founder-brand

founder-brand is a skill for Claude Code from cmj-hub/claude-founder-brand. It costs 162 tokens per session (1,720 once invoked), scanned A, original, MIT.

A content-planning and writing system for business founders who publish on LinkedIn, a professional social network. It organizes posts around four themes: ideas, evidence, working methods, and personal experience.

In plain words
What is it for?
It helps create LinkedIn posts, plan a 12-week publishing schedule, generate opening lines, and critique drafts against the stated writing guidelines.
Why use it?
It gives founders a repeatable way to plan several weeks of posts and review drafts for an overly promotional or artificial writing style.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the founder-brand plugin — 5 skills shipped together

Good fit It helps create LinkedIn posts, plan a 12-week publishing schedule, generate opening lines, and critique drafts against the stated writing guidelines.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cmj-hub/claude-founder-brand/founder-brand
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 cmj-hub/claude-founder-brand --skill founder-brand
Clone the repo
git clone --depth 1 https://github.com/cmj-hub/claude-founder-brand

Made for: Claude Code.

Or install founder-brand, the plugin that ships this one along with the rest of its 5 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.

agentmods badge for founder-brand

README.md
[![agentmods](https://agentmods.dev/badge/skills/cmj-hub/claude-founder-brand/founder-brand/github.svg)](https://agentmods.dev/skills/cmj-hub/claude-founder-brand/founder-brand)
Your own site
<a href="https://agentmods.dev/skills/cmj-hub/claude-founder-brand/founder-brand"><img src="https://agentmods.dev/badge/skills/cmj-hub/claude-founder-brand/founder-brand/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 founder-brand

Your own site · 80×15
<a href="https://agentmods.dev/skills/cmj-hub/claude-founder-brand/founder-brand"><img src="https://agentmods.dev/badge/skills/cmj-hub/claude-founder-brand/founder-brand.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 162 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,720 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 $0.00162 $0.01720
Opus 5 $0.00081 $0.00860
Sonnet 5 $0.00032 $0.00344
Haiku 4.5 $0.00016 $0.00172

Measured 3d ago against content hash a5c37bf5c516, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

founder-brand 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 3d 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.

founder-brand/SKILL.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Founder Brand — Founder-Led Social System

Compounding content engine for B2B founders. Produces LinkedIn-native posts on a 4-pillar rotation, plans a 12-week content engine, and critiques drafts against the JMC "founder voice" rubric (no thought-leader voice, no LinkedIn-influencer cadence, no AI-detection signals).

Quick reference

Slash What it does
/founder-brand Interactive — detect intent, route to a sub-skill
/founder-brand content <pillar> Generate a LinkedIn post on a specific pillar
/founder-brand engine Plan a 12-week content engine across all 4 pillars
/founder-brand critique <post> Critique a draft for voice + anti-patterns
/founder-brand hooks <topic> Generate 5 hook variants across the 5 hook archetypes

The framework — 4 content pillars

Rotate weekly. Don't do all four in one week (overwhelming) or skip a pillar for 4+ weeks (drift). The 4 pillars:

# Pillar Job Example
1 Pillar Big claim / point of view / contrarian take "We don't run cold email programs that don't anchor on a PSP. Here's why."
2 Proof Case study / specific metric / receipt "Series-B SaaS — 14 SQLs in 30 days from one PSP rewrite. Here's the breakdown."
3 Process How you actually do the work / SOP / framework "Our 7-step Pain Signal Profile worksheet, with the 3 places teams get stuck."
4 Person The human behind the work — story, stake, reason you care "I shipped 3 outbound programs that failed before I figured out the PSP layer."

The 5 hook archetypes

The first line of any post does one of these jobs. If it doesn't, the post won't pull demand.

# Hook Pattern Example
1 Contrarian "Most teams do X. We do Y instead — here's why." "Most outbound programs blame the SDRs. The actual issue is upstream."
2 Specific receipt ": . ." "14 SQLs in 30 days. The lever wasn't the sequence — it was the PSP."
3 Confession "I used to think X. I was wrong. Here's what I learned." "I used to think cold email volume was the lever. After 3 failed programs, I figured out it wasn't."
4 Pattern observation "I've reviewed N . Here's the one pattern that keeps showing up." "Reviewed 60 cold email programs this year. One pattern shows up in every program that's hitting."
5 Question reframe "Stop asking . Ask instead." "Stop asking 'what's our ICP?' Ask 'what just happened publicly that proves we should reach out?'"

Read the full file on GitHub · 141 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. 3d ago Changed · -1 lines a5c37bf5c516
  2. 12d ago First seen · 142 lines · 162 tokens per session scan A b6697b6646f3

Subscribe to this mod's changes

founder-brand is a skill published in the GitHub repository cmj-hub/claude-founder-brand (2 stars, last pushed 3d ago), licensed MIT. It adds 162 tokens to every session and 1,720 once invoked, about $0.0008 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.

Related

Other skills, from other repositories