Identifique os campos obrigatórios listados neste documento — na criação,
order_id,payment_method,payment_typeeamountnunca podem faltar; não omita nenhum. - Verifique que
access_tokennão aparece como literal string no código gerado — use sempreTRAY_ACCESS_TOKENeTRAY_API_ADDRESSpor variável de ambiente, e SEMPRE como query parameter (?access_token={token}), nunca em header. - Confirme que esta é a skill correta para o recurso: pagamento é o registro
financeiro de um pedido; se for o pedido em si leia
when_not_to_usee redirecione paratray-pedidos; se for notificação de status, lembre que não há webhookpayment(use o escopoorderemtray-webhooks).
What ships with it
18 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/pagamento-atualizar.curl.sh 813 B runs code
- examples/pagamento-atualizar.fixture.json 122 B
- examples/pagamento-atualizar.node.mjs 1.2 KB runs code
- examples/pagamento-configuracoes.curl.sh 592 B runs code
- examples/pagamento-configuracoes.node.mjs 859 B runs code
- examples/pagamento-consultar.curl.sh 637 B runs code
- examples/pagamento-consultar.node.mjs 906 B runs code
- examples/pagamento-criar.curl.sh 702 B runs code
- examples/pagamento-criar.fixture.json 281 B
- examples/pagamento-criar.node.mjs 1.1 KB runs code
- examples/pagamento-excluir.curl.sh 886 B runs code
- examples/pagamento-excluir.node.mjs 1.1 KB runs code
- examples/pagamento-listar.curl.sh 579 B runs code
- examples/pagamento-listar.node.mjs 873 B runs code
- examples/pagamento-opcoes.curl.sh 590 B runs code
- examples/pagamento-opcoes.node.mjs 850 B runs code
- schemas/payment.create.json 3.2 KB
- schemas/payment.update.json 1.7 KB
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 · 824 lines · 176 tokens per session scan A d0281fcffca9
tray-pagamentos is a skill published in the GitHub repository tray-tecnologia/tray-api-ai-plugin (15 stars, last pushed 1mo ago), licensed MIT. It adds 176 tokens to every session and 12,029 once invoked, about $0.0009 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.
Other skills, from other repositories
billing-automation
Build automated billing systems for recurring payments, invoicing, subscription lifecycle, and dunning management. Use when implementing subscription billing, automating invoicing, or managing recurring payment systems.
helius-jupiter
Skill "helius-jupiter" from helius-labs/core-ai, covering helius x jupiter — build defi apps on solana, mcp router surface, prerequisites, 1. helius mcp server and 2. jupiter api key.
helius-okx
Skill "helius-okx" from helius-labs/core-ai, covering helius x okx — build trading & intelligence apps on solana, mcp router surface, prerequisites, 1. helius mcp server and 2. okx skill library (required).
api-commerce-stripe
Stripe payment processing — Checkout Sessions, Payment Intents, subscriptions, webhooks, Connect, customer management, error handling.
llm-cost-advisor
WHAT — Recommend the most cost-effective LLM provider for a given task type. Shows estimated cost per run across available providers and integrates with devcompanion llm-status to show what is actually available.
lemon-squeezy
Lemon Squeezy simplifies global tax compliance and recurring billing. The official @lemonsqueezy/lemonsqueezy.js SDK handles interactions cleanly.