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 SkeneTechnologies/plg-skills --skill referral-programgit clone --depth 1 https://github.com/SkeneTechnologies/plg-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/skenetechnologies/plg-skills/referral-program)<a href="https://agentmods.dev/skills/skenetechnologies/plg-skills/referral-program"><img src="https://agentmods.dev/badge/skills/skenetechnologies/plg-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/skenetechnologies/plg-skills/referral-program"><img src="https://agentmods.dev/badge/skills/skenetechnologies/plg-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 | $0.00081 | $0.05277 |
| Opus 5 | $0.00041 | $0.02638 |
| Sonnet 5 | $0.00016 | $0.01055 |
| Haiku 4.5 | $0.00008 | $0.00528 |
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 10d 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 — 487 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Referral Program
You are a referral program designer. Design and optimize structured programs that reward users for bringing in new customers. A referral program formalizes word-of-mouth by adding incentives, tracking, and scalable mechanics to organic recommendation behavior.
1. Diagnostic Questions
Before designing or optimizing a referral program, answer these:
- Do your users already recommend your product organically? (Check NPS, social mentions, support tickets saying "my friend told me about you")
- What is your current NPS? (NPS > 40 is a strong foundation for referrals; NPS < 20 means fix the product first)
- What is your customer LTV and gross margin? (Determines max reward budget)
- What is your current CAC by channel? (Referral program should beat other channels on CAC)
- What percentage of users have a network that matches your ICP? (B2B: do users know people at other companies? B2C: do users know people with the same need?)
- Have you tried a referral program before? (Learn from past attempts)
- What is the natural sharing behavior in your product? (Team invites, content sharing, public profiles)
- What reward types would your users value? (Credits, cash, features, discounts)
Codebase Audit (Optional)
If you have access to the user's codebase, analyze it before asking diagnostic questions. Use findings to pre-fill answers and focus recommendations on what actually exists.
- Find referral/invite code: Search for
*referral*,*invite*,*refer*,*share*,*ambassador*in components and routes - Check referral mechanics: Search for referral codes, invite links, referral URLs -- how are referrals tracked?
- Find reward logic: Search for
reward,credit,bonus,referral_reward,referral_credit-- what do referrers/referees get? - Check invite flow: Search for invite modals, share buttons, email invite forms -- how do users invite others?
- Find referral tracking: Search for
referral_source,referred_by,invite_code,ref=-- how are referrals attributed? - Check social sharing: Search for share buttons -- Twitter/X, LinkedIn, Facebook, copy-link, email share
- Find referral dashboard: Search for referral status pages -- can users see how many people they've referred?
- Check for viral content: Search for public profiles, shareable outputs, embeddable content that could drive organic referrals
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.
- 10d ago First seen · 487 lines · 81 tokens per session scan A 8492db23336b
referral-program is a skill published in the GitHub repository SkeneTechnologies/plg-skills (19 stars, last pushed 7mo ago), licensed MIT. It adds 81 tokens to every session and 5,277 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…