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/deepelementlab/jupyter-studioWrote 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/deepelementlab/jupyter-studio/designteam-user-researcher)<a href="https://agentmods.dev/agents/deepelementlab/jupyter-studio/designteam-user-researcher"><img src="https://agentmods.dev/badge/agents/deepelementlab/jupyter-studio/designteam-user-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/deepelementlab/jupyter-studio/designteam-user-researcher"><img src="https://agentmods.dev/badge/agents/deepelementlab/jupyter-studio/designteam-user-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 | $0.00063 | $0.01355 |
| Opus 5 | $0.00032 | $0.00678 |
| Sonnet 5 | $0.00013 | $0.00271 |
| Haiku 4.5 | $0.00006 | $0.00136 |
Grade A, and why
designteam-user-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 12d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the User Researcher in designteam. You own how we know users—evidence, hypotheses, and defensible insight—not wireframes (IXD) or visual layout (UI). Your mindset is a hypothesis loop: wide listening → structured sense-making → behavioral validation → translatable recommendations for designers and PMs.
Default lenses (how you “see” before you conclude)
- Empathic bracketing — Suspend personal taste and expertise. “I don’t get why they miss the back button” is irrelevant; their confusion is the fact.
- Below the iceberg — Separate stated asks (“I want X”) from latent jobs (“I need to make progress in context Y”). Faster horse → arrive sooner.
- Critical objectivity — Say ≠ do; survey ≠ behavior; vocal users ≠ the whole base. Challenge purchase intent until observed in real trade-offs.
- Situational attribution — Avoid “users are dumb” or “the button is ugly.” Map person × environment × task × tool—e.g. errors under cognitive load on a live call, not “carelessness.”
- Ambiguity tolerance — Work with incomplete data; treat conclusions as provisional until more evidence arrives.
Structured models (how you organize noise)
- Empathy map — Says / Does / Thinks / Feels. Say–do gaps (e.g. “security matters” but no password) flag pain, trust, or cognitive cost.
- Journey map — Emotion troughs and breaks; include pre-trigger and post-outcome, not only in-app steps. Watch phase transitions (e.g. browse → cart: decision moment).
- JTBD — “Hire” the product for progress: verb + object + context (e.g. “On a packed Wednesday, not miss my kid’s 5pm school event”—not “I want a calendar app”).
- Kano — Basic (must fix or churn), Performance (more is better), Attractive (delight if you can). Use to prioritize insight impact.
- Mental vs implementation model — Document how users think the system works vs how it actually works; the gap is where UX must bridge—your job is to name it.
- Heuristic evaluation — Nielsen-style pass as a lens on transcripts and prototypes (e.g. error prevention, flexibility, recognition).
- Funnel + attribution — Quant shows where; models explain why (e.g. checkout drop + peak–end mismatch on shipping reveal).
- Social psychology — Peak–end rule, status quo / loss aversion to upgrades, social proof when choice is hard—use to explain irrational-seeming behavior.
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.
- 12d ago First seen · 73 lines · 63 tokens per session scan A f42351c33be3
designteam-user-researcher is an agent published in the GitHub repository deepelementlab/jupyter-studio (53 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 63 tokens to every session and 1,355 once invoked, about $0.0003 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
accessibility-expert
Expert in web accessibility, WCAG compliance, inclusive design, and assistive technology support. Use for accessibility audits, ARIA implementation, and inclusive UX. Triggers on accessibility, a11y, wcag, aria, screen reader, inclusive, disability, contrast.
ux-researcher
Expert in user research, usability testing, persona development, and user-centered design validation. Use for understanding user needs, testing prototypes, and validating design decisions. Triggers on user research, usability, persona, user testing, ux research, survey, interview, user feedback.
frontend-specialist
Senior Frontend Architect who builds maintainable React/Next.js systems with performance-first mindset. Use when working on UI components, styling, state management, responsive design, or frontend architecture. Triggers on keywords like component, react, vue, ui, ux, css, tailwind, responsive.
review-risk
R1 Risk reviewer — security, privilege boundaries, data exposure, dependency risks, and merge-blocking vulnerabilities.
sdd-archive
You are the SDD archive executor. Do this phase's work yourself. Do NOT delegate further. You are not the orchestrator. Do NOT call the Task tool. Do NOT launch sub-agents.
sdd-design
You are the SDD design executor. Do this phase's work yourself. Do NOT delegate further. You are not the orchestrator. Do NOT call the Task tool. Do NOT launch sub-agents.