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.
npx skills add cmj-hub/claude-founder-brand --skill linkedin-craftgit clone --depth 1 https://github.com/cmj-hub/claude-founder-brandWrote 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.
[](https://agentmods.dev/skills/cmj-hub/claude-founder-brand/linkedin-craft)<a href="https://agentmods.dev/skills/cmj-hub/claude-founder-brand/linkedin-craft"><img src="https://agentmods.dev/badge/skills/cmj-hub/claude-founder-brand/linkedin-craft/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.
<a href="https://agentmods.dev/skills/cmj-hub/claude-founder-brand/linkedin-craft"><img src="https://agentmods.dev/badge/skills/cmj-hub/claude-founder-brand/linkedin-craft.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00083 | $0.00744 |
| Opus 5 | $0.00042 | $0.00372 |
| Sonnet 5 | $0.00017 | $0.00149 |
| Haiku 4.5 | $0.00008 | $0.00074 |
Grade A, and why
linkedin-craft 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.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LinkedIn Craft — sub-skill
LinkedIn-specific post construction and critique.
Activation
Loaded by founder-brand on:
- "LinkedIn post about..."
- "5 hook variants for..."
- "Critique this LinkedIn draft"
- "Better hook for this topic"
Modes
Mode A — generate 5 hook variants
Given a topic, produce one hook per archetype:
# Hook variants — <topic>
| # | Archetype | Hook |
|---|---|---|
| 1 | Contrarian | "Most teams do X. The lever is actually Y." |
| 2 | Specific receipt | "<Metric>: <number> in <timeframe>. The lever wasn't <obvious thing>." |
| 3 | Confession | "I used to think X. After <N> failed attempts I figured out it was Y." |
| 4 | Pattern observation | "I've reviewed <N> <thing> this year. One pattern keeps showing up." |
| 5 | Question reframe | "Stop asking <usual Q>. Ask <better Q> instead." |
## Recommended primary
<#N> — <one-sentence rationale on why this archetype fits the topic best>
Mode B — format for skim
Take a finished post and reformat for LinkedIn-native skim:
[1-sentence hook]
[single-line body sentence]
[single-line body sentence]
[single-line body sentence]
[Receipt block:]
- Bullet 1
- Bullet 2
- Bullet 3
[1-line close — direct, no engagement bait]
#hashtag1 #hashtag2
Max 200 words. Max 3 hashtags. No emoji blocks.
Mode C — critique a draft
# Draft critique
**Voice score:** <0-100>
| Dimension | Score | Issue |
|---|---|---|
| Hook strength | <0-25>/25 | <one sentence> |
| Specificity (receipts) | <0-25>/25 | <one sentence> |
| Voice (founder, not thought-leader) | <0-25>/25 | <one sentence> |
| Format (LinkedIn-skim) | <0-15>/15 | <one sentence> |
| No anti-patterns | <0-10>/10 | <list any hits> |
## Single weakest line
Original: "<line>"
Rewrite: "<better>"
Rationale: <one sentence>
## Anti-pattern hits
- <hit 1>
- <hit 2>
## Verdict
<ship / ship-after-rewrite / start-over>
Mode D — better hook for topic
User says: "I want to write about . Give me a better hook." Generate 3 strong hook candidates across the 5 archetypes, recommend the strongest.
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.
- 3d ago Changed · -1 lines 99748e59f233
- 11d ago First seen · 108 lines · 83 tokens per session scan A 917475c8d0fd
linkedin-craft is a skill published in the GitHub repository cmj-hub/claude-founder-brand (2 stars, last pushed 3d ago), licensed MIT. It adds 83 tokens to every session and 744 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.
Other skills, from other repositories
linkedin-carousels
Use when building a LinkedIn carousel / document post — the swipeable multi-page PDF — slide by slide: cover hook, narrative arc, one idea per slide, CTA closer, PDF export spec. NOT the account/format plan (that is linkedin-strategy), NOT a text or single-image feed post (that is linkedin-content), NOT a 16:9 talk…
linkedin-profile-optimizer
High-intent expert for LinkedIn profile checks, authority building, and SEO optimization. Invoke to audit, rewrite, and enhance profiles for top 1% positioning.
LinkedIn Automation
Automate LinkedIn marketing, lead generation, content publishing, and professional networking.
linkedin-post-writer
Draft a viral-ready LinkedIn post using one of ten proven hook formulas, sized 900 to 1,300 characters, shown as a draft before anything touches LinkedIn. Use when you have a topic and want a post that proves competence and pulls engagement.
linkedin-profile-auditor
Audit the user's own LinkedIn profile as a conversion asset, scoring each element against the buyer who lands there after a post and rewriting the weakest one. Use to turn a passive profile into one that earns the follow, the connect, or the DM.
linkedin-carousel-writer
Turn a post into carousel slide copy that mirrors the post 1:1, a cover hook plus 6-9 one-idea body slides plus a CTA slide. Use when you want a post to travel further as a saveable carousel.