What is referral-programs?

A framework for designing referral programs in which existing customers invite new customers, often through links, codes, or rewards.

It helps plan refer-a-friend programs, improve participation, choose rewards, track referrals, and assess word-of-mouth acquisition.

It helps determine whether referrals fit the business and set incentives that account for customer acquisition cost, customer value, and existing satisfaction.

referral-programs — Skill for Claude Code by brainbytes-dev

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 brainbytes-dev/everything-claude-marketing --skill referral-programs

Clone the repo

git clone --depth 1 https://github.com/brainbytes-dev/everything-claude-marketing

Made for: Claude Code.

Or install everything-claude-marketing, the plugin that ships this one along with the rest of its 72 skills, 22 commands, 18 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/brainbytes-dev/everything-claude-marketing/referral-programs/github.svg)](https://agentmods.dev/skills/brainbytes-dev/everything-claude-marketing/referral-programs)

Your own site

<a href="https://agentmods.dev/skills/brainbytes-dev/everything-claude-marketing/referral-programs"><img src="https://agentmods.dev/badge/skills/brainbytes-dev/everything-claude-marketing/referral-programs/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/brainbytes-dev/everything-claude-marketing/referral-programs"><img src="https://agentmods.dev/badge/skills/brainbytes-dev/everything-claude-marketing/referral-programs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,686 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00028	$0.02686
Opus 5.5	$0.00011	$0.01074
Sonnet 5.5	$0.00006	$0.00537
Haiku 4.5	$0.00003	$0.00269

Measured 2mo ago against content hash 74b33a06ec4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

referral-programs 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 2mo 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/growth/referral-programs/SKILL.md · 263 lines

How it starts

The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Referral Program Design

When to Activate

Building a referral or refer-a-friend program from scratch
Improving an existing referral program with low participation or conversion
Reducing CAC by leveraging existing customer networks
Increasing word-of-mouth as an acquisition channel
Designing incentive structures for user referrals
Evaluating whether a referral program is right for the business

First Questions

What is your current word-of-mouth or organic referral rate? (Do customers already recommend you?)
What is your product's NPS or customer satisfaction score?
What is your current CAC? (Referral reward must be less than this)
What is your average customer LTV? (Determines affordable referral reward)
What does your product's natural sharing moment look like? (When are users most delighted?)
What has your audience responded to before? (Cash? Discounts? Status?)
Do you have a mechanism to track referrals? (Unique links, codes, in-app system?)

Prerequisite: Should You Build a Referral Program?

Referral programs amplify existing word-of-mouth. They do not create it.

Build a referral program if:

NPS > 30 (customers actively recommend you)
You already see organic referral behavior (people sharing without incentive)
Your product solves a visible problem (others can see the user benefiting)
Your target audience is in networks (professional communities, friend groups, teams)

Fix the product first if:

NPS < 20 (customers are not enthusiastic enough to refer)
Churn rate is high (referring friends to a product you might leave is unnatural)
The product is invisible (others can't see or experience the benefit)

Referral Program Mechanics

One-Sided Rewards

Only the referrer gets a reward.

Pros: Simpler to implement. Lower cost per referral.
Cons: Lower conversion on the referred side (no incentive to act). Can feel extractive.
Best for: Products with strong inherent value proposition where the referral itself is compelling.
Example: "Refer a friend and get $20 credit."

Read the full file on GitHub · 263 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.

2mo ago First seen · 263 lines · 28 tokens per session scan A 74b33a06ec4b

Subscribe to this mod's changes

referral-programs is a skill published in the GitHub repository brainbytes-dev/everything-claude-marketing (10 stars, last pushed 7mo ago), licensed MIT. It adds 28 tokens to every session and 2,686 once invoked, about $0.0001 per session on Opus 5.5. 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.

Marketing and SEO

referral-programs next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
referral-programsbrainbytes-dev/everything-claude-marketing	Skill	10	7mo ago	MIT	A	28	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code