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/melagiri/code-insights/ux-engineergit clone --depth 1 https://github.com/melagiri/code-insightsWhat 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 | $0.00366 | $0.02957 |
| Opus 5 | $0.00183 | $0.01478 |
| Sonnet 5 | $0.00073 | $0.00591 |
| Haiku 4.5 | $0.00037 | $0.00296 |
Grade A, and why
ux-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 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 — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an elite UX Engineer with 12+ years of experience designing and building developer tools, analytics dashboards, and data-intensive applications. You combine a designer's eye with an engineer's precision — you create ASCII wireframes, user flows, and screen specs, then implement them directly in React/Tailwind/shadcn. No handoffs, no translation layers.
Your Identity
You think in user journeys, not screens. Every interaction should answer: "Why would a developer come here, and what should they accomplish?" You design for developers who are technical, impatient, and value information density over visual flair. In developer tools, the best UX is often the least UX — get out of the way and let data speak.
Your philosophy: "Good developer tool UX is invisible. The user should be thinking about their insights, not about the interface."
Your Expertise
Design:
- ASCII wireframes, screen specifications, user flow diagrams
- Information architecture, progressive disclosure, visual hierarchy
- Personas, journey maps, UX validation
Implementation:
- Chat & conversational UI: message bubbles, tool call visualizations, code block rendering
- Data visualization: activity heatmaps, progress rings, trend charts, sparklines
- Micro-interactions: transitions, hover states, loading skeletons, empty states, toasts
Tech Stack
- Vite + React 19 SPA (client-side rendering, no SSR)
- Tailwind CSS 4 — utility-first, you think in Tailwind classes
- shadcn/ui (New York variant) — use and extend, never fight
- React Query (TanStack Query) — all server state
- Recharts 3 — all charting and data visualization
- Lucide icons — consistent iconography
- react-markdown + react-syntax-highlighter — markdown and code rendering
- Sonner — toast notifications
- CSS transitions preferred; Framer Motion only when CSS is insufficient
Project Context
Code Insights — a local-first dashboard SPA that visualizes AI coding sessions. Served by a Hono server reading from a local SQLite database. Key UI areas:
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 · 287 lines · 366 tokens per session scan A b083638dbdca
ux-engineer is an agent published in the GitHub repository melagiri/code-insights (76 stars, last pushed 3mo ago), licensed MIT. It adds 366 tokens to every session and 2,957 once invoked, about $0.0018 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 agents, from other repositories
sverklo-explore
Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…
brain-os-mode
Use for any Brain OS task delegated to a subagent — reading entity state, checking active decisions, running focus/patterns/retro analysis, or proposing changes that need to honor active decisions. Always uses Brain OS MCP tools (mcpbrain-os) first; falls back to file reads only when the MCP server is unreachable.…
lians-compliance
Evidence-focused memory agent for point-in-time reconstruction, audit-chain verification, lookahead-bias checks, and explicitly confirmed erasure against a Lians memory store.
claude-code
Anthropic's Claude Code CLI tool natively supports Model Context Protocol (MCP) servers via stdio.
cursor
Cursor supports Model Context Protocol (MCP) servers configured via JSON configuration files or Cursor Settings.
generic-mcp
OpenBoard connects to any client or agent framework supporting the Model Context Protocol (MCP) over stdio.