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-twitter-cardWrote 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-twitter-card)<a href="https://agentmods.dev/skills/slogsdon/skills-design/design-twitter-card"><img src="https://agentmods.dev/badge/skills/slogsdon/skills-design/design-twitter-card/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-twitter-card"><img src="https://agentmods.dev/badge/skills/slogsdon/skills-design/design-twitter-card.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 | $0.00097 | $0.02723 |
| Opus 5 | $0.00048 | $0.01362 |
| Sonnet 5 | $0.00019 | $0.00545 |
| Haiku 4.5 | $0.00010 | $0.00272 |
Grade A, and why
design-twitter-card 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 11d 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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: twitter-card
Produces a pixel-exact HTML canvas for Twitter/X. Two canvas modes:
feed(default, 1600×900) — in-timeline post image at the recommended max-quality 16:9 ratioog(1200×630) — Open Graph link card for shared URLs from your site
Plus an optional companion tweet (280-char limit) or thread starter.
When to use
- User wants a visual asset for a tweet, an X thread cover, or an Open Graph card on their site
- A
DESIGN.mdexists for the brand
Inputs
- Required: brand slug, post headline / title (1 line)
- Optional: mode (
feed|og, defaultfeed), supporting line, attribution, companion tweet style
Output
./design/<brand-slug>/artifacts/twitter-<mode>-YYYY-MM-DD-<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. Pick the canvas mode
If user said "OG card" or "link card", use og (1200×630).
Otherwise default to feed (1600×900) — sharper, larger, displays better in-timeline.
3. Gather the brief
Ask in one message:
1. Headline — the dominant text on the canvas (max 10 words for feed mode, max 6 for OG)
2. Optional supporting line
3. Attribution — name + role, or leave blank
4. Companion tweet style: claim | thread-starter | quote | question | none
4. Pick variation — ARCHITECTURE FIRST
Pick ONE architecture archetype before any other axis. The single biggest cause of AI-editorial output is reaching for chrome-led by default.
- Architecture archetype (pick FIRST):
chrome-led— eyebrow + headline + footer band. Last resort. AI-editorial default; structural sameness across artifacts.type-only— type only, no chrome.number-led— single oversized number/stat dominates the canvas; rest is caption.object-of-content— the artifact IS the thing being said (transcript, list, fake printed page, receipt).pattern-led— typographic repetition fills the canvas; one element breaks the pattern.inverse-text— text becomes surface (carved-out headline, body wrapping negative space).
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.
- 11d ago First seen · 242 lines · 97 tokens per session scan A 6fffe7d3e9bd
design-twitter-card is a skill published in the GitHub repository slogsdon/skills-design (3 stars, last pushed 27d ago), licensed MIT. It adds 97 tokens to every session and 2,723 once invoked, about $0.0005 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
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.
canva
The Canva craft skill — produce on-brand social graphics, carousels, quote cards, infographics, and thumbnails at scale without a designer, and escape the "Canva look." Use when someone wants to design in Canva, make social graphics, set up a Brand Kit, batch-produce graphics (Bulk Create), resize one design for every…
pinterest-pin-design
The Pinterest pin design skill -- the visual half that pairs with pinterest-seo's keyword layer. Use when someone wants to design a pin, a Pinterest pin image, a pin text overlay, fresh pin variations for an existing URL, or board covers. Designs and briefs the 2:3 (1000x1500) vertical pin: one focal point, a keyword…
quote-cards-and-text-graphics
The craft of turning a single quote, line, or stat into a designed typographic graphic — quote cards, pull-quotes, text-on-image, stat cards, typography posts. Use when someone wants a quote card, a text graphic, a pull-quote, a stat card, or to turn a strong line into a shareable image. The design amplifies a strong…
design-and-templates
The reusable on-brand template-SYSTEM skill -- build a brand kit + a small set of reusable templates so a non-designer can produce consistent on-brand graphics fast across formats. Use when someone wants templates, a brand kit, a consistent visual system, or help choosing/using a design tool (Canva/Adobe…