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/tznthou/claude-prismWrote 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/tznthou/claude-prism/pi-ui-design)<a href="https://agentmods.dev/commands/tznthou/claude-prism/pi-ui-design"><img src="https://agentmods.dev/badge/commands/tznthou/claude-prism/pi-ui-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/commands/tznthou/claude-prism/pi-ui-design"><img src="https://agentmods.dev/badge/commands/tznthou/claude-prism/pi-ui-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 | $0.00014 | $0.01702 |
| Opus 5 | $0.00007 | $0.00851 |
| Sonnet 5 | $0.00003 | $0.00340 |
| Haiku 4.5 | $0.00001 | $0.00170 |
Grade A, and why
pi-ui-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 10d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI/UX Mockup via Gemini
Use Gemini (via agy, the Antigravity CLI) to generate a previewable HTML mockup from a design specification document. The mockup is a single self-contained HTML file (Tailwind CDN) that can be opened in a browser for visual confirmation before implementation.
Workflow: Design spec → /pi-ui-design → Browser preview → Confirm → Claude Code implements
Execution
Bash invocation rules (v0.12.3+): Call
call-codex.sh/call-gemini.shin foreground synchronous mode withtimeout: 600000(Bash tool's 10-minute ceiling). Do not use&, do not setrun_in_background: true, do not usenohup— Claude Code 2026-04+ has an auto-background child-lifecycle regression that silently kills the process (output file stays 0 bytes). Userun_in_background: true+ BashOutput polling only as an exception when the call is genuinely expected to exceed 10 minutes.
1. Parse input
Based on $ARGUMENTS:
- File path (
.md,.txt): read the file as a design specification → Gemini generates HTML mockup - Text description (no file): treat as requirements → Gemini generates a design spec first, then ask user if they want to proceed to mockup
- No args: use AskUserQuestion to ask what to design
2. Read the design spec
Read the design specification file using the Read tool. Identify the key sections that inform the mockup:
- Information Architecture (routes, page structure)
- Layout Specification (grid, spacing, responsive breakpoints)
- Component Breakdown (component tree, key elements)
- Visual Direction (colors, typography, spacing scale)
- Interaction Design (hover states, transitions)
3. Call Gemini — Generate HTML mockup
Step 3a — Persist the full prompt (framing + spec) to a temp file:
- Bash:
PROMPT_FILE=$(mktemp -t prism-ui-design-XXXXXX.md) && echo "$PROMPT_FILE"— capture the path. - Use the Write tool to write the following prompt to that path, with the spec content from Step 2 appended at the end:
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.
- 10d ago First seen · 135 lines · 14 tokens per session scan A 1d47bc04004e
pi-ui-design is a command published in the GitHub repository tznthou/claude-prism (10 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 1,702 once invoked, about $0.0001 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 commands, from other repositories
critique
Design lens critique covering visual hierarchy, clarity, and anti-slop patterns — produces a findings table, no code edits unless asked. Use when the user wants a design review, says "what's wrong with this UI", or needs a second opinion before a handoff or presentation.
ui-flow-review
Review menus, HUD, navigation, and player flow from a UX perspective.
init-brand-tokens
Generate OKLCH design tokens with WCAG validation, shadcn/ui integration, and Tailwind v4 theming via 8 customization questions.
role-design
UX, flows, and information hierarchy lens.
create-ui-component
Create a UI component with design system compliance and Storybook stories.
sddesign
Full spec-driven pipeline — walks brief → tokens → shape (spec) → craft (build) → converge → ship in one guided run. Writes .ui-craft/spec.md. Run when starting a net-new surface from scratch.