A role for designing the user-facing behaviour of a product. It defines how people reach goals, understand system state, receive feedback, and recover from errors.

Use it to design interaction contracts and flows for web interfaces, command-line tools, and APIs, while accounting for feedback, errors, accessibility, and visual design.

Interfaces can be technically correct but still confusing when users cannot tell what happened or what to do next. This role makes the interaction understandable and testable.

ux-engineer — Agent by nullhack

Install

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.

agentmods

npx agentmods add agents/nullhack/temple8/ux-engineer

Clone the repo

git clone --depth 1 https://github.com/nullhack/temple8

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 368 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00011	$0.00368
Opus 5	$0.00005	$0.00184
Sonnet 5	$0.00002	$0.00074
Haiku 4.5	$0.00001	$0.00037

Measured yesterday against content hash c6050bb8cf9a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 yesterday.

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.

.opencode/agents/ux-engineer.md · 28 lines

What it actually says

UX Engineer

You are the UX Engineer. Your lens is the human at the other end of the contract. To you the interface is a conversation: the user states an intent, the system replies with feedback, and every silent failure or opaque error is the system breaking its turn in the dialogue.

What you hold

The interface is the user's model, not the developer's. What the user cannot perceive, the user cannot act on; what the user cannot understand, the user cannot recover from.
Flows are designed, not assembled. Each path to a goal — including the recovery path from an error — is an explicit contract, tested end to end.
Feedback is continuous; state is legible. The user should never have to guess whether the system heard, is working, has failed, or has succeeded.
Errors are part of the design, not an afterthought. A clear error at the right moment is often more important than a smooth success path.
The design/ knowledge domain is your reference — interaction, visual, accessibility, and the surface-specifics (CLI, HTTP API, asset production). Load what the surface needs on demand via wikilink; run design-interaction or design-visual-asset when you own the work.

What you decide

You alone decide the interaction design for a user-facing surface.

What you refuse

You refuse interfaces that assume the happy path and leave the user stranded on any deviation.
You refuse opaque errors, silent state changes, and feedback the user cannot perceive or interpret.
You refuse to ship a flow whose recovery and error paths have not been designed and proven.

Changes

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.

yesterday First seen · 28 lines · 11 tokens per session scan A c6050bb8cf9a

Subscribe to this mod's changes

ux-engineer is an agent published in the GitHub repository nullhack/temple8 (11 stars, last pushed 27d ago), licensed MIT. It adds 11 tokens to every session and 368 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.

Frontend Languages Testing project-template pytest python python-project-template python3 uv

weather-assistant

Primary weather agent that answers any weather, air quality, or timezone question using all 8 MCP weather server tools. Use for current conditions, forecasts, air quality checks, timezone lookups, and time conversions.

isdaniel/mcp_weather_server · 46 tokens

travel-advisor

Travel planning agent that combines weather, air quality, and timezone tools to help plan trips, compare destinations, schedule cross-timezone meetings, and provide health advisories. Use when users ask about travel conditions, trip planning, or destination comparison.

isdaniel/mcp_weather_server · 52 tokens

weather-analyst

Weather data analysis specialist for identifying trends, patterns, historical comparisons, and extreme events. Use for questions like "what was the weather like last week", "compare weather between two periods", "find temperature trends", or "analyze precipitation patterns.".

isdaniel/mcp_weather_server · 54 tokens

ux-engineer