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 Dragoon0x/everything-design-taste --skill design-economicsgit clone --depth 1 https://github.com/Dragoon0x/everything-design-tasteWrote 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/dragoon0x/everything-design-taste/design-economics)<a href="https://agentmods.dev/skills/dragoon0x/everything-design-taste/design-economics"><img src="https://agentmods.dev/badge/skills/dragoon0x/everything-design-taste/design-economics/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/dragoon0x/everything-design-taste/design-economics"><img src="https://agentmods.dev/badge/skills/dragoon0x/everything-design-taste/design-economics.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 | $0.00025 | $0.00649 |
| Opus 5.5 | $0.00010 | $0.00260 |
| Sonnet 5.5 | $0.00005 | $0.00130 |
| Haiku 4.5 | $0.00003 | $0.00065 |
Grade A, and why
design-economics 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Economics
Why This Matters
"Design is valuable" isn't an argument. "Design reduced support tickets by 30%, saving $240K/year" is.
Design Metrics Framework
Business Metrics (outcomes design influences)
- Revenue: Conversion rate, average order value, lifetime value
- Retention: Churn rate, daily/monthly active users, session length
- Efficiency: Task completion time, support ticket volume, onboarding completion
- Growth: Referral rate, NPS, app store rating
Experience Metrics (design quality indicators)
- Usability: Task success rate, error rate, time on task
- Satisfaction: SUS score, CSAT, ease-of-use rating
- Engagement: Feature adoption, return visits, depth of use
- Accessibility: WCAG compliance %, assistive tech compatibility
System Metrics (design operations health)
- Velocity: Time from design to dev, design system adoption rate
- Consistency: Component reuse %, custom override frequency
- Coverage: % of features with design specs, % tested with users
Building a Business Case
The Formula
Cost of the problem (current state)
- Cost of the solution (design investment)
= Net value of design
Example
Current state: 40% onboarding drop-off
Users lost/month: 2,000
Average LTV: $120
Monthly revenue loss: $240,000
Design investment: 2 designers x 6 weeks = ~$50,000
Target: reduce drop-off to 25% (conservative)
Users saved/month: 750
Monthly revenue recovered: $90,000
Payback period: < 1 month
Annual ROI: 2,060%
What to Measure Before and After
- Pick 2-3 metrics maximum
- Measure baseline for 4+ weeks before changes
- Measure impact for 4+ weeks after launch
- Account for seasonality and other variables
- Be honest about attribution (design is rarely the only factor)
Common Arguments and Responses
"Design is subjective" Response: Usability isn't. Task completion rate isn't. Conversion rate isn't. We can measure whether design achieves its goals objectively.
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 · 76 lines · 25 tokens per session scan A 3258125fdc68
design-economics is a skill published in the GitHub repository Dragoon0x/everything-design-taste (13 stars, last pushed 6mo ago), licensed MIT. It adds 25 tokens to every session and 649 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 2026-09-03.
Other skills, from other repositories
antislop
Anti Slop: Rules for AI Coding Agents. The core filter. Load always to stop generic AI slop.
antislop-human
Human and accessibility skill for antislop. Contrast, keyboard, focus, states, and interaction affordances for real people. Includes the contrast checker.
antislop-ui
UI and visual skill for antislop. Use when building or editing any interface: color, layout, components, motion, and page performance. Load with the core.
role-ui-ux-designer
Use when orchestrating UI/UX design systems, anti-AI-slop frontend styling, tactile micro-interactions, responsive design tokens, accessibility standards, and high-fidelity interface engineering.
taste
Anti-slop frontend engineering directive and design taste system. Enforces brief inference, dynamic design dials, absolute prohibition of AI visual tells, and 100% full-output completion.
design-taste-frontend
A page built by a model usually looks like the average of every page the model has seen: a centred headline over three lines, a little label above it, a row of icon cards, a soft gradient, a few thin rules and a monospace caption. Nothing in it is wrong and nothing in it was decided.