A referral-marketing guide for creating, improving, or reviewing programs that encourage customers or partners to recommend a product. It uses available evidence and marks whether claims are measured, estimated, or otherwise uncertain.

Use it to plan referral, affiliate, ambassador, partner, or refer-a-friend programs and their incentives. It can also help analyze referral results and recommend next steps.

It helps turn a broad word-of-mouth goal into a defined audience, objective, constraints, and success measure. It also avoids making changes or publishing anything without permission.

referrals — Skill for Claude Code by iamwaqargulzar/Marketing-Agent-OS

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 iamwaqargulzar/Marketing-Agent-OS --skill referrals

Clone the repo

git clone --depth 1 https://github.com/iamwaqargulzar/Marketing-Agent-OS

Made for: Claude Code.

Or install marketing-agent-os, the plugin that ships this one along with the rest of its 175 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/iamwaqargulzar/marketing-agent-os/referrals/github.svg)](https://agentmods.dev/skills/iamwaqargulzar/marketing-agent-os/referrals)

Your own site

<a href="https://agentmods.dev/skills/iamwaqargulzar/marketing-agent-os/referrals"><img src="https://agentmods.dev/badge/skills/iamwaqargulzar/marketing-agent-os/referrals/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/iamwaqargulzar/marketing-agent-os/referrals"><img src="https://agentmods.dev/badge/skills/iamwaqargulzar/marketing-agent-os/referrals.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 802 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.

Model	Per session	Once invoked
Fable 5.1	$0.00036	$0.00802
Opus 5.5	$0.00014	$0.00321
Sonnet 5.5	$0.00007	$0.00160
Haiku 4.5	$0.00004	$0.00080

Measured 22d ago against content hash 887902286442, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

referrals 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 22d 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.

skills/referrals/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Referrals

Quick Start

Use this skill for referrals. Start from the user’s concrete objective and available evidence; do not substitute generic marketing advice for task-specific analysis.

Skill Contract

Reads: user-provided context; relevant project files; .agents/product-marketing.md when present; approved public or connected data sources.
Writes: recommendations and artifacts in the response by default. Persistent file/account changes require explicit request or authorization.
Evidence: label consequential claims as measured, user-provided, calculated, estimated, or proxy. Never upgrade uncertainty silently.
Side effects: do not publish, send, spend, delete, mutate accounts, or persist registry truth without user authorization.
Freshness: verify current platform rules, search eligibility, ad policies, model/tool capabilities, laws, pricing, and other time-sensitive claims before acting.

Instructions

Define the exact referrals objective, audience/scope, constraints and success metric before recommending action.
Load shared product-marketing context when it materially changes the answer; ask only for missing facts that block a decision.
Collect the minimum evidence needed for referrals. Distinguish direct observations from assumptions and proxies.
Execute the referrals analysis or artifact using the domain checklist below; prefer specific outputs over generic best-practice lists.
Prioritize actions by impact, confidence, effort and dependency. Identify what would falsify important assumptions.
For external side effects, publishing, sending, spend changes, account changes or persistent writes, obtain authorization first.
Finish with decision-ready output, evidence labels, open loops, and no more than three next-best skills.

Reviews and affiliate operations

Read references/reviews-and-affiliates.md for honest review programs, responses, testimonial permission, affiliate terms, reconciliation, and incremental measurement. Keep review requests distinct from positive-feedback gating and referral payout mechanics. Default to no review incentive pending a current platform-specific check; public reviews do not automatically authorize reuse in advertising.

Read the full file on GitHub · 79 lines

Files

What ships with it

5 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.

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.

22d ago Changed · +4 lines · -71 tokens per session 887902286442
2mo ago First seen · 75 lines · 107 tokens per session scan A 872bb9347aa9

Subscribe to this mod's changes

referrals is a skill published in the GitHub repository iamwaqargulzar/Marketing-Agent-OS (8 stars, last pushed 3d ago), licensed Apache-2.0. It adds 36 tokens to every session and 802 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-05.

Claude Code Marketing and SEO aeo agent-skills ai-agents amp answer-engine-optimization

referrals next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
referralsiamwaqargulzar/Marketing-Agent-OS	Skill	8	3d ago	Apache-2.0	A	36	Claude Code
ansvisor-aeo-coach-standaloneansvisor/ansvisor	Skill	232	yesterday	MIT	A	148	Claude Code, Codex
aeroCanonry/canonry	Skill	198	yesterday	MIT	A	93	Claude Code
refreshansvisor/ansvisor	Skill	232	yesterday	MIT	A	17	Claude Code, Codex
wrongclaimansvisor/ansvisor	Skill	232	yesterday	MIT	A	17	Claude Code, Codex
seo-vertical-detectHainrixz/claude-seo-ai	Skill	82	13d ago	MIT	A	71	Claude Code
mcp-geoAKzar1el/mcp-geo	Skill	40	yesterday	MIT	A	42	Claude Code