Borrowing it
Nothing to install: this file belongs to andrejkanuch/design-lenses. 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/andrejkanuch/design-lenses/main/.claude/skills/design-loop/SKILL.mdgit clone --depth 1 https://github.com/andrejkanuch/design-lensesWrote 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/andrejkanuch/design-lenses/design-loop)<a href="https://agentmods.dev/skills/andrejkanuch/design-lenses/design-loop"><img src="https://agentmods.dev/badge/skills/andrejkanuch/design-lenses/design-loop/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/andrejkanuch/design-lenses/design-loop"><img src="https://agentmods.dev/badge/skills/andrejkanuch/design-lenses/design-loop.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 | $0.00062 | $0.07368 |
| Opus 5 | $0.00031 | $0.03684 |
| Sonnet 5 | $0.00012 | $0.01474 |
| Haiku 4.5 | $0.00006 | $0.00737 |
Grade A, and why
design-loop 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 — 556 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrate a comprehensive design review through 8 specialist agents across 4 iterations, transforming functional UI into production-grade design.
Prerequisites
Before running the design loop, verify these conditions:
- File must exist — the target must be an HTML, JSX, TSX, Vue, or Svelte file that already renders a functional UI. This loop refines design; it does not build features.
- Target file should be committed — the target file should have no uncommitted changes. Auto-apply edits have no rollback mechanism; git is your safety net. Run
git statusand warn the user if the target file has uncommitted changes. Other files in the working tree can have changes — only the target file matters. - Fully standalone — this skill is self-contained. All agent prompts include their own evaluation criteria, checklists, and output formats. No other plugins are required. The Impeccable plugin is a complementary tool that provides its own slash commands for individual design concerns — it is not a dependency and this skill does not call Impeccable commands.
Input Validation
Parse $ARGUMENTS and validate:
- File path or directory (required, first positional argument):
- If missing:
"Error: path required. Usage: /design-loop <file-or-dir> [--domain=motorcycle] [--iterations=2] [--resume] [--no-apply] [--dry-run]" - If a directory: glob for supported files (
*.html,*.jsx,*.tsx,*.vue,*.svelte) in the directory (non-recursive). If none found:"Error: no supported UI files found in [DIR]. Supported: .html, .jsx, .tsx, .vue, .svelte". If multiple found, list them and run the loop on each sequentially with shared DESIGN_CONTEXT (see Multi-File Mode). - If a file: validate it exists, is a supported type, and is not binary. Error messages:
- Not found:
"Error: file not found at [PATH]. Check the path and try again." - Unsupported:
"Error: unsupported file type '[EXT]'. Supported: .html, .jsx, .tsx, .vue, .svelte" - Binary:
"Error: [PATH] appears to be a binary file. This skill works on source files only."
- Not found:
- Multiple files: space-separated paths are accepted. All must be valid supported files.
- If missing:
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 556 lines · 62 tokens per session scan A 93306dae5099
design-loop is a skill published in the GitHub repository andrejkanuch/design-lenses (5 stars, last pushed 5mo ago), licensed MIT. It adds 62 tokens to every session and 7,368 once invoked, about $0.0003 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.