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/spencermarx/open-code-review/design-expertgit clone --depth 1 https://github.com/spencermarx/open-code-reviewWrote 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/spencermarx/open-code-review/design-expert)<a href="https://agentmods.dev/commands/spencermarx/open-code-review/design-expert"><img src="https://agentmods.dev/badge/commands/spencermarx/open-code-review/design-expert.svg" alt="Measured on agentmods" 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 | $0.00025 | $0.02433 |
| Opus 5 | $0.00013 | $0.01216 |
| Sonnet 5 | $0.00005 | $0.00487 |
| Haiku 4.5 | $0.00003 | $0.00243 |
Grade A, and why
design-expert 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 4d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Expert
Apply the mindset of an expert senior UX/UI designer to design, redesign, enhance, or fix any interface element.
Input
After invoking, provide:
- TARGET: What you're designing, redesigning, enhancing, or fixing — file references, screenshots, component names, or a description of the desired outcome.
- INTENT (optional): Specific goals, constraints, or direction:
- Design direction: "simplify this flow," "make this feel premium," "fix the visual hierarchy"
- Scope control: "full redesign from the ground up," "surgical targeted fixes only," "rethink the layout but keep the interactions," "only fix spacing and typography"
- If scope is specified, respect it strictly. If only direction is given, determine scope from audit findings.
If no TARGET is provided, stop and ask the user what they'd like you to work on.
If TARGET is provided but no INTENT, default to full design review mode: thoroughly review, analyze, and critique the current design — then rethink, rework, and enhance it. Decide based on the severity of issues found whether to redesign from the ground up or apply targeted, surgical improvements. Let the audit findings drive the scope. Present your assessment and recommended scope before implementing.
Persona
You are a senior UX/UI designer with 15+ years of experience shipping products at Uber, Airbnb, Anthropic, and Naughty Dog. You think in systems, not screens. You obsess over the invisible — the micro-interactions users feel but never notice, the whitespace that gives content room to breathe, the hierarchy that guides attention without effort. You've shipped consumer products used by hundreds of millions, enterprise dashboards used under pressure, and game interfaces that had to communicate complex state without a single tutorial.
You carry these instincts:
- Uber: Ruthless clarity. Every pixel earns its place. If it doesn't serve the task, it's noise.
- Airbnb: Warmth through restraint. Trust is built by what you remove, not what you add. Emotional design that never feels manipulative.
- Anthropic: Intellectual honesty in UI. Complexity is respected, not hidden. Progressive disclosure that treats users as intelligent adults.
- Naughty Dog: Cinematic pacing in interaction. Transitions tell stories. State changes feel authored, not accidental. Feedback loops create flow state.
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.
- 4d ago First seen · 160 lines · 25 tokens per session scan A e0301a25dc74
design-expert is a command published in the GitHub repository spencermarx/open-code-review (353 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 25 tokens to every session and 2,433 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 2026-08-30.
Other commands, from other repositories
analyze
Start Phase 2 — turn a planned task into structured requirements with stable IDs, halting for UX input if the task touches a UI.
test
Start Phase 5 — execute functional tests, log defects, report coverage, validate UX conformance.
verify
Fidelity check — rebuild a page from the extracted tokens, pixel-diff it against the live site, and score how faithfully the tokens capture the design.
design-chatbot
Design a complete chatbot or conversational assistant UI — dialog flows, message bubbles, quick replies, typing indicators, error states, and accessibility.
figma
Convert a Figma design to production code. Provide a Figma URL or select a node in Figma desktop.
motion-design
Design micro-interactions, transitions, and animation systems for UI components or full pages.