referral-loop-design

referral-loop-design is a skill for Claude Code, Codex from deciqAI/knowledge-skills. It costs 77 tokens per session (638 once invoked), scanned A, original, MIT.

A repeatable cycle in which a satisfied customer invites someone else, the new user quickly receives value, and that user is then prompted to invite another person. A referral program is the system of incentives, timing, and sharing steps that supports the cycle.

In plain words
What is it for?
Use it to design referral programs, choose the right moment and reward, reduce sharing friction, guide new users to value, and measure invite conversion.
Why use it?
It helps replace isolated “refer a friend” requests with a process that can produce ongoing word-of-mouth growth. It also makes clear that referrals spread existing customer satisfaction rather than fixing poor retention.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to design referral programs, choose the right moment and reward, reduce sharing friction, guide new users to value, and measure invite conversion.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/deciqai/knowledge-skills/referral-loop-design
Install

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.

Any agent
npx skills add deciqAI/knowledge-skills --skill referral-loop-design
Clone the repo
git clone --depth 1 https://github.com/deciqAI/knowledge-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for referral-loop-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/deciqai/knowledge-skills/referral-loop-design/github.svg)](https://agentmods.dev/skills/deciqai/knowledge-skills/referral-loop-design)
Your own site
<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/referral-loop-design"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/referral-loop-design/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.

agentmods 80×15 button for referral-loop-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/referral-loop-design"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/referral-loop-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 638 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00077 $0.00638
Opus 5 $0.00039 $0.00319
Sonnet 5 $0.00015 $0.00128
Haiku 4.5 $0.00008 $0.00064

Measured 9d ago against content hash 61ffcb8a2679, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

referral-loop-design 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 9d 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.

referral-loop-design/SKILL.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Referral Loop Design — Turn Customers into a Channel

Overview

A referral loop is a repeatable cycle where using the product produces new users: a happy customer is prompted, at the right moment, with the right incentive and an easy share, and the new user enters the same loop. Loops compound; one-off "refer a friend" banners don't. Referrals only work on a product people already value — they amplify love, they don't create it.

The Process

  1. Verify the precondition — strong retention/NPS. Gate: referring a product people don't love just spreads churn — fix retention first.
  2. Pick the trigger moment — right after a value peak (a win, a result, an "aha"), not at signup. (Pairs with peak-end thinking.)
  3. Choose the incentive type — double-sided (giver + receiver), status, or pure delight — matched to the audience's motivation.
  4. Remove friction — one-tap share, pre-written message, obvious reward. Gate: any extra step halves participation.
  5. Close the loop — the referred user lands in an experience that gets them to their own value fast, then hits the same trigger.
  6. Instrument K-factor — invites sent × conversion; iterate the weakest step. Gate: K without measuring each step = you can't tell what to fix.

When to Use

  • Loved product with weak organic spread
  • Designing/relaunching a referral program
  • Cheap growth for low-budget SMBs/creators

Applying It Well

  • Timing (post-value) matters more than reward size.
  • Double-sided incentives usually beat one-sided.
  • Referred users often retain better — treat their onboarding as sacred.

Red Flags

  • Bolting referrals onto a leaky-retention product.
  • Asking at signup, before any value.
  • Multi-step share flows that kill participation.

Verification

  • Retention/NPS precondition met
  • Trigger fires at a value peak
  • Incentive matched to audience; share is one-tap
  • Each loop step instrumented and iterated

Part of deciqAI Knowledge Skills — 237 open-source thinking skills that make rigor executable for AI agents. The same skills power every deciqAI agent, which runs them autonomously to operate your company. See it run → https://www.deciqai.com/s/referral-loop-design · Built by deciqAI · github.com/deciqAI · Contributions welcome.

Read the full file on GitHub · 44 lines

Changes

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.

  1. 9d ago First seen · 44 lines · 77 tokens per session scan A 61ffcb8a2679

Subscribe to this mod's changes

referral-loop-design is a skill published in the GitHub repository deciqAI/knowledge-skills (10 stars, last pushed 11d ago), licensed MIT. It adds 77 tokens to every session and 638 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 2026-09-03.

Related

Other skills, from other repositories

edge-tts

Text-to-speech conversion using uvx edge-tts for generating audio from text. Use when (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, driving, cooking). (3) User wants a specific voice, speed, pitch, or format for TTS…

aahl/skills · 85 tokens

mcp-deepwiki

Skills for accessing and searching docs in DeepWiki/GitHub’s public code repositories can help users understand open-source project source codes, and users can also ask questions directly about the code docs.

aahl/skills · 44 tokens

tianqi

A weather-lookup workflow for Chinese locations, covering forecasts, hourly conditions, weather warnings, and daily-life indexes.

aahl/skills · 24 tokens

cto-advisor

Records technical decisions that serve a business outcome: constraints, architecture options, build-or-buy tradeoffs, and a justified skill selection. Use when the CEO asks "which architecture fits", "should we build or buy", "which skill should this department use", or "review our technical plan".

alebgl77/claude-inc · 62 tokens

compliance-check

Compliance pre-flight for a feature, campaign, or initiative — maps the data and activity involved, checks applicable regimes (privacy/GDPR-style, consumer protection, marketing rules, sector-specific), lists required approvals and notices, builds a gap list with remediation owners, and ends in a go/no-go…

alebgl77/claude-inc · 98 tokens

plan-payroll

Plans payroll cash: true loaded cost per hire (gross plus employer taxes, benefits, tools), a payroll calendar with cutoffs and cash-out dates, a scenario table for new hire vs raise vs contractor-vs-employee, and a payroll-to-revenue check against rough industry bands. Use when the user asks "can I afford to hire"…

alebgl77/claude-inc · 0 tokens