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 rajitsaha/100xprism --skill referral-programgit clone --depth 1 https://github.com/rajitsaha/100xprismWrote 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/rajitsaha/100xprism/referral-program)<a href="https://agentmods.dev/skills/rajitsaha/100xprism/referral-program"><img src="https://agentmods.dev/badge/skills/rajitsaha/100xprism/referral-program.svg" alt="Measured on agentmods" 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 | $0.00063 | $0.01456 |
| Opus 5 | $0.00032 | $0.00728 |
| Sonnet 5 | $0.00013 | $0.00291 |
| Haiku 4.5 | $0.00006 | $0.00146 |
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 7d 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Referral & Affiliate Programs
Design and optimize programs that turn customers into growth engines.
Before Starting
Product context: If .agents/product-marketing-context.md exists (or .claude/product-marketing-context.md in older setups), read it first and tailor output to it; only ask for what it doesn't cover.
Gather (ask if not provided):
- Program Type — customer referral, affiliate, or both? B2B or B2C? Average customer LTV? Current CAC from other channels?
- Current State — existing program? Referral rate (% who refer)? Incentives tried?
- Product Fit — shareable product? Network effects? Do customers naturally talk about it?
- Resources — tools/platforms in use or considered? Budget for incentives?
Referral vs. Affiliate
Customer referral programs — best for existing customers recommending to their network, products with natural word-of-mouth, lower-ticket or self-serve products. Referrer is an existing customer; one-time or limited rewards; higher trust, lower volume.
Affiliate programs — best for reaching audiences you don't have access to (content creators, influencers, bloggers) and higher-ticket products that justify commissions. Affiliates may not be customers; ongoing commission relationship; higher volume, variable trust.
Referral Program Design
The Referral Loop
Trigger Moment → Share Action → Convert Referred → Reward → (Loop)
Step 1: Identify Trigger Moments
High-intent moments: right after first "aha" moment, after achieving a milestone, after exceptional support, after renewing or upgrading.
Step 2: Design Share Mechanism
Ranked by effectiveness:
- In-product sharing (highest conversion)
- Personalized link
- Email invitation
- Social sharing
- Referral code (works offline)
Step 3: Choose Incentive Structure
- Single-sided (referrer only): simpler, works for high-value products
- Double-sided (both parties): higher conversion, win-win framing
- Tiered: gamifies referrals, increases engagement
What ships with it
4 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.
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.
- 7d ago First seen · 192 lines · 63 tokens per session scan A bc275b53582c
referral-program is a skill published in the GitHub repository rajitsaha/100xprism (10 stars, last pushed 6d ago), licensed MIT. It adds 63 tokens to every session and 1,456 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
ad-campaign-analyzer
Analyze cross-channel campaign data, quantify uncertainty, and propose evidence-labeled budget tests without overstating causality.
google-analytics
Skill "google-analytics" from VKirill/claude-lane-stack, covering version requirements (may 2026), usage, use this skill when, do not use this skill when and purpose.
google-tag-manager
Skill "google-tag-manager" from VKirill/claude-lane-stack, covering 🎯 version requirements (june 2026), usage, use this skill when, do not use this skill when and purpose.
analyzing-windows-lnk-files-for-artifacts
Parse Windows LNK shortcut files to extract target paths, timestamps, volume information, and machine identifiers for forensic timeline reconstruction.
openapi-designer
Design complete OpenAPI 3.1 specifications for RESTful APIs. Covers schemas, security, examples, webhooks, and documentation generation.
laravel-api
Build production-ready RESTful APIs with Laravel. Covers authentication (Sanctum/Passport), versioning, resources, rate limiting, and API testing.