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/impactbrussels/founderos/customer-interviewsnpx skills add impactbrussels/FounderOS --skill customer-interviewsgit clone --depth 1 https://github.com/impactbrussels/FounderOSWrote 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/impactbrussels/founderos/customer-interviews)<a href="https://agentmods.dev/skills/impactbrussels/founderos/customer-interviews"><img src="https://agentmods.dev/badge/skills/impactbrussels/founderos/customer-interviews.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 | $0.00100 | $0.01274 |
| Opus 5 | $0.00050 | $0.00637 |
| Sonnet 5 | $0.00020 | $0.00255 |
| Haiku 4.5 | $0.00010 | $0.00127 |
Grade A, and why
customer-interviews 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 4d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customer Interviews (the Mom Test)
First-time founders run "interviews" that are really pitches in disguise, then walk away with a notebook full of "yeah, I'd totally use that" - and build the wrong thing for a year. The problem isn't the people; it's the questions. Anyone, even your mom, will lie to you if you ask whether your idea is good. They won't lie about their own life. This skill makes you ask about their life, their past behaviour, and their real pain - never your idea - so the data you collect is worth building on.
The method
Built on the Founder OS scaffold (High tier). Full question bank, rules, and synthesis template in references/interview-guide.md.
Step 1 - Pick who to talk to
Talk to people who plausibly have [PROBLEM] now, not a random "target market." Define a
tight screen for [ICP]: a role, a behaviour, a recent trigger ("bought X in the last month",
"manages Y today"). 5-10 of the right people beats 50 randoms. Friends and family don't
count - they protect your feelings (see Constraints).
Step 2 - Write non-leading questions
The whole game is removing yourself and your idea from the question. Bad questions invite a
compliment ("Would you use an app that…?"). Good questions excavate the past ("Walk me through
the last time you dealt with [PROBLEM]"). Build a script of 5-8 questions about their life
and past behaviour, ordered from broad to specific. Keep [ONE_LINER] out of your mouth.
Step 3 - Run the conversation
Make it a conversation, not a survey. Open broad, then dig for specifics: "When was the last time?", "What did you do next?", "How much did that cost you - in time or money?". Shut up and listen - silence pulls out the truth. Don't pitch, don't correct, don't sell. Your job is to learn, not to be liked.
Step 4 - Spot good vs. bad signals
Score what you heard against the signal table. Specific past stories, emotion, money/time already spent, and concrete commitments are gold. Generic futures, compliments, and "yes I would" are noise - a draft is not a decision, and a polite "yes" is not a customer. Capture each as a real signal or an anti-signal.
What ships with it
1 file 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.
- 4d ago First seen · 89 lines · 100 tokens per session scan A b8c4dd80c94d
customer-interviews is a skill published in the GitHub repository impactbrussels/FounderOS (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 100 tokens to every session and 1,274 once invoked, about $0.0005 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
copilotkit-develop
Use when building AI-powered features with CopilotKit v2 -- adding chat interfaces, registering frontend tools, sharing application context with agents, handling agent interrupts, and working with the CopilotKit runtime.
copilotkit-upgrade
Use when migrating a CopilotKit v1 application to v2 -- updating package imports, replacing deprecated hooks and components, switching from GraphQL runtime to AG-UI protocol runtime, and resolving breaking API changes.
metrics-instrumentation
Specification for instrumenting an opik-backend workflow with operational OpenTelemetry metrics — per-stage throughput/latency/error counters and native histograms, dimensioned per-customer (workspace). Use when a pipeline (scoring, ingestion, experiments, jobs) needs per-stage visibility. Covers metric emission only…
review-agents-md
Audit Dograh AGENTS.md files for drift against the live repo and for bad scope boundaries between parent and child docs. Use when the user asks to review existing AGENTS files, identify stale guidance, decide whether a subtree needs its own AGENTS.md, or update the AGENTS.md hierarchy under the repo root, api/, or ui/.
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…
experiment-tracking-swanlab
Provides guidance for experiment tracking with SwanLab. Use when you need open-source run tracking, local or self-hosted dashboards, and lightweight media logging for ML workflows.