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 skills add stunt-double/stuntdouble-mcp --skill run-user-interviewgit clone --depth 1 https://github.com/stunt-double/stuntdouble-mcpWrote 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/stunt-double/stuntdouble-mcp/run-user-interview)<a href="https://agentmods.dev/skills/stunt-double/stuntdouble-mcp/run-user-interview"><img src="https://agentmods.dev/badge/skills/stunt-double/stuntdouble-mcp/run-user-interview.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 5.1 | $0.00031 | $0.01278 |
| Opus 5 | $0.00015 | $0.00639 |
| Sonnet 5 | $0.00006 | $0.00256 |
| Haiku 4.5 | $0.00003 | $0.00128 |
Grade A, and why
run-user-interview 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 8d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run user interview
When to use
- When you want qualitative research on a specific user journey or concept before shipping
- When you need a discussion guide run against a live URL by several realistic participants
- When a checklist or workflow surfaces something that needs deeper "why" exploration
- When you want a one-pass report — summary, themes, recommendations, per-question rollup — from a small panel
Instructions
-
Find the workspace and project:
list_workspaces()→ pick the workspacelist_projects(workspace_id)→ pick the project the interview is about
-
Create the interview:
create_interview(workspace_id, project_id, name, target_url, research_brief?)name— short, descriptive (e.g. "Onboarding clarity — week 1")target_url— the live page participants should land onresearch_brief— 1–3 paragraphs of context (what you're trying to learn, decisions it will inform)
-
Build the discussion guide:
- For each topic,
add_interview_section(interview_id, title, intro_script?) - For each section, add 2–5 items with
add_interview_item(section_id, type, prompt_text, expected_evidence?)type: "question"— open-ended prompt the participant answers in their own wordstype: "task"— instruction the participant performs in the browser ("Sign up for a free account")expected_evidence— optional note about what a successful answer looks like
- Aim for 1–3 sections, 3–8 items total — interviews longer than ~15 items get expensive and noisy
- For each topic,
-
Recruit participants:
- For each participant,
add_interview_participant(interview_id, …):- Existing actor: pass
actor_id(uselist_actorsto find one — useful when you've already shaped the persona viacreate-actor-panel) - Ad-hoc persona: pass
persona_specwithname,bio, and 3–5traits
- Existing actor: pass
- 3–5 participants is the sweet spot. Vary segment, device, and locale for coverage.
- For each participant,
-
Launch the round:
launch_interview(interview_id)→ returns a trigger run ID; interview flips torunning- This is async. Participants run in parallel and update independently.
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.
- 8d ago First seen · 103 lines · 31 tokens per session scan A 99eb65bac487
run-user-interview is a skill published in the GitHub repository stunt-double/stuntdouble-mcp (1 stars, last pushed 23d ago), licensed MIT. It adds 31 tokens to every session and 1,278 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 2026-08-31.
Other skills, from other repositories
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
apollo-lead-finder
Two-phase Apollo.io prospecting: free People Search to discover ICP-matching leads, then selective enrichment to reveal emails/phones (credits per contact). Creates Apollo lists. Deduplicates against existing contacts by LinkedIn URL.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.
browse-and-evaluate
Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.
render-3d-product-showcase
Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the brand-color canvas, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed at…
render-airdrop-carousel
Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like to share a · Decline / Accept") springs up and its preview window CYCLES through the products, landing on a range/lineup payoff with an…