referral-system

referral-system is a skill for Claude Code from rshankras/claude-code-apple-skills. It costs 41 tokens per session (2,183 once invoked), scanned A, original, MIT.

A referral and invite system that gives users shareable codes or links and records who referred whom. Referral programs encourage existing users to bring in new users, often for a reward.

In plain words
What is it for?
Use it to create invite codes, share deep links, track successful referrals, award rewards, and add SwiftUI invite screens.
Why use it?
It replaces manually tracked invitations with a way to link referrals to users, record rewards, and detect fraudulent activity.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Part of the apple-skills plugin — 147 skills shipped together , and of apple-skills

Good fit Use it to create invite codes, share deep links, track successful referrals, award rewards, and add SwiftUI invite screens.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rshankras/claude-code-apple-skills/referral-system
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.

Any agent
npx skills add rshankras/claude-code-apple-skills --skill referral-system
Clone the repo
git clone --depth 1 https://github.com/rshankras/claude-code-apple-skills

Made for: Claude Code.

Or install apple-skills, the plugin that ships this one along with the rest of its 147 skills.

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 referral-system

README.md
[![agentmods](https://agentmods.dev/badge/skills/rshankras/claude-code-apple-skills/referral-system/github.svg)](https://agentmods.dev/skills/rshankras/claude-code-apple-skills/referral-system)
Your own site
<a href="https://agentmods.dev/skills/rshankras/claude-code-apple-skills/referral-system"><img src="https://agentmods.dev/badge/skills/rshankras/claude-code-apple-skills/referral-system/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 referral-system

Your own site · 80×15
<a href="https://agentmods.dev/skills/rshankras/claude-code-apple-skills/referral-system"><img src="https://agentmods.dev/badge/skills/rshankras/claude-code-apple-skills/referral-system.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,183 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
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 $0.00041 $0.02183
Opus 5 $0.00020 $0.01092
Sonnet 5 $0.00008 $0.00437
Haiku 4.5 $0.00004 $0.00218

Measured 7d ago against content hash ca60582d8d6a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

referral-system 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 7d 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.

skills/generators/referral-system/SKILL.md · 285 lines

How it starts

The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Referral System Generator

Generate a production referral/invite system with unique code generation, deep link sharing, reward tracking, fraud prevention, and SwiftUI views for inviting friends and monitoring referral performance.

When This Skill Activates

Use this skill when the user:

  • Asks to "add a referral system" or "referral codes"
  • Wants to "invite friends" or "refer a friend" flow
  • Mentions "viral growth" or "invitation system"
  • Asks about "referral rewards" or "referral tracking"
  • Wants "invite codes" or "shareable invite links"

Pre-Generation Checks

1. Project Context Detection

  • Check Swift version (requires Swift 5.9+)
  • Check deployment target (iOS 17+ / macOS 14+ for @Observable and SwiftData)
  • Identify source file locations
  • Check for existing entitlements (Associated Domains for deep links)

2. Conflict Detection

Search for existing referral/invite code:

Glob: **/*Referral*.swift, **/*Invite*.swift, **/*InviteCode*.swift
Grep: "referralCode" or "inviteCode" or "ReferralManager"

If existing referral system found:

  • Ask if user wants to replace or extend it
  • If extending, identify integration points

3. Deep Link Setup Detection

Search for existing deep link handling:

Glob: **/*DeepLink*.swift, **/*UniversalLink*.swift
Grep: "onOpenURL" or "userActivity" or "NSUserActivity"

If deep link handling exists, integrate with it rather than generating a standalone handler.

Configuration Questions

Ask user via AskUserQuestion:

  1. Reward type?

    • Both-get (referrer and invitee both earn a reward) -- recommended
    • Referrer-only (only the person who shares gets rewarded)
    • Points-based (both parties earn points toward rewards)
  2. Code format?

    • Short alphanumeric (e.g., A7K2M9) -- recommended
    • Custom prefix (e.g., MYAPP-A7K2M9)
    • Username-based (e.g., john-A7K2)
  3. Sharing method?

    • Deep link (universal link with embedded code) -- recommended
    • Clipboard copy (copy code to pasteboard)
    • Share sheet (system share with link and message)
    • All of the above

Read the full file on GitHub · 285 lines

Files

What ships with it

1 file 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. 7d ago First seen · 285 lines · 41 tokens per session scan A ca60582d8d6a

Subscribe to this mod's changes

referral-system is a skill published in the GitHub repository rshankras/claude-code-apple-skills (713 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 2,183 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 2026-09-03.