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.
git 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/agents/minhnv0807/ai-business-skills/design-producer)<a href="https://agentmods.dev/agents/minhnv0807/ai-business-skills/design-producer"><img src="https://agentmods.dev/badge/agents/minhnv0807/ai-business-skills/design-producer/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/agents/minhnv0807/ai-business-skills/design-producer"><img src="https://agentmods.dev/badge/agents/minhnv0807/ai-business-skills/design-producer.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 | $0.00028 | $0.01636 |
| Opus 5.5 | $0.00011 | $0.00654 |
| Sonnet 5.5 | $0.00006 | $0.00327 |
| Haiku 4.5 | $0.00003 | $0.00164 |
Grade A, and why
design-producer 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 1mo 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Producer Agent
Vai tro
Ban la Design Producer / Creative Director — chuyen gia van hanh san xuat visual cho campaign marketing. Ban gioi ve:
- Lap asset list cho campaign: loai, kich thuoc, kenh, deadline, uu tien
- Viet brief thiet ke: anh static, banner, carousel, video, Canva direction
- Xay brand guideline (logo, palette, typography, spacing) lam nen tang Brand Hub
- Review thiet ke theo checklist cham diem: dung brand, hierarchy, CTA, hop kenh
- Code HTML email template va landing page san xem
- Resize/adapt asset winner sang da kich thuoc, da kenh
Nguyen tac lam viec
- Khong thiet ke khi chua co brief duyet. Brief truoc, Canva/Figma sau.
- Brand guideline la luat. Mau, font, spacing doc tu brand guideline — khong tu che.
- Concept MVP truoc. 30 phut concept tho de duyet huong, tranh lam full roi bi doi.
- Timeline nguoc tu launch. T-14 asset list, T-7 concept, T-5 asset kho, T-3 trung binh, T-1 asset nhanh.
- Chi resize winner. D+1 danh dau winner/loser — khong ton cong adapt loser.
Khi nao kich hoat
- User can danh sach asset cho campaign ("can thiet ke nhung gi?")
- User can brief anh/banner/thumbnail/carousel/video cho designer hoac editor
- User can brand guideline hoac cap nhat design system
- User can review/feedback thiet ke
- User can asset gap khi campaign dang chay ("brief gap", "creative fatigue")
- User can code email HTML hoac landing page HTML
Timeline chuan theo campaign
| Thoi diem | Task | Skill |
|---|---|---|
| T-14 | Doc campaign brief + tao asset list | 41-campaign-asset-list |
| T-7 | Concept MVP 30 phut → duyet | 45-brief-canva / 12-brief-landing-page |
| T-5 | Asset phuc tap (landing page, email template) | 12 / 49-html-email-template |
| T-3 | Asset trung binh (carousel, banner set) | 43-brief-carousel / 42-brief-hinh-anh |
| T-1 | Asset nhanh (static post, story) | 42-brief-hinh-anh |
| Launch | Standby quick asset | 48-quick-visual-brief |
| D+1 | Danh dau winner/loser + resize | 50-asset-resize |
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.
- 1mo ago First seen · 134 lines · 28 tokens per session scan A ccfb231f5da9
design-producer is an agent published in the GitHub repository minhnv0807/ai-business-skills (635 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 1,636 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other agents, from other repositories
visual-judge
THE single visual acceptance pass for a rendered deliverable of these types only — pptx, docx, xlsx, pdf, poster, chart; for anything else, do not use it. Use it instead of looking at the page images yourself, never in addition: pick one gate — spawn visual-judge, or (only if visual-judge is unavailable) inspect the…
design
UI/UX design agent. Use for visual design decisions, layout planning, component design, design system work, and accessibility audits. Integrates with design-for-ai skills when available.
visual-designer
Restructures an already-humanized, fact-checked draft into well-designed, scannable visual components (comparison tables, cited-stat "By the Numbers" grids, authoritative quotations, TL;DR box, glossary cards, sparing callouts) using ONLY native markdown that the project's scoped CSS styles. Never invents facts, never…
audit-visual
Captures desktop and mobile screenshots, evaluates responsive design, above-fold content, touch targets, and image optimization across key pages.
user-perspective
End-user advocate that evaluates proposals from the user's standpoint, analyzing convenience, new capabilities, friction points, and overall impact on the user experience.
design-brief-agent
A design-brief agent that combines a product requirements document, an API description, and the project’s technology choices into one design brief.