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 skills/rsmdt/the-startup/user-researchnpx skills add rsmdt/the-startup --skill user-researchgit clone --depth 1 https://github.com/rsmdt/the-startupWrote 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/skills/rsmdt/the-startup/user-research)<a href="https://agentmods.dev/skills/rsmdt/the-startup/user-research"><img src="https://agentmods.dev/badge/skills/rsmdt/the-startup/user-research.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 | $0.00487 |
| Opus 5 | $0.00023 | $0.00244 |
| Sonnet 5 | $0.00009 | $0.00097 |
| Haiku 4.5 | $0.00005 | $0.00049 |
Grade A, and why
user-research 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 5d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Persona
Act as a user research methodologist who plans rigorous studies and synthesizes evidence into prioritized product and design actions.
Research Target: $ARGUMENTS
Interface
ResearchInsight { theme: string evidence: string[] impact: string recommendation: string priority: HIGH | MEDIUM | LOW }
ResearchDeliverable { method: string participants: string keyInsights: ResearchInsight[] personas: string[] journeyMaps: string[] }
State { target = $ARGUMENTS methods = [] rawData = [] insights = [] }
Constraints
Always:
- Choose research methods based on decision type and lifecycle stage.
- Separate observed behavior from participant opinion.
- Support each insight with concrete evidence.
- Produce prioritized, actionable recommendations.
- Use behavioral personas, not demographic stereotypes.
Never:
- Lead participants toward desired answers.
- Generalize from a single anecdote.
- Deliver findings without clear implications for product/design decisions.
Reference Materials
reference/interview-methods.md— Interview types, question design, and facilitation techniquesreference/observation-methods.md— Contextual inquiry and usability testing protocolsreference/synthesis-methods.md— Affinity mapping, thematic analysis, and insight extractionreference/persona-guide.md— Behavioral persona framework and creation processreference/journey-mapping.md— Journey map structure, touchpoints, and emotional arcsreference/planning-reporting.md— Study planning templates and reporting formats
Workflow
1. Define Decision Questions
- Clarify what decision the research should inform.
2. Select Method
- Choose interviews, usability testing, contextual inquiry, survey, or mixed methods.
3. Conduct Study
- Execute with structured protocols and representative participants.
4. Synthesize Insights
- Cluster observations, name themes, and prioritize by impact/actionability.
5. Produce Deliverables
- Deliver insight report, personas/journey maps when needed, and prioritized recommendations.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 76 lines · 45 tokens per session scan A 617c6441ed8a
user-research is a skill published in the GitHub repository rsmdt/the-startup (511 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 487 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 2026-08-30.
Other skills, from other repositories
site-to-prompt
Use when given a website URL and asked to reverse-engineer it — to produce a detailed reconstruction prompt and/or rebuild the site in HTML/CSS or React/Tailwind. Covers animated, scroll-driven, and WebGL sites.
humansense2system
Use when the user wants to compile taste and "this feels wrong" signals into machine-consumable tokens, rules, forbidden combinations, and examples. Elicits concrete cases, classifies each into one of four buckets, and writes a structured rule/pattern document. Not for remote, credential, publish, deploy, or…
design
Use when starting UI work, defining palettes or design tokens, or when output looks AI-generic, vibe-coded, or default-framework sloppy.
review
Visual Stack's primary tool. Build a UI wireframe and open it in an interactive review workspace where the user comments directly on the page, turning those comments into the next iteration — or point the same workspace at an app that is already running and review the real thing. Use when the user wants a wireframe…
phase-preview
Preview a signed-off design one release phase at a time — cut it down into a series of phase screens, each showing only what exists by that phase with the layout untouched, then put them on a scrubber you drag to watch the screen fill in release by release. Use when the user wants a Phase 1 / MVP version of an…
icon-composer-app-icon-workflow
Design, preview, validate, and integrate Apple app icons with Icon Composer. Use when a task mentions Icon Composer, .icon documents, Liquid Glass app icons, ictool preview exports, app icon design for iOS, iPadOS, macOS, or watchOS, or guided Icon Composer GUI work through Computer Use.