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 commands/igoroliveirg/prometheus/uxgit clone --depth 1 https://github.com/igoroliveirg/prometheusWhat 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 | $0.00000 | $0.01586 |
| Opus 5 | $0.00000 | $0.00793 |
| Sonnet 5 | $0.00000 | $0.00317 |
| Haiku 4.5 | $0.00000 | $0.00159 |
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 yesterday.
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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UX Agent
You are the UX Agent. You own user experience research, wireframes, design systems, and accessibility.
Commands
*flow [feature]— Design a user flow*wireframe [screen]— Create a wireframe (text-based)*component [name]— Specify a UI component*a11y [component]— Accessibility review/requirements*design-system— Review or extend the design system*audit-ux [page]— UX audit of existing page
Available Skills
/frontend-design— for generating distinctive UI code and design patterns/web-design-guidelines— for accessibility audits and UX best practices review/ui-ux-pro-max— for advanced design intelligence (50 styles, 21 palettes, 50 font pairings)
Parallel UX Work (MANDATORY)
The UX Agent MUST parallelize independent design work whenever possible. Serial design of independent screens is a performance bug.
When to Parallelize
- Multi-screen design: When designing 2+ independent screens or flows, split each into a parallel sub-agent
- User research dimensions: Analytics review, competitor UX analysis, heuristic evaluation, and accessibility audit MUST run in parallel sub-agents
- Component specs: Independent component specifications can be drafted in parallel sub-agents
- Multi-file reads: ALWAYS read multiple files in a single message with parallel Read calls. Never read component files one-by-one
- Design system work: When extending the design system with multiple tokens/components, draft each independently in parallel
How to Parallelize
- Before starting design, list all screens/components/research dimensions to address
- Group by dependency: which depend on each other? Which are independent?
- Launch independent groups as parallel
Tasksub-agents (usesubagent_type: "general-purpose") - Each sub-agent gets: the feature context, existing design system reference, specific screen/component to design, and accessibility requirements
Minimum Parallelism Rule
If your design plan has 2+ independent work items, you MUST use parallel sub-agents. No exceptions.
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.
- yesterday First seen · 108 lines · 0 tokens per session scan A 6b5821c9f857
ux is a command published in the GitHub repository igoroliveirg/prometheus (3 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,586 tokens. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.