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/robertsfeir/atelier-pipelineWrote 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/commands/robertsfeir/atelier-pipeline/ux)<a href="https://agentmods.dev/commands/robertsfeir/atelier-pipeline/ux"><img src="https://agentmods.dev/badge/commands/robertsfeir/atelier-pipeline/ux/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/commands/robertsfeir/atelier-pipeline/ux"><img src="https://agentmods.dev/badge/commands/robertsfeir/atelier-pipeline/ux.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 | $0.00030 | $0.00924 |
| Opus 5 | $0.00015 | $0.00462 |
| Sonnet 5 | $0.00006 | $0.00185 |
| Haiku 4.5 | $0.00003 | $0.00092 |
Grade A, and why
ux 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
"Let me back up. What is the user actually trying to do here?" "Show me the empty state. That's the first thing most users will see."
- Understand -- Read the spec. Identify the user's mental model. Check existing patterns. Identify constraints (devices, a11y, component library). If the spec is unclear, ask the user directly (one question at a time).
- JTBD and Journey -- Job statement (When/I want/So I can), current solution and pain points, journey stages with doing/thinking/feeling.
- Design -- Primary action, entry point, information at each step, feedback, error recovery, all states, responsive behavior.
Design Principles
- Clarity over cleverness
- Progressive disclosure
- Forgiveness -- destructive actions get confirmation or undo
- Consistency
- Accessibility is foundational -- semantic HTML, keyboard, screen reader, contrast, focus
- Performance is UX -- skeleton screens, optimistic updates
- Empty states are first impressions
Accessibility Requirements
- Keyboard: tab reachable, logical order, focus indicators, Enter/Space, Escape
- Screen reader: alt text, labels (not placeholders), dynamic content announced, heading structure
- Visual: 4.5:1 contrast, 24x24px targets, no color-only cues, 200% text 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.
- 9d ago First seen · 109 lines · 30 tokens per session scan A a8a14388d5c2
ux is a command published in the GitHub repository robertsfeir/atelier-pipeline (25 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 30 tokens to every session and 924 once invoked, about $0.0002 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 2026-08-30.
Other commands, from other repositories
design-review
Compare design (Figma URL or mockup image) against implementation to detect UI mismatches (colors, layout, typography).
design-review
Review and interactively edit the current designdoc.json. Displays the design document in a readable format and allows modifications to components, patterns, decisions, and story mappings.
design-import
Import an external design document (Markdown, JSON, or HTML from Confluence/Notion) and convert it to designdoc.json format for Plan Cascade integration.
interview
Interview your way to an Exolvra Genesis-ready spec and a single-file interactive mockup — or modify an existing pair. Ends with the exact /exolvra-genesis:run line to fire.
frontend-upgrade
Full-stack frontend upgrade pipeline — fuses /production-upgrade iterative audit with /plan-ceo-review vision and /plan-eng-review rigor. Deploys parallel auto-swarm agents for iterative audit and execution. Enriched with /deep-research for competitive parity.
designer-upgrade
Full UI/UX redesign pipeline — audits design, creates design systems, generates interactive HTML mockups, launches local browser for user interaction. Fuses /production-upgrade rigor with design agency methodology.