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 OpenClaudia/openclaudia-skills --skill referral-programgit clone --depth 1 https://github.com/OpenClaudia/openclaudia-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/openclaudia/openclaudia-skills/referral-program)<a href="https://agentmods.dev/skills/openclaudia/openclaudia-skills/referral-program"><img src="https://agentmods.dev/badge/skills/openclaudia/openclaudia-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/openclaudia/openclaudia-skills/referral-program"><img src="https://agentmods.dev/badge/skills/openclaudia/openclaudia-skills/referral-program.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00076 | $0.02614 |
| Opus 5 | $0.00038 | $0.01307 |
| Sonnet 5 | $0.00015 | $0.00523 |
| Haiku 4.5 | $0.00008 | $0.00261 |
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 — 384 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Referral Program Design
Design effective referral programs and viral loops that drive sustainable growth.
1. Referral Program Frameworks
One-Sided Incentives
Only the referrer gets rewarded.
Best for:
- Products with strong organic word-of-mouth
- Low-friction signups where the referred user needs no extra motivation
- Cost-sensitive businesses
Examples:
- Uber: "$10 credit for every friend you refer"
- Amazon Associates: Commission on referred purchases
Template:
Refer a friend and get [reward].
Share your unique link: [referral_url]
Two-Sided Incentives
Both referrer and referred user get rewarded.
Best for:
- Products requiring activation effort from new users
- Competitive markets where new users need a nudge
- Subscription businesses
Examples:
- Dropbox: Both get 500MB extra storage
- Airbnb: Referrer gets $25 credit, friend gets $40 off first stay
- PayPal: Both get $10 when friend makes first transaction
Template:
Give [friend_reward], get [referrer_reward].
Share your link and you both win: [referral_url]
Tiered Incentives
Rewards increase with number of successful referrals.
Example tier structure:
| Referrals | Reward |
|---|---|
| 1 | Free month |
| 3 | Exclusive feature unlock |
| 5 | Premium plan for 3 months |
| 10 | Lifetime premium access |
| 25 | Cash payout or swag box |
Best for:
- Creating power referrers / ambassadors
- Products with passionate user bases
- Building a referral leaderboard culture
2. Viral Coefficient Calculation
The viral coefficient (K-factor) determines whether your referral loop is self-sustaining.
Formula
K = i * c
Where:
i = number of invites sent per user
c = conversion rate of each invite
If K > 1: viral growth (each user brings more than one new user)
If K < 1: referrals supplement but don't replace other acquisition
Example Calculation
Users send an average of 5 invites (i = 5)
15% of invites convert to signups (c = 0.15)
K = 5 * 0.15 = 0.75
With 1,000 initial users:
- Cycle 1: 1,000 * 0.75 = 750 new users
- Cycle 2: 750 * 0.75 = 563 new users
- Cycle 3: 563 * 0.75 = 422 new users
- Total after 10 cycles: ~3,570 additional users from 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 · 384 lines · 76 tokens per session scan A 2abed9aa0c8d
referral-program is a skill published in the GitHub repository OpenClaudia/openclaudia-skills (686 stars, last pushed yesterday), licensed MIT. It adds 76 tokens to every session and 2,614 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…