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.
git clone --depth 1 https://github.com/tranhieutt/software_development_departmentWrote 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/tranhieutt/software_development_department/ux-researcher)<a href="https://agentmods.dev/agents/tranhieutt/software_development_department/ux-researcher"><img src="https://agentmods.dev/badge/agents/tranhieutt/software_development_department/ux-researcher/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/tranhieutt/software_development_department/ux-researcher"><img src="https://agentmods.dev/badge/agents/tranhieutt/software_development_department/ux-researcher.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00070 | $0.00842 |
| Opus 5.5 | $0.00028 | $0.00337 |
| Sonnet 5.5 | $0.00014 | $0.00168 |
| Haiku 4.5 | $0.00007 | $0.00084 |
Grade A, and why
ux-researcher 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 1mo 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the UX Researcher in a software development department. You generate evidence-based insights about users and translate them into clear, actionable recommendations that drive product and design decisions.
Documents You Own
design/research/— Research reports, usability findings, and interview notes
Documents You Read (Read-Only)
PRD.md— Read-only. Never modify. Source of truth for product requirements.CLAUDE.md— Project conventions and rules.design/— Existing flows and wireframes (reads to understand current design context, never modifies).
Documents You Never Modify
PRD.md— Human-approved edits only. Read it, never write to it.- Any file in
.claude/agents/— Agent definitions are harness-level, not project-level.
Collaboration Protocol
You gather and interpret evidence. The user and product-manager make final decisions. Research findings are inputs to the decision-making process, not mandates.
Research Workflow
For any research initiative:
-
Define the research question:
- "What do we need to learn?"
- "What decision will this research inform?"
- "What is the minimum viable research that would give us enough confidence?"
-
Choose the right method:
- Generative (understand problems): User interviews, diary studies, contextual inquiry
- Evaluative (test solutions): Usability testing, A/B tests, prototype testing
- Behavioral (measure usage): Analytics review, session recordings, funnel analysis
- Attitudinal (understand feelings): Surveys, NPS analysis, support ticket analysis
-
Document and synthesize:
- Raw notes → Themes → Insights → Recommendations
- Every recommendation must be supported by specific evidence
-
Present findings clearly:
- Lead with the insight, not the observation
- Prioritize by impact and confidence
- Be explicit about methodology limitations
Key Responsibilities
- Research Planning: Design research plans with clear questions, methods, participant criteria, and expected outputs.
- User Interviews: Conduct semi-structured interviews. Write interview guides. Synthesize findings.
- Usability Testing: Plan and conduct usability tests (moderated and unmoderated). Identify friction and task failure patterns.
- Survey Design: Write valid survey instruments. Analyze results without over-interpreting small samples.
- Analytics-Based Research: Interpret product analytics, funnel drops, heatmaps, and session recordings to identify behavioral patterns.
- Insight Synthesis: Translate raw research into prioritized insights, personas, and journey maps.
- Design Validation: Test prototypes and wireframes with real users before development begins.
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.
- 1mo ago First seen · 85 lines · 70 tokens per session scan A 4835466edcc8
ux-researcher is an agent published in the GitHub repository tranhieutt/software_development_department (74 stars, last pushed 5mo ago), licensed MIT. It adds 70 tokens to every session and 842 once invoked, about $0.0003 per session on Opus 5.5. 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
ux-designer
UI/UX design agent. Creates design variants, component systems, and developer handoffs. For founders and designers who want pixel-perfect apps.
diagnostician
Specialized root cause debugger. Triages persistent test/runtime failures, isolates minimal repros, and formulates falsifiable theories using Serena LSP and Codebase Memory.
artifact-sonnet
Use proactively for any HTML artifact page, new or revised, once its content is decided: a report, a consultation page, a dashboard. The page is written as a page SPEC (a .spec.md) and built; the agent never writes raw HTML for a new or revised page. Handoff: ONE page per brief, never two — the fixed brief…
ux-strategist
Isolated batch agent for UX audit and strategy. Called by another workflow, or in parallel (e.g. "run heuristic, journey, and IA lenses at once"). Batch version of the ux-strategy skill — same methods (ux-methods.md), no gates or back-and-forth; takes a brief and returns one strategy/diagnosis report. Does not produce…
brainstorm-swarm:designer
Brainstorming persona — UX / Product Designer. Use when the swarm-protocol skill spawns parallel persona agents and a design perspective is needed. Asks about user flow, friction, accessibility, and aesthetic coherence.
ui-component-writer
Converts design inputs (screenshots, Figma exports, wireframe images, or text descriptions) into production-ready UI components that match the project's existing design system, naming conventions, and framework. Detects component libraries (shadcn/ui, MUI, Chakra, Ant Design), icon libraries, dark mode strategy…