Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/slogsdon/skills-designnpx agentmods add skills/slogsdon/skills-design/design-linkedin-postWrote 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/slogsdon/skills-design/design-linkedin-post)<a href="https://agentmods.dev/skills/slogsdon/skills-design/design-linkedin-post"><img src="https://agentmods.dev/badge/skills/slogsdon/skills-design/design-linkedin-post/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/slogsdon/skills-design/design-linkedin-post"><img src="https://agentmods.dev/badge/skills/slogsdon/skills-design/design-linkedin-post.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 | $0.00086 | $0.03093 |
| Opus 5 | $0.00043 | $0.01546 |
| Sonnet 5 | $0.00017 | $0.00619 |
| Haiku 4.5 | $0.00009 | $0.00309 |
Grade A, and why
design-linkedin-post 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 10d 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 — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: linkedin-post
Produces a pixel-exact 1200×627 HTML canvas suitable for screenshotting and uploading to LinkedIn as a post image, plus a markdown block with the recommended companion text. Reads from a brand's DESIGN.md system — never hardcodes brand values.
When to use
- User wants a visual asset for a LinkedIn post (announcement, milestone, opinion piece, takeaway from a project)
- A
DESIGN.mdexists for the brand. If it doesn't, stop and tell the user to run/design-plan→/design-systemfirst.
Inputs
- Required: brand slug, post topic / headline (1 line)
- Optional: key claim or supporting line, CTA text, attribution (author name + role), variation hints
Output
./design/<brand-slug>/artifacts/linkedin-YYYY-MM-DD-<topic-slug>.html
Steps
1. Verify brand exists
test -f ./design/<brand-slug>/tokens.css
If missing, stop and instruct the user to build the design system first.
2. Gather the brief
Ask in one message:
1. Headline — the single sentence on the image (max 8 words for legibility at feed scale)
2. Optional supporting line (max 14 words)
3. Optional CTA text (e.g. "Read more →") — leave blank to omit
4. Attribution — your name + role, or leave blank for a clean unsigned look
5. Companion text style: insight | story | announcement | question
3. Pick variation — ARCHITECTURE FIRST
Before anything else, pick ONE architecture archetype. This is the structural skeleton; everything else is decoration. The single biggest cause of AI-editorial output is reaching for chrome-led by default.
- Architecture archetype (most-important choice — pick FIRST):
chrome-led— eyebrow + headline + signature-row footer. Treat as the LAST resort. This is the AI-editorial default; using it more than once per brand creates structural sameness.type-only— nothing but the type. No eyebrow, no footer, no rules. The headline IS the artifact.number-led— one oversized number/stat dominates ~60%+ of canvas; the rest is short caption. Everything bows to the figure.object-of-content— the artifact IS the thing being communicated. Looks like a fragment of the product (a transcript, a printed page, a list of entries, a receipt). The "post" frame disappears.pattern-led— typographic pattern or repetition fills the canvas; one element breaks the pattern as the punctum.inverse-text— text becomes surface. Massive headline with body text wrapping the negative space; or a block of body type with the headline carved out as a void.
What ships with it
1 file 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.
- 10d ago First seen · 259 lines · 86 tokens per session scan A f7f8e02ca5be
design-linkedin-post is a skill published in the GitHub repository slogsdon/skills-design (3 stars, last pushed 27d ago), licensed MIT. It adds 86 tokens to every session and 3,093 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
self-media-short-video
A planning and production guide for vertical short videos on platforms such as TikTok, Xiaohongshu, and WeChat Channels.
self-media-wechat-publisher
A publishing workflow that turns approved Markdown into formatted WeChat articles or image posts and saves them as drafts.
paint
Paint a complete visual universe with genjutsu - art direction brainstorm, design system, implementation, audit. Anti-AI-slop design pipeline. Adapts to Web, Android (Compose), Apple (SwiftUI).
smart-illustrator
An image-generation tool for adding illustrations to articles, creating slide presentations and infographics, or making cover images and thumbnails. It can also create prompts without generating the images.
tt-humanizer
Remove the AI-script tells viewers hear in a TikTok spoken script and caption: 2026 vocabulary by density, reveal bridges, staccato stacks, stacked triads, performed sincerity, written-not-spoken phrasing, "hey guys" filler; caps em dashes. Includes --mode audit pre-film check (hook, completion design, caption fit)…
tiktok-marketing
Plan, script, caption, and publish short-form video for TikTok. Use when the user wants to write the first 1-3 second hook (spoken line plus on-screen text), draft a caption under 2,200 chars with TikTok settings and hashtags, ride a trending sound without being cringe, strip AI tells from a spoken script to sound…