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.
npx skills add IAPro-Community/Orquestrador-Maestro --skill skill-abacatepay-integrationgit clone --depth 1 https://github.com/IAPro-Community/Orquestrador-MaestroWrote 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/iapro-community/orquestrador-maestro/skill-abacatepay-integration)<a href="https://agentmods.dev/skills/iapro-community/orquestrador-maestro/skill-abacatepay-integration"><img src="https://agentmods.dev/badge/skills/iapro-community/orquestrador-maestro/skill-abacatepay-integration/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/iapro-community/orquestrador-maestro/skill-abacatepay-integration"><img src="https://agentmods.dev/badge/skills/iapro-community/orquestrador-maestro/skill-abacatepay-integration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Data Exfiltration · line 25 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 | $0.00055 | $0.00899 |
| Opus 5 | $0.00028 | $0.00449 |
| Sonnet 5 | $0.00011 | $0.00180 |
| Haiku 4.5 | $0.00006 | $0.00090 |
Grade A, and why
skill-abacatepay-integration 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 11d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
skill-abacatepay-integration
Workflow
- Inspect the project backend boundary first: Netlify/Vercel function, Express route, server action, Edge Function, or other server-only layer.
- Keep all AbacatePay calls behind that backend boundary. Browser code calls the project API, never AbacatePay directly with secrets.
- Validate customer data before billing creation: email, cellphone with country code, CPF/CNPJ without punctuation, amount in cents, plan ID, and tenant/user identity.
- Create billing with stable metadata:
user_id,tenant_id,plan_id, internal correlation ID, and payment link token when present. - Persist provider IDs, normalized status, amount, currency, raw event reference, and support/debug timestamps.
- Process webhooks idempotently, update entitlements from trusted backend evidence, and audit every access transition.
- Verify with local webhook tooling or provider test events plus project build/typecheck.
Current API Shape (v2)
Use API v2 for new work. API v1 remains only for legacy integrations:
- base URL:
https://api.abacatepay.com/v2 - hosted checkout:
POST /checkouts/create - subscriptions:
POST /subscriptions/create - transparent PIX/card/boleto checkout:
POST /transparents/create - webhook management:
POST /webhooks/create - auth header:
Authorization: Bearer <abacatepay-api-key> - current checkout events:
checkout.completed,checkout.refunded,checkout.disputed - current subscription events:
subscription.completed,subscription.renewed,subscription.cancelled
The old v1 routes such as /v1/billing/create and events such as billing.paid are legacy-compatible references. Do not copy them into new integrations; if maintaining v1, isolate an adapter and plan migration to v2.
Guardrails
- Keep
ABACATEPAY_API_KEYand webhook secrets server-side. - Treat checkout redirect as advisory. Grant access only after trusted backend/webhook confirmation.
- Deduplicate webhook processing by the v2 event ID and the provider checkout/subscription ID.
- Do not log API keys, webhook secrets, full CPF/CNPJ, full phone numbers, or unnecessary PII.
- Keep plan and entitlement rules in local product tables, not encoded only in AbacatePay objects.
- Support retries and out-of-order delivery by re-reading local payment state before mutation.
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.
- 11d ago First seen · 72 lines · 55 tokens per session scan A b58461e0d6c6
skill-abacatepay-integration is a skill published in the GitHub repository IAPro-Community/Orquestrador-Maestro (42 stars, last pushed today), licensed Apache-2.0. It adds 55 tokens to every session and 899 once invoked, about $0.0003 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
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
compound-interest-calculator
Calculate compound interest given principal, rate, time, and compounding frequency.
Invoice Automation
Automate invoice generation, sending, tracking, and payment reconciliation across accounting platforms.
tdm-daos-agent
Handle the current public TDM DaOS payment contract and recovery guidance. Use when a TDM service returns HTTP 402 from POST /authorize, when the user needs help with Session Gas Tank behavior, or when the user should be guided toward tdm connect, tdm fuel, tdm sweep, or tdm cashout.
market-brief
Generate a current morning market brief for Mick's indices, commodities, currencies, macro, and expanded crypto watchlist. Trigger immediately when the user starts with "mb" or asks for a market brief, morning brief, market update, pre-market summary, market open summary, or asks what the market is doing. Always…
alpaca-trading
Work safely in the Trading repository for Alpaca helpers, backtesting, journaling, scheduling, and related PowerShell modules. Prefer additive changes, preserve existing trading logic unless the user asks otherwise, and default to paper-trading-safe guidance.