founder-post-generator

founder-post-generator is a skill for Claude Code from First-Touch-Inc/firsttouch-agent-skill-packs. It costs 88 tokens per session (1,401 once invoked), scanned A, original, MIT.

A writing workflow that turns a founder’s opinions, customer evidence, market observations, and sales conversations into LinkedIn posts. It drafts the posts but does not publish them.

In plain words
What is it for?
It creates founder-voice post drafts, uses saved examples to match tone, and routes people who engage toward warm follow-up.
Why use it?
It helps founders post consistently and attract people who match their target audience, while keeping the final publishing decision with the founder.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the founder-pack plugin — 2 skills shipped together

Good fit It creates founder-voice post drafts, uses saved examples to match tone, and routes people who engage toward warm follow-up.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/first-touch-inc/firsttouch-agent-skill-packs/founder-post-generator
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 First-Touch-Inc/firsttouch-agent-skill-packs --skill founder-post-generator
Clone the repo
git clone --depth 1 https://github.com/First-Touch-Inc/firsttouch-agent-skill-packs

Made for: Claude Code.

Or install founder-pack, the plugin that ships this one along with the rest of its 2 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-post-generator

README.md
[![agentmods](https://agentmods.dev/badge/skills/first-touch-inc/firsttouch-agent-skill-packs/founder-post-generator/github.svg)](https://agentmods.dev/skills/first-touch-inc/firsttouch-agent-skill-packs/founder-post-generator)
Your own site
<a href="https://agentmods.dev/skills/first-touch-inc/firsttouch-agent-skill-packs/founder-post-generator"><img src="https://agentmods.dev/badge/skills/first-touch-inc/firsttouch-agent-skill-packs/founder-post-generator/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-post-generator

Your own site · 80×15
<a href="https://agentmods.dev/skills/first-touch-inc/firsttouch-agent-skill-packs/founder-post-generator"><img src="https://agentmods.dev/badge/skills/first-touch-inc/firsttouch-agent-skill-packs/founder-post-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,401 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 $0.00088 $0.01401
Opus 5 $0.00044 $0.00700
Sonnet 5 $0.00018 $0.00280
Haiku 4.5 $0.00009 $0.00140

Measured 9d ago against content hash 45de4bad65a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

founder-post-generator 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.

plugins/founder-pack/skills/founder-post-generator/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Founder Post Generator

Outcome: A steady stream of founder-voice LinkedIn posts that create the engagement the rest of this pack harvests. Posts feed Social Engagement monitoring; engagers feed warm-engager-followup; conversations feed pipeline. This skill drafts - the founder posts from their own account.

First-run note

This skill sends nothing and uses no daily send budget. Before the first run, capture two things (reuse them every run):

  1. Founder voice profile: 2-3 sample posts or messages the founder actually wrote, plus tone rules - phrases they use, phrases they hate, formality level, topics they will not touch. Save this as a reusable profile: restate it in the first run's output so the founder can keep it (notes file, saved prompt, agent memory). On every later run, if a profile exists, confirm "still accurate?" and reuse it - never make the founder re-explain their voice. Re-calibrate when a draft sounds off or roughly monthly.
  2. Audience: who should engage (the ICP from ../../references/onboarding.md). A post that attracts the wrong engagers creates busywork downstream.

When to use

  • "What should I post this week?"
  • Post engagement is thin and the warm-engager play has nothing to harvest
  • Before launching Social Engagement monitoring on the founder's own profile
  • A customer win, product lesson, or strong opinion is sitting unused

Step-by-step

1. Collect raw material

Ask for whichever exists - one strong input beats five weak ones:

  • A recent customer conversation, win, or objection that surprised the founder
  • A market observation ("everyone is doing X, we keep seeing Y")
  • A build-in-public moment: something shipped, broken, learned, or changed
  • A strong opinion the founder actually holds and will defend in comments When HubSpot is connected, closed-won stories and common deal objections are good seeds - but never use customer names or details without explicit approval.

2. Pick the post type

Five types, rotate across the week - do not post the same shape twice in a row:

Read the full file on GitHub · 87 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 · 87 lines · 88 tokens per session scan A 45de4bad65a5

Subscribe to this mod's changes

founder-post-generator is a skill published in the GitHub repository First-Touch-Inc/firsttouch-agent-skill-packs (5 stars, last pushed 2mo ago), licensed MIT. It adds 88 tokens to every session and 1,401 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 2026-08-31.