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 minhnv0807/ai-business-skills --skill 42-image-brief-globalgit clone --depth 1 https://github.com/minhnv0807/ai-business-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/minhnv0807/ai-business-skills/42-image-brief-global)<a href="https://agentmods.dev/skills/minhnv0807/ai-business-skills/42-image-brief-global"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/42-image-brief-global/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/minhnv0807/ai-business-skills/42-image-brief-global"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/42-image-brief-global.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00169 | $0.02357 |
| Opus 5 | $0.00084 | $0.01179 |
| Sonnet 5 | $0.00034 | $0.00471 |
| Haiku 4.5 | $0.00017 | $0.00236 |
Grade A, and why
42-image-brief-global 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 9d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image Brief (Global)
A good image brief means the designer finishes without a single clarifying call. Communicate the feeling you want, not just "make it look good". Colors, fonts, and logo usage come from the brand guideline (46-brand-guideline-global), never invented here.
Information gathering
Read .agents/product-marketing-context-global.md, the brand guideline, and the asset list (41-campaign-asset-list-global) if available. If information is missing, ask up to 4 questions:
- Image type and subject? Social post, ad banner, thumbnail, product shot, lifestyle, or infographic — attached to which campaign or content piece?
- Channel and dimensions? Meta, TikTok, LinkedIn, Pinterest, website, or email — ratio 1:1, 4:5, 9:16, 16:9, 2:3, or custom?
- Visual objective and copy? Stop the scroll, build trust, or drive the click — is the headline, subtext, and CTA written and approved?
- Constraints? Reference images (link or file), deadline, maximum number of revision rounds?
Principles
- Complete enough that nobody has to ask. Any blank field means the brief is not finished. If a decision is genuinely open, write "designer's call, per brand guideline".
- Copy is approved before it is set. Do not rewrite copy after the layout exists.
- References are mandatory. One reference image replaces a thousand words. "Make it look clean and professional" is not a brief.
- One image, one visual objective. Do not stack three messages into one frame.
- More than two revision rounds usually means the brief was unclear, not that the designer is weak.
- If multiple sizes are needed, state the adaptation rules for each one (see
50-asset-resize-global).
Workflow
1. Define the visual objective
Before briefing the concept, decide what this image must accomplish in the first three seconds of attention.
| Objective | Visual direction |
|---|---|
| Stop the scroll | Strong hook, high contrast, pattern interrupt |
| Build trust | Clean, professional, visible social proof |
| Drive the click | Prominent CTA, explicit offer, urgency if it 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.
- 9d ago First seen · 191 lines · 169 tokens per session scan A 2275ea370c1c
42-image-brief-global is a skill published in the GitHub repository minhnv0807/ai-business-skills (572 stars, last pushed 26d ago), licensed MIT. It adds 169 tokens to every session and 2,357 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 2026-09-03.
Other skills, from other repositories
claude-design
Design one-off HTML artifacts (landing, deck, prototype).
tldraw-offline
Drive and script tldraw offline canvases with an agent.
sketch
Throwaway HTML mockups: 2-3 design variants to compare.
baoyu-infographic
An infographic generator that turns supplied content into a visual summary using different information layouts and visual styles. It supports standard and custom image proportions and multiple languages.
excalidraw
Hand-drawn Excalidraw JSON diagrams (arch, flow, seq).
adversarial-ux-test
Roleplay a hostile user to find and triage UX pain points.