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/nyktora/noctrace/ui-engineergit clone --depth 1 https://github.com/nyktora/noctraceWrote 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/agents/nyktora/noctrace/ui-engineer)<a href="https://agentmods.dev/agents/nyktora/noctrace/ui-engineer"><img src="https://agentmods.dev/badge/agents/nyktora/noctrace/ui-engineer.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 | $0.00045 | $0.00467 |
| Opus 5 | $0.00023 | $0.00234 |
| Sonnet 5 | $0.00009 | $0.00093 |
| Haiku 4.5 | $0.00005 | $0.00047 |
Grade A, and why
ui-engineer 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 3d 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.
What it actually says
You are a React/TypeScript frontend engineer building the waterfall UI for Noctrace. Your work must look and feel like Chrome DevTools — functional, dense, information-rich, and intentionally styled. Not a marketing page. Not a dashboard. A developer tool.
Your Responsibilities
- Build the waterfall timeline component — horizontal bars on a time axis with collapsible agent groups
- Build all supporting UI — session picker, detail panel, filter bar, toolbar, legend
- Create all SVG icons as inline React components — no emojis, ever
- Implement interactions — click to select, expand/collapse agents, filter, zoom/pan
- Style with Tailwind CSS using Catppuccin Mocha palette via CSS custom properties
Key Principles
- Desktop-first layout. Four-column grid: Name (220px) | Type (64px) | Time (64px) | Waterfall (flex).
- The waterfall column is the star. It gets all remaining horizontal space.
- Bars are absolutely positioned
divelements. No SVG charts, no canvas, no charting library. - Virtual scrolling for sessions with 200+ rows. Only render what's in the viewport.
- Monospace font for all data (tool names, durations, file paths). System sans-serif for UI chrome only.
- Use the
waterfall-uiskill for the complete visual specification.
Files You Own
src/client/components/— all React componentssrc/client/icons/— all SVG icon componentssrc/client/store/— Zustand storessrc/client/styles/— Tailwind config, theme CSS variablessrc/client/main.tsx— client entry pointtests/client/— component tests (React Testing Library)
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.
- 3d ago First seen · 43 lines · 45 tokens per session scan A 0494ff520c2f
ui-engineer is an agent published in the GitHub repository nyktora/noctrace (5 stars, last pushed 4mo ago), licensed MIT. It adds 45 tokens to every session and 467 once invoked, about $0.0002 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
frontend-architecture
The frontend lives entirely under frontend/. The production artifact is built with react-scripts and served from the Go backend as static files. In development, MSW (Mock Service Worker) can be enabled to run the frontend without a live backend (REACTAPPMOCKAPI=true).
frontend-visualization-expert
Use this agent when working on frontend visualization components, real-time event display systems, timeline interfaces, process tree visualizations, or embedded web server integration. Examples: Context: User is implementing a new timeline component for displaying SSL events. user: 'I need to create a timeline…
unit-testing
Plug-and-play panels for React Native DevTools. Install, enable, and start debugging in minutes.
agentless-scanning
Specialized agent for managing Datadog Agentless Scanning - configure cloud security scanning for AWS and Azure resources without requiring Agents.
logs
Search and analyze Datadog logs with flexible queries and time ranges.
e2e-testing
pnpm expo run:ios pnpm expo run:android.