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.
npx skills add finsilabs/awesome-ecommerce-skills --skill referral-programgit clone --depth 1 https://github.com/finsilabs/awesome-ecommerce-skillsWrote 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.
[](https://agentmods.dev/skills/finsilabs/awesome-ecommerce-skills/referral-program)<a href="https://agentmods.dev/skills/finsilabs/awesome-ecommerce-skills/referral-program"><img src="https://agentmods.dev/badge/skills/finsilabs/awesome-ecommerce-skills/referral-program/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.
<a href="https://agentmods.dev/skills/finsilabs/awesome-ecommerce-skills/referral-program"><img src="https://agentmods.dev/badge/skills/finsilabs/awesome-ecommerce-skills/referral-program.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00030 | $0.03011 |
| Opus 5.5 | $0.00012 | $0.01204 |
| Sonnet 5.5 | $0.00006 | $0.00602 |
| Haiku 4.5 | $0.00003 | $0.00301 |
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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Referral Program
Overview
A referral program turns your existing customers into an acquisition channel by rewarding them for introducing new customers. Referral apps like ReferralCandy and Referral Hero handle unique link generation, double-sided rewards (referrer and referee), fraud detection, and post-purchase email triggers without custom code. Only build a custom referral system if your tiering logic, CRM integration, or fraud rules exceed what these tools support.
When to Use This Skill
- When building a "give $10, get $10" refer-a-friend program
- When adding tiered rewards that escalate with the number of successful referrals
- When fraud from self-referrals or multiple accounts is draining referral reward budget
- When measuring referral program CAC versus other acquisition channels
- When integrating referral tracking with post-purchase email flows in Klaviyo
Core Instructions
Step 1: Determine platform and choose the right referral tool
| Platform | Recommended Tool | Why |
|---|---|---|
| Shopify | ReferralCandy | Purpose-built for e-commerce; auto-generates referral links per customer, handles double-sided rewards, post-purchase email trigger, and fraud detection |
| Shopify | Referral Hero | More flexible reward types (cash, gift cards, store credit, custom); deep Klaviyo integration for referral email flows |
| Shopify | Smile.io | Combines loyalty points with referral mechanics in one app — best when you want both |
| WooCommerce | ReferralCandy or Referral Hero | Both offer WooCommerce plugins; connect via REST API to track orders and issue rewards |
| BigCommerce | ReferralCandy | Available on the BigCommerce App Marketplace |
| Custom / Headless | Build referral tracking + reward logic | Required when platform integrations or fraud rules don't match your needs |
Step 2: Platform-specific setup
Shopify
Option A: ReferralCandy (recommended — full referral suite)
What ships with it
7 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.
- evals/cookie-based-referral-attribution/criteria.json 2.2 KB
- evals/cookie-based-referral-attribution/task.md 1.6 KB
- evals/referral-fraud-signal-detection/criteria.json 2.5 KB
- evals/referral-fraud-signal-detection/task.md 1.7 KB
- evals/tiered-rewards-and-first-purchase-logic/criteria.json 2.5 KB
- evals/tiered-rewards-and-first-purchase-logic/task.md 1.5 KB
- tile.json 228 B
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.
- 1mo ago First seen · 268 lines · 30 tokens per session scan A 06e003831006
referral-program is a skill published in the GitHub repository finsilabs/awesome-ecommerce-skills (60 stars, last pushed 5d ago), licensed MIT. It adds 30 tokens to every session and 3,011 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 2026-08-30.
Other skills, from other repositories
referral-copy-writer
Writes the in-email referral section that asks existing subscribers to share the newsletter with colleagues or friends — including the ask, the framing of the reward or reciprocity, and the specific share copy subscribers can use verbatim.
viral-loop-designer
Use this skill to design a viral or referral loop for a post-PMF product by extracting the PATTERN (not the tactic) from canonical case studies — Dropbox bilateral-incentive referral, Hotmail email-signature instrumented virality, Airbnb Craigslist cross-posting, LinkedIn public-profile SEO virality — and adapting it…
growth-engine
Motor de crescimento para produtos digitais -- growth hacking, SEO, ASO, viral loops, email marketing, CRM, referral programs e aquisicao organica.
Growth Hacker
Design and execute growth experiments using lean, data-driven tactics.
asc-subscription-localization
Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.
food-order
Reorder previous Foodora orders, preview cart contents, and track delivery ETA/status with ordercli. Use when the user wants to reorder food, check delivery status, or browse recent Foodora order history. Never confirm an order without explicit user approval.