ide-prompt

ide-prompt is an agent for coding agents from grtsnx/payba3. It costs 0 tokens per session (398 once invoked), scanned A, original, MIT.

A ready-made instruction prompt for an IDE coding assistant that helps integrate the Payba3 payment package into an application.

In plain words
What is it for?
Use it when generating TypeScript or JavaScript code for Payba3 payments, provider setup, webhooks, transaction status checks, transfers, refunds, or debits.
Why use it?
It sets rules for server-side code, secret handling, sandbox use, payment checks, and human approval so payment integrations are less likely to expose credentials or confirm unsafe transactions.

Agent

Install

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.

agentmods
npx agentmods add agents/grtsnx/payba3/ide-prompt
Clone the repo
git clone --depth 1 https://github.com/grtsnx/payba3

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 ide-prompt

README.md
[![agentmods](https://agentmods.dev/badge/agents/grtsnx/payba3/ide-prompt.svg)](https://agentmods.dev/agents/grtsnx/payba3/ide-prompt)
Your own site
<a href="https://agentmods.dev/agents/grtsnx/payba3/ide-prompt"><img src="https://agentmods.dev/badge/agents/grtsnx/payba3/ide-prompt.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 398 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00398
Opus 5 $0.00000 $0.00199
Sonnet 5 $0.00000 $0.00080
Haiku 4.5 $0.00000 $0.00040

Measured 4d ago against content hash 7ff944d6bf08, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ide-prompt 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 4d 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.

agents/ide-prompt.md · 50 lines

What it actually says

payba3 IDE Prompt

Use this prompt in an IDE coding agent, app generator, or AI pair-programming tool.

You are integrating @grtsnx/payba3.

Read these package docs before writing code:
- @grtsnx/payba3/llms.txt
- @grtsnx/payba3/agents.md
- @grtsnx/payba3/llms-full.txt if you need more context
- @grtsnx/payba3/llms/<provider>.txt for every requested provider

Rules:
- Generate server-side TypeScript or JavaScript only.
- Import createPayba3 from @grtsnx/payba3.
- Configure only the provider being used.
- Keep all provider secrets in environment variables or the host app's secret manager.
- Never expose provider keys, access tokens, refresh tokens, JWT client assertions, BVN, NIN, OTP, or webhook secrets to client code.
- Use sandbox by default unless the developer explicitly asks for live.
- Validate tool/API input before calling payba3.
- Verify webhooks and transaction status server-side before marking anything paid or fulfilled.
- Ask for human confirmation before live transfers, refunds, debits, or other money-moving actions unless the host app already has an approval workflow.

Minimal code shape:

import { createPayba3 } from '@grtsnx/payba3';

const payba3 = createPayba3({
  paystack: {
    secretKey: process.env.PAYSTACK_SECRET_KEY,
  },
});

export async function createCheckout(input: {
  email: string;
  amountInKobo: number;
  reference: string;
}) {
  return payba3.use('paystack').initializeOneTimeCheckout({
    email: input.email,
    amountInKobo: input.amountInKobo,
    currency: 'NGN',
    reference: input.reference,
  });
}
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. 4d ago First seen · 50 lines · 0 tokens per session scan A 7ff944d6bf08

Subscribe to this mod's changes

ide-prompt is an agent published in the GitHub repository grtsnx/payba3 (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 398 tokens. 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 2026-08-31.