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 naveedharri/benai-skills --skill bens-linkedin-post-writergit clone --depth 1 https://github.com/naveedharri/benai-skillsWrote 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/naveedharri/benai-skills/bens-linkedin-post-writer)<a href="https://agentmods.dev/skills/naveedharri/benai-skills/bens-linkedin-post-writer"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/bens-linkedin-post-writer/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/naveedharri/benai-skills/bens-linkedin-post-writer"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/bens-linkedin-post-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Memory Poisoning · line 125 Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.Fix: Do not allow untrusted input to persist in agent memory or context. Validate all content before storing and implement memory isolation between sessions.
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 | $0.00166 | $0.01663 |
| Opus 5 | $0.00083 | $0.00831 |
| Sonnet 5 | $0.00033 | $0.00333 |
| Haiku 4.5 | $0.00017 | $0.00166 |
Grade A, and why
bens-linkedin-post-writer 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 7d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ben's LinkedIn Post Writer
Take source material (YouTube videos, blog articles, guides, or raw insights) and walk the user through a structured, collaborative process to create a LinkedIn post that sounds authentically like Ben Van Sprundel.
This is an iterative, step-by-step process. Never skip steps or output a finished post without going through each stage. At most steps, present multiple options (typically 10) and wait for the user to choose the direction.
Reference documents
Read each one only when its step says to. Do not frontload everything at once.
| Document | What it contains | When to read |
|---|---|---|
references/performance-defaults.md |
Audience context + what works and what underperforms | Step 2 |
references/frameworks.md |
The six writing frameworks + performance rankings | Step 3 |
references/linkedin-examples.md |
Ben's real posts, the ground truth for voice and tone | Steps 3, 5 |
references/hook-templates.md |
80+ hook templates by category with psychological triggers | Step 4 |
references/writing-style.md |
Ben's sentence, tone, and flow rules | Step 5 |
references/humanization.md |
AI-tell removal pass + iteration questions | Step 5 (before delivery) |
Step 0: Source intake
Always use provided data first. Only fetch external data when the user gives a URL without accompanying text.
- User provides a transcript, article text, notes, or a document: read it, give a 1-2 sentence summary, move on.
- User provides only an insight or idea (no source): summarize it back to confirm. This is valid input.
- User provides only a URL:
- YouTube: if the Apify MCP server is available, get the transcript with an actor like
topaz_sharingan/Youtube-Transcript-Scraper-1. Otherwise ask the user to paste the transcript. - Blog/article: prefer an Apify web scraper actor, else WebFetch, else ask the user to paste the text.
- YouTube: if the Apify MCP server is available, get the transcript with an actor like
- Never scrape LinkedIn profiles or posts. If LinkedIn is the source, ask the user to paste the text.
What ships with it
6 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.
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.
- 7d ago First seen · 142 lines · 166 tokens per session scan A efd6814a6dd4
bens-linkedin-post-writer is a skill published in the GitHub repository naveedharri/benai-skills (61 stars, last pushed today), licensed MIT. It adds 166 tokens to every session and 1,663 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 2026-09-05.
Other skills, from other repositories
project
A single starting point for setting up an AI-assisted project in Claude Cowork. It asks questions about the work, reviews available add-ons, and creates project instructions, custom agents, and connected workflows.
design-sync-upload
An uploader for design-system files such as DESIGN.md, tokens, logos, fonts, and images into Claude Design. It can either use an authenticated connection or prepare a folder and guide for manual upload.
doc-html-slide
A renderer that turns presentation content into a single HTML slide deck that opens directly in a browser. It creates a 16:9 slide sequence with navigation, fullscreen viewing, printing to PDF, and speaker-note controls.
cs-channel-message
A channel-message writing tool for search ads, advertising, customer relationship messages, and app notifications. It uses the NCM sequence—Need, Channel, Moment, Message, and CTA—to adapt wording to where and when customers see it.
design-tokens-transformer
A converter for design tokens, which are named values for colors, fonts, spacing, borders, shadows, and motion. It translates one shared token source into CSS variables and Tailwind or shadcn-style theme files, and can convert them back for checking.
media-higgsfield-explainer
A Higgsfield workflow for making non-photorealistic narrated explainer videos. It pairs each narration line with a 10-second animated clip and joins the clips into one finished video.