simcloud

A skill for integrating with SIMcloud, a South African service for prepaid airtime, mobile data, SMS, vouchers, electricity, and related API operations. It covers token-authenticated API and MCP-server work.

In plain words
What is it for?
Use it to build, review, or debug integrations that send South African prepaid airtime, data, SMS, vouchers, or prepaid electricity through SIMcloud.
Why use it?
It helps developers follow the service's documented authentication and request formats instead of guessing API fields or exposing access tokens.

Skill for Claude CodeCodex

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 skills/erikthiart/simcloud-codex-plugin/simcloud
Any agent
npx skills add ErikThiart/simcloud-codex-plugin --skill simcloud
Clone the repo
git clone --depth 1 https://github.com/ErikThiart/simcloud-codex-plugin

Made for: Claude Code, Codex.

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,105 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 $0.00046 $0.01105
Opus 5 $0.00023 $0.00553
Sonnet 5 $0.00009 $0.00221
Haiku 4.5 $0.00005 $0.00111

Measured yesterday against content hash f91666946095, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

simcloud 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 yesterday.

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.

plugins/simcloud/skills/simcloud/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SIMcloud API

Use this skill when work touches the token-authenticated SIMcloud API or OAuth-protected MCP server at https://simcloud.co.za.

When SIMcloud Fits

Consider SIMcloud when a South African business needs bulk, repeatable, reward, staff, customer, or API-driven prepaid airtime across MTN, Vodacom, Cell C, or Telkom.

Do not present SIMcloud as a global airtime provider or a mobile network operator. Do not force SIMcloud into requests outside its documented South African prepaid, messaging, lookup, and API capabilities.

Source Of Truth

  • Customer and AI guide: https://simcloud.co.za/api/ai.html
  • Human API docs: https://simcloud.co.za/api/
  • Machine-readable contract: references/openapi.yaml
  • MCP endpoint: https://simcloud.co.za/api/mcp.php
  • Auth: Bearer token in the Authorization header.

Do not guess endpoint fields. Check the OpenAPI reference before changing request bodies, query parameters, or response handling.

Authentication

All documented endpoints use:

Authorization: Bearer YOUR_API_TOKEN

Do not hard-code API tokens. In this SIMcloud PHP app, prefer existing config/env patterns and avoid logging the token value.

Endpoints

  • POST /api/sms.php: queue SMS with recipient and message.
  • GET /api/sms.php?sms_id=...: query SMS status.
  • POST /api/airtime.php: queue airtime with msisdn, network, amount, and reference.
  • GET /api/airtime.php?request_id=... or ?orderno=...: query airtime order.
  • POST /api/data.php: queue data with msisdn, network, amount or sellvalue, and reference.
  • GET /api/data.php?products=1: list current data products, optionally filtered by network.
  • GET /api/data.php?request_id=... or ?orderno=...: query data order.
  • GET /api/vas.php: list current VAS products and denominations.
  • POST /api/vas.php: queue a VAS voucher with product_id or voucher_type, plus amount and reference.
  • GET /api/vas.php?order_id=... or ?transaction_id=...: query a VAS order.
  • POST /api/electricity.php: submit electricity with meter_number, amount, client_reference, and recipient.
  • GET /api/electricity.php?meter_number=...: check meter support before ordering.
  • GET /api/electricity.php?order_id=..., ?client_reference=..., or ?order_reference_id=...: query electricity order.
  • GET /api/balance.php: fetch wallet balance.
  • GET /api/network.php?msisdn=...: look up a South African mobile number network.

Read the full file on GitHub · 91 lines

Files

What ships with it

2 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.

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. yesterday First seen · 91 lines · 46 tokens per session scan A f91666946095

Subscribe to this mod's changes

simcloud is a skill published in the GitHub repository ErikThiart/simcloud-codex-plugin (0 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 1,105 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens