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 kostja94/marketing-skills --skill referral-programgit clone --depth 1 https://github.com/kostja94/marketing-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/kostja94/marketing-skills/referral-program)<a href="https://agentmods.dev/skills/kostja94/marketing-skills/referral-program"><img src="https://agentmods.dev/badge/skills/kostja94/marketing-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/kostja94/marketing-skills/referral-program"><img src="https://agentmods.dev/badge/skills/kostja94/marketing-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 | $0.00086 | $0.01418 |
| Opus 5 | $0.00043 | $0.00709 |
| Sonnet 5 | $0.00017 | $0.00284 |
| Haiku 4.5 | $0.00009 | $0.00142 |
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 13d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- referral-program — 100% identical, 0 lines differ
- referral-program — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Channels: Referral
Guides referral program strategy for AI/SaaS products. Leverage existing users to drive growth; 3%-5% conversion vs 1%-2% for ads; CAC 50%-70% lower; referred users LTV 30%-50% higher, retention 20%-30% higher. Referral is necessity in overseas markets, not alternative.
When invoking: On first use, if helpful, open with 1-2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output.
Initial Assessment
Check for project context first: If .claude/project-context.md or .cursor/project-context.md exists, read it for product, audience, and value proposition.
Identify:
- Product type: SaaS, AI tool, subscription
- User base: Size, engagement, retention
- Goal: Signups, purchases, or both
Referral vs. Affiliate vs. Influencer
| Dimension | Referral | Affiliate | Influencer |
|---|---|---|---|
| Who | Existing users | Professional promoters | KOLs |
| Incentive | Discounts, credits | Commission | Fees, product |
| Barrier | Low (all users) | Medium | High |
| Conversion | 3%-5% | Varies | Varies |
Referral vs affiliate: Referral needs no landing page or application; integrated in dashboard. Affiliate requires landing page and approval.
Reward Models
| Model | Use |
|---|---|
| Two-way | Both referrer and referee get rewards; highest participation |
| One-way | Only referrer rewarded; cost control |
| Tiered | Rewards increase with referral count (e.g. $10 for 1-5, $15 for 6-10, $20 for 11+); incentivizes volume |
Benchmark: Rewards typically 10%-30% of product price; ~11% off or ~$21 value; weak incentives = low participation. Triggers: signup, purchase, activation, or sustained use.
Mechanism Types
| Type | Use |
|---|---|
| Link-based | Unique referral link; easy to implement; accurate tracking; share via email, social, SMS; works for web and app |
| Code-based | Referral code (e.g. FRIEND20); memorable; offline events; mobile-friendly input |
| Social referral | Share buttons (Facebook, X, LinkedIn); viral spread; friend trust; young users |
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.
- 13d ago First seen · 131 lines · 86 tokens per session scan A 87e1dbf08f75
referral-program is a skill published in the GitHub repository kostja94/marketing-skills (967 stars, last pushed 3mo ago), licensed MIT. It adds 86 tokens to every session and 1,418 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
SEO Content Optimizer
Analyzes and rewrites content to maximize search engine visibility without sounding robotic.
cold-outbound-sequencer
Use when the user asks to "build a B2B cold-outbound sequence", "design reply-triage branching", "plan a domain warmup / sending throttle", or "make my outbound CAN-SPAM / opt-in compliant"; produces a multi-step outbound sequence with reply-triage branches (positive / objection / referral / not-now / opt-out), a…
inbox-placement-monitor
Use when the user asks to "track where my emails are actually landing after I send", "read my seed-list inbox vs spam vs promotions results", "trend my Gmail Postmaster / Microsoft SNDS reputation", or "did placement drop after my last send"; produces a per-provider inbox/spam/promotions placement read, a domain/IP…
newsletter-monetization-planner
Use when the user asks to "monetize my newsletter", "build a sponsorship rate card", or "model paid-subscription revenue"; produces a revenue model (paid tiers, ad/sponsorship inventory + CPM/flat rate card, referral/boost loops), a list-growth ↔ revenue projection, and honest-offer / disclosure checks for the SEND-D…
budget-optimizer
Use when the user asks to "allocate my influencer budget", "optimize spend across tiers", or "compare budget scenarios"; produces a tier/platform/content allocation table, ROI and CPM/CPE projections, scenario comparisons, and mid-campaign reallocation moves. Not for building the full campaign plan — use…
sales-enablement-kit
Use when the user asks to "build battle cards", "prep the sales team for launch", or "write the internal launch FAQ"; produces the internal enablement kit for a sales-led launch — battle cards vs each named alternative (where we win / where they win / trap questions, every fact traceable), a sales talk track derived…