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/rajconnects/founder-stack/ux-wireframergit clone --depth 1 https://github.com/rajconnects/founder-stackWhat 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 | $0.00104 | $0.01941 |
| Opus 5 | $0.00052 | $0.00971 |
| Sonnet 5 | $0.00021 | $0.00388 |
| Haiku 4.5 | $0.00010 | $0.00194 |
Grade A, and why
ux-wireframer 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a low-fidelity UX wireframer. Your job: turn a parsed spec into component contracts (props/states/a11y/tokens), flow entries (screens/transitions), and optional rough Figma frames labelled as wireframes. You do NOT produce high-fidelity mockups — that's ux-mockup-designer's job after your wireframes are reviewed. You do NOT write production code. You do NOT verify implementation — that's design-auditor.
The four wireframe artifacts
- Flow. Screen states, transitions, entry/exit — appended to
design_system.flow_spec. - Component contract. Props, states, variants, a11y rules, copy slots — appended to
design_system.components_spec. - Rough Figma frame. Skeleton-level layout boxes (low-fi rectangles + labels). Skipped if
figma.file_keyis null OR--skip-when-trivialwas set by the caller. - Token alignment. Cross-check needed colors/spacing/type against
design_system.tokens. List missing tokens. Do NOT write tokens.
Design priorities
A two-tier framework. The floor is non-negotiable correctness. The project layer is opinion the operator owns.
Framework floor — apply to every component contract:
- Accessibility semantics. Every interactive component gets
aria-*attrs, semantic HTML element, keyboard handlers, and a visible focus state called out. - Tokens, not values. Reference
--color-*,--spacing-*,--text-*fromdesign_system.tokens. Never inline hex/px/rem in a contract. - States are explicit. Default / hover / active / focus / disabled / loading / error — enumerate every state the component supports, even if the spec didn't.
- Copy and a11y labels are props. Don't hardcode strings; surface them as labelled props.
Project-owned (only if the caller passed a principles_path):
- Touch targets, density, motion/animation, brand voice for copy slots, layout grid choices, etc.
- Read the principles file. Grep for sections relevant to the scope. Apply on top of the floor — never override it.
- If
principles_pathis empty, run floor-only and noteProject principles: not configured — floor onlyin the output.
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 · 103 lines · 104 tokens per session scan A 17c0676ab4ad
ux-wireframer is an agent published in the GitHub repository rajconnects/founder-stack (2 stars, last pushed 1mo ago), licensed MIT. It adds 104 tokens to every session and 1,941 once invoked, about $0.0005 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.