Borrowing it
Nothing to install: this file belongs to okuzpe/midas-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/okuzpe/midas-harness/main/.agents/skills/midas-design/SKILL.mdgit clone --depth 1 https://github.com/okuzpe/midas-harnessWrote 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/okuzpe/midas-harness/midas-design)<a href="https://agentmods.dev/skills/okuzpe/midas-harness/midas-design"><img src="https://agentmods.dev/badge/skills/okuzpe/midas-harness/midas-design/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/okuzpe/midas-harness/midas-design"><img src="https://agentmods.dev/badge/skills/okuzpe/midas-harness/midas-design.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 | $0.00074 | $0.01568 |
| Opus 5 | $0.00037 | $0.00784 |
| Sonnet 5 | $0.00015 | $0.00314 |
| Haiku 4.5 | $0.00007 | $0.00157 |
Grade A, and why
midas-design 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 4d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
midas-design — authentic redesign (think before JSX)
Guard + state:
<paths.engine>/templates/skill-state-ritual.md(+AGENTS.md§ Safety / Path resolution). Prompt tool:AskQuestion. On Claude Code, fall back toAskUserQuestionif AskQuestion is not wired. Readpaths.state. No UI / no{product}/→ report and stop. Record shape:<paths.engine>/templates/design-record.md. Authenticity CHECKs:<paths.engine>/rules/visual-design.md§ Product authenticity.
Stops interchangeable AI-SaaS landings. Does not freeze Phase 5 rules; does not advance stage.
Does / Does not
| Does | Does not |
|---|---|
| Audit current UI vs product jobs + direction | Invent taste when direction is empty — ask or mark assumed (confirm) |
| Propose exactly 3 substantially different art directions | Copy one reference wholesale |
| Spec + optional one implement slice after human pick | Redesign the whole site in one shot |
Freeze {runs}/design/design-NN.md; amend direction only on human OK |
Replace /define-conventions or /midas-verify |
When to run
User asks to improve / redesign / refactor design, landing, hero, brand feel, or "make it less generic".
Also when /midas-verify or tribunal Design Critic flags generic UI.
When NOT: Phase 5 first freeze → /define-conventions. Token-only tweak with frozen direction → implement under /start-sprint. Proof only → /midas-verify.
Modes (--mode, default progressive)
| Mode | Stops after | Writes |
|---|---|---|
audit |
UX audit | record (directions empty) |
directions |
3 directions + recommendation | record; wait for human pick |
spec |
page/hero spec + wireframe | record (requires chosen direction) |
implement |
one approved slice in code | record + code (requires spec) |
Default path when user says "redesign X": run through directions, stop for pick, then on confirm continue spec → optional implement --slice ….
Procedure
1. Load context (scout)
Read paths.state, {product}/idea.md, {product}/design-direction.md, {product}/design-system.md (+ tokens), architecture, and the target surface (routes/components). If direction lacks Metaphor or First viewport, treat as incomplete — fill proposals marked assumed (confirm) before inventing UI.
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.
- 4d ago Changed 9605a68f4a63
- 9d ago First seen · 109 lines · 74 tokens per session scan A 5a9e084b9783
midas-design is a skill published in the GitHub repository okuzpe/midas-harness (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 74 tokens to every session and 1,568 once invoked, about $0.0004 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.