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 m-binimran/design-pack --skill social-graphicsgit clone --depth 1 https://github.com/m-binimran/design-packWrote 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/m-binimran/design-pack/social-graphics)<a href="https://agentmods.dev/skills/m-binimran/design-pack/social-graphics"><img src="https://agentmods.dev/badge/skills/m-binimran/design-pack/social-graphics/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/m-binimran/design-pack/social-graphics"><img src="https://agentmods.dev/badge/skills/m-binimran/design-pack/social-graphics.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 | $0.00042 | $0.00327 |
| Opus 5 | $0.00021 | $0.00163 |
| Sonnet 5 | $0.00008 | $0.00065 |
| Haiku 4.5 | $0.00004 | $0.00033 |
Grade A, and why
social-graphics 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 8d 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.
What it actually says
social-graphics
One concept, correctly sized for every platform, on-brand.
Platform sizes (verify current specs)
- Instagram post 1080x1080 / portrait 1080x1350; Story/Reel 1080x1920.
- Facebook/LinkedIn shared ~1200x630; X ~1600x900.
- YouTube thumbnail 1280x720; cover/banner per platform. Keep text inside safe areas; mind platform UI overlap on stories.
Process
- One strong concept (headline, hero visual, CTA) from the brand kit.
- Generate/lay out via Canva (branded) or
image-generatefor custom hero art. - Resize to each platform - reflow, don't just crop; keep hierarchy and safe areas.
- Check contrast of text over imagery (the
contrast-guardhook +accessibility-contrast). - Export + name per platform (hand to
asset-export); note licensing.
Output
- The graphic set (one per platform, confirmed from the connector), with sizes + the brief + licensing notes.
Guardrails
- On-brand colours/type/logo; text legible over imagery (contrast).
- Fair platform ad rules; record stock/AI licensing. Confirm connector output is real.
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.
- 8d ago First seen · 29 lines · 42 tokens per session scan A 795a6ff54d98
social-graphics is a skill published in the GitHub repository m-binimran/design-pack (3 stars, last pushed 2mo ago), licensed MIT. It adds 42 tokens to every session and 327 once invoked, about $0.0002 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
deck-outline
This skill should be used when the user asks to "outline a deck on X," "what's the storyline for this deck," "build a slide-by-slide outline," or needs a presentation structured before any actual slide design happens.
treatment
Kiến trúc & dựng HỒ SƠ TREATMENT đạo diễn ColorMedia (v1.3 — generate-first). Nhận kịch bản/brief đã chốt → dựng treatment theo Nguyên lý 3 Điểm Chạm (Thị giác – Thính giác – Trái tim), bẻ shot + storyboard, rồi CHỦ ĐỘNG TẠO ASSET THẬT: ảnh reference/keyvisual/storyboard bằng ChatGPT Image 2 (qua Claude-in-Chrome)…
ad-creative-studio
Use when the user wants to CREATE ad creative — design new Facebook/Instagram/Google ads (static OR video), generate ad images, write ad copy, or turn competitor intel into their own ads. Triggers include "make me some ads", "create ad creative", "design an ad", "build this in Canva", "make me a video ad", "new…
brand-kit-extractor
Use before generating any creative for a firm — extracts their brand identity (colors, fonts, logo, imagery style, tone of voice) from their website so new ads and content look on-brand. Triggers include "what are my brand colors", "extract my brand", "build a brand kit", "make it match my site", or any request to…
canva-asset-manager
Upload and manage assets (images, videos, audio) in your Canva account. Use this skill when user wants to upload files to Canva, manage their asset library, or work with uploaded media. Handles image, video, and audio uploads. Follows 3-mode workflow. For organizing uploaded assets use canva-folder-organizer.
canva-brand-kit
Manage and apply brand kits in Canva. Use this skill when user wants to work with brand colors, fonts, logos, or maintain brand consistency across designs. Helps define brand guidelines and ensures designs follow brand standards. Requires Canva Pro/Enterprise for full brand kit features.