lead-gen

lead-gen is a skill for Claude Code, Codex from lucasheriques/shipmate. It costs 65 tokens per session (2,200 once invoked), scanned A, original, MIT.

A lead-generation planning procedure based on Hormozi's Core Four framework. A lead is someone you can contact, while an engaged lead has shown interest by opting in, replying, or booking.

In plain words
What is it for?
Use it to design lead magnets, warm or cold outreach, content, paid advertising, referral programs, affiliate programs, or employee-led lead generation.
Why use it?
It helps diagnose an empty sales pipeline and choose an acquisition approach around actual interested prospects rather than impressions, followers, or list size.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/lucasheriques/shipmate/lead-gen
Any agent
npx skills add lucasheriques/shipmate --skill lead-gen
Clone the repo
git clone --depth 1 https://github.com/lucasheriques/shipmate

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 lead-gen

README.md
[![agentmods](https://agentmods.dev/badge/skills/lucasheriques/shipmate/lead-gen.svg)](https://agentmods.dev/skills/lucasheriques/shipmate/lead-gen)
Your own site
<a href="https://agentmods.dev/skills/lucasheriques/shipmate/lead-gen"><img src="https://agentmods.dev/badge/skills/lucasheriques/shipmate/lead-gen.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,200 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00065 $0.02200
Opus 5 $0.00032 $0.01100
Sonnet 5 $0.00013 $0.00440
Haiku 4.5 $0.00006 $0.00220

Measured 4d ago against content hash f26ecd0738ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lead-gen 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 4d 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/lead-gen/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lead generation (Hormozi Core Four)

When to use

Any task shaped like "get more engaged leads": designing a lead magnet, picking or scaling an acquisition channel, planning outreach/content/ads, building referral or affiliate programs, or diagnosing an empty pipeline. Assumes a core offer already exists; if the offer itself is weak, fix that first.

The procedure

Phase 1 — Define the unit: engaged leads

  1. A lead is anyone you can contact. An engaged lead is someone who showed interest (opted in, replied, booked). Engaged leads are the only output that counts — never impressions, followers, or list size.
  2. Before designing anything, write down: current engaged leads per week, per channel. If nobody can answer this, instrument it first.

Phase 2 — Design the lead magnet (7 steps)

Advertise the core offer directly when it's cheap and impulse-friendly; use a lead magnet when it's expensive or considered. A lead magnet is a complete solution to a narrow problem that, once solved, reveals the problem your core offer solves.

  1. Pick the problem and person. Narrow, meaningful, and its next revealed problem must be one your core offer solves.
  2. Pick the solution type (one of three): reveal their problem (diagnosis/audit — best when waiting makes it worse), sample or trial (best for recurring offers), or one step of a multi-step process.
  3. Pick the delivery vehicle (one of four): software/tool, information, service, or physical product. 3 types x 4 vehicles = up to 12 magnets per problem; rotate them.
  4. Test the name — headline first, then image, then subheadline. The headline is ~80% of the ad spend's leverage.
  5. Make it easy to consume — offer every format you can (video, audio, text, tool); multi-format lifts take rates 2-4x.
  6. Make it darn good — give away the secrets, sell the implementation. It must be good enough to charge for; most consumers never buy, but all of them judge you on it.
  7. Make the CTA obvious: say exactly what to do, plus a real reason to do it now (ethical scarcity = advertise actual capacity limits; deadlines; any stated reason beats none).

Read the full file on GitHub · 95 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. 4d ago First seen · 95 lines · 65 tokens per session scan A f26ecd0738ac

Subscribe to this mod's changes

lead-gen is a skill published in the GitHub repository lucasheriques/shipmate (4 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 2,200 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.