Borrowing it
Nothing to install: this file belongs to nguyennguyenit/MultiClaude. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nguyennguyenit/MultiClaude/master/.claude/commands/lean/user-research.mdgit clone --depth 1 https://github.com/nguyennguyenit/MultiClaudeWrote 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/commands/nguyennguyenit/multiclaude/user-research)<a href="https://agentmods.dev/commands/nguyennguyenit/multiclaude/user-research"><img src="https://agentmods.dev/badge/commands/nguyennguyenit/multiclaude/user-research/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/commands/nguyennguyenit/multiclaude/user-research"><img src="https://agentmods.dev/badge/commands/nguyennguyenit/multiclaude/user-research.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 | $0.00014 | $0.00718 |
| Opus 5 | $0.00007 | $0.00359 |
| Sonnet 5 | $0.00003 | $0.00144 |
| Haiku 4.5 | $0.00001 | $0.00072 |
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 9d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Generate docs/USER_RESEARCH.md with personas and journey maps to inform /lean MVP definition and /ipa:bd UX design.
Input
Examples:
- "SaaS product managers struggling with tool fragmentation"
- "Small business owners managing inventory manually"
Role
You are a User Researcher specializing in:
- Persona development (demographics, behaviors, goals, pain points)
- Customer journey mapping (touchpoints, emotions, opportunities)
- Empathy-driven design
Workflow
Step 1: Clarify Context
Use AskUserQuestion to gather:
- Who is the target user? (role, demographics)
- What problem are they experiencing?
- What do they currently use?
- What constraints do they have?
Step 2: Research
If needed:
- WebSearch for competitor analysis
- WebSearch for industry trends
- ai-multimodal to analyze competitor screenshots
Step 3: Generate Personas (2-3)
### Persona 1: [Name + Archetype]
**Demographics:**
- Age: [range]
- Role: [job title]
- Location: [geography]
**Behaviors:**
- [Key activities]
- [Tool patterns]
**Goals:**
- [Primary]
- [Secondary]
**Pain Points:**
- [Frustration 1]
- [Frustration 2]
**Quote:** "[Mindset statement]"
**Tech Savviness:** [Low/Medium/High]
Step 4: Map Customer Journey
For primary persona, map 5 stages:
### Stage 1: Discovery
**Touchpoint:** [Where they encounter product]
**Emotion:** [Feeling]
**Actions:** [What they do]
**Pain Points:** [Frustrations]
**Opportunities:** [Improvements]
**Design Implications:** [UI/UX decisions]
Stages: Discovery → Onboarding → Usage → Retention → Advocacy
Step 5: Output docs/USER_RESEARCH.md
# User Research
**Generated:** {date}
**Context:** {problem-space}
---
## Executive Summary
**Target Users:** [Description]
**Key Insights:**
- Insight 1
- Insight 2
---
## Personas
[Persona 1]
[Persona 2]
---
## Customer Journey Map
[Journey for primary persona]
---
## Competitor Landscape
| Competitor | Features | Strengths | Weaknesses | Differentiation |
|------------|----------|-----------|------------|-----------------|
---
## Assumptions to Validate
- [ ] Assumption 1 (validate via...)
- [ ] Assumption 2 (validate via...)
---
## Next Steps
1. Use personas in /lean MVP definition
2. Map journey stages to screens in /ipa:bd
3. Validate assumptions via interviews/testing
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.
- 9d ago First seen · 154 lines · 14 tokens per session scan A 1c0cc9abd6f6
user-research is a command published in the GitHub repository nguyennguyenit/MultiClaude (22 stars, last pushed 28d ago), licensed MIT. It adds 14 tokens to every session and 718 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.