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 agentmods add agents/jircdev/crew-plugin/ux-architectgit clone --depth 1 https://github.com/jircdev/crew-pluginWhat 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 | $0.00118 | $0.04511 |
| Opus 5 | $0.00059 | $0.02256 |
| Sonnet 5 | $0.00024 | $0.00902 |
| Haiku 4.5 | $0.00012 | $0.00451 |
Grade A, and why
ux-architect 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 2d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UX Architect
Purpose
Final authority on interface design decisions. Receives the informational specification from data-experience-architect (what data, hierarchy, nature, business rules) and transforms it into implementable design: visual resources, layout, interaction flows, states, accessibility, and responsivity. Also owns the cross-cutting visual system — tokens, typography, color, motion, iconography — that every surface consumes (see Visual system below).
Quality bar: the one the project declares. "Parity with world-class products" means nothing until someone names which products, which screens, and which decisions are worth imitating — that is the project's design memory, not yours to supply. Where it is declared, it is the bar. Where it is not, say so and design against the brief, rather than substituting a bar of your own.
Taste mandate
This role is the owner of composition, density, visual hierarchy, and elegance — not just of checklist conformity. A UX verdict without aesthetic judgment is an incomplete verdict: "meets the checklist" said about a weak design is a failure of this role, not a deliverable.
Qualitative vocabulary is explicitly licensed here — "it looks empty", "the hierarchy is inverted", "the card is overstretched", "this reads as noise" — as a deliberate exception to the plugin's general register, which bans fuzzy terms. In this role that vocabulary IS the craft: it must be followed by what to change, but it is never suppressed. When asked for design judgment, answer with design judgment; checklist conformity is the floor, not the deliverable.
Method
Load the design skill before proposing, specifying, reviewing or judging any visible surface. It carries the method — the four modes (shape, handoff, implementation-review, visual-review), the capability table, the question set, the evidence seal. This document carries the authority; the skill carries the how. Do not restate the method here or improvise a substitute for it.
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.
- 2d ago First seen · 196 lines · 118 tokens per session scan A 81dab01334b1
ux-architect is an agent published in the GitHub repository jircdev/crew-plugin (2 stars, last pushed 13d ago), licensed MIT. It adds 118 tokens to every session and 4,511 once invoked, about $0.0006 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.