referral-program

referral-program is a skill for Claude Code, Codex from Dokkabei97/forged-claude-code. It costs 35 tokens per session (889 once invoked), scanned A, original, MIT.

A guide for designing a referral program, where existing users invite new users in exchange for rewards. It covers who gets rewarded, what triggers rewards, sharing methods, tracking, and different reward structures.

In plain words
What is it for?
Use it to plan two-sided, one-sided, tiered, or milestone-based referral programs and document their setup.
Why use it?
It helps replace ad-hoc referral ideas with a defined program that explains how invitations and rewards should work.

Skill for Claude CodeCodex

Part of the forged-claude-code plugin — 29 skills, 14 commands, 9 agents, 2 hooks shipped together

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/dokkabei97/forged-claude-code/referral-program
Any agent
npx skills add Dokkabei97/forged-claude-code --skill referral-program
Clone the repo
git clone --depth 1 https://github.com/Dokkabei97/forged-claude-code

Made for: Claude Code, Codex.

Or install forged-claude-code, the plugin that ships this one along with the rest of its 29 skills, 14 commands, 9 agents, 2 hooks.

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-program

README.md
[![agentmods](https://agentmods.dev/badge/skills/dokkabei97/forged-claude-code/referral-program.svg)](https://agentmods.dev/skills/dokkabei97/forged-claude-code/referral-program)
Your own site
<a href="https://agentmods.dev/skills/dokkabei97/forged-claude-code/referral-program"><img src="https://agentmods.dev/badge/skills/dokkabei97/forged-claude-code/referral-program.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 889 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 $0.00035 $0.00889
Opus 5 $0.00017 $0.00445
Sonnet 5 $0.00007 $0.00178
Haiku 4.5 $0.00003 $0.00089

Measured 4d ago against content hash 150ec609a947, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

referral-program 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.

skills/cmo/referral-program/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Referral Program - Viral Growth Design

Overview

Designs referral programs that turn users into your best sales channel. Dropbox grew 3900% with referrals. The best growth is growth that pays for itself.


1. When to Apply

Trigger Behavior
Reducing CAC Referral program design
"referral", "레퍼럴" Full program setup guide
Users already sharing organically Amplify existing behavior

2. Referral Program Types

Type Mechanism Best For Example
Double-sided Both referrer and referee get reward SaaS, marketplace Dropbox, Airbnb
One-sided (referrer) Only referrer gets reward Low-friction products Cash referral bonus
One-sided (referee) Only new user gets benefit Trial/freemium "Get 1 month free"
Tiered Rewards increase with more referrals Power users Ambassador programs
Milestone Reward at specific referral counts Viral products "Invite 5 → unlock feature"

3. Program Design Template

# Referral Program: [Product Name]

## Incentive Structure
| Role | Reward | Trigger |
|------|--------|---------|
| Referrer | [e.g., 1 month free] | When referee [signs up / pays / activates] |
| Referee | [e.g., 20% off first month] | On signup via referral link |

## Sharing Mechanics
- **Unique referral link**: [user].product.com/ref/[code]
- **Share channels**: Copy link, Email, Twitter, WhatsApp
- **In-app placement**: Settings → "Invite Friends" + post-value moment

## Tracking
- Referral code in URL → cookie → attribution on signup
- Dashboard: referrals sent, signed up, converted, rewards earned

## Reward Fulfillment
- Automatic credit/discount application
- Email notification on successful referral
- Leaderboard for top referrers (optional)

## Anti-Fraud Rules
- Max [N] referrals per user per month
- Self-referral detection (same IP, email domain)
- Minimum activity threshold before reward unlock

Read the full file on GitHub · 132 lines

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 · 132 lines · 35 tokens per session scan A 150ec609a947

Subscribe to this mod's changes

referral-program is a skill published in the GitHub repository Dokkabei97/forged-claude-code (2 stars, last pushed 6mo ago), licensed MIT. It adds 35 tokens to every session and 889 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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 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

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 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