consumer-product-testing

consumer-product-testing is a skill for Claude Code, Codex from impactbrussels/FounderOS. It costs 135 tokens per session (1,218 once invoked), scanned A, original, Apache-2.0.

A method for testing consumer and physical products with real users, from early ideas to products used at home. It helps determine whether a product actually works, rather than only whether people say they like the idea.

In plain words
What is it for?
Choosing and planning concept, prototype, sensory, home-use, or location-based product tests. It helps test food, cosmetics, household goods, hardware, and other packaged products before launch or when supporting product claims.
Why use it?
Interviews show what people report wanting, but not how they behave when using a product. These tests provide evidence about performance, sensory experience, and use over time.

Skill for Claude CodeCodex

Part of the founderos plugin — 23 skills, 3 agents shipped together

Install

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.

agentmods
npx agentmods add skills/impactbrussels/founderos/consumer-product-testing
Any agent
npx skills add impactbrussels/FounderOS --skill consumer-product-testing
Clone the repo
git clone --depth 1 https://github.com/impactbrussels/FounderOS

Made for: Claude Code, Codex.

Or install founderos, the plugin that ships this one along with the rest of its 23 skills, 3 agents.

Wrote 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.

agentmods badge for consumer-product-testing

README.md
[![agentmods](https://agentmods.dev/badge/skills/impactbrussels/founderos/consumer-product-testing.svg)](https://agentmods.dev/skills/impactbrussels/founderos/consumer-product-testing)
Your own site
<a href="https://agentmods.dev/skills/impactbrussels/founderos/consumer-product-testing"><img src="https://agentmods.dev/badge/skills/impactbrussels/founderos/consumer-product-testing.svg" alt="Measured on agentmods" height="20"></a>
Per session 135 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,218 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00135 $0.01218
Opus 5 $0.00068 $0.00609
Sonnet 5 $0.00027 $0.00244
Haiku 4.5 $0.00014 $0.00122

Measured 5d ago against content hash 360c1dac47b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

consumer-product-testing 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.

skills/consumer-product-testing/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Consumer Product Testing

Interviews tell you whether people have the problem. They don't tell you whether your product actually delivers - whether it works in a real kitchen, bathroom, or living room, day after day. For consumer and physical products, you have to put the thing in real hands and watch what happens. This skill picks the right test for where you are and keeps you honest about what the result proves. Proof before hype: observed behaviour beats reported intention.

The method

Built on the Founder OS scaffold. Test menu, protocols, and rules in references/testing-playbook.md.

Step 1 - Name the question for this stage

Different stages need different tests. Don't run a home-use test on an idea, or a concept test on a finished product.

Stage Question Test
Concept "Do they want this idea of a product?" Concept test (description/mockup + intent + price reaction)
Prototype "Does the thing work and perform?" Prototype / functional test; sensory test if tasted/smelled/felt
Pre-launch "Does it hold up in real use over time?" Home-Use Test (HUT) or Central Location Test (CLT)
Claims/shelf "Can I prove the claim / does it sell on shelf?" Claims substantiation, A/B pack & shelf tests

Step 2 - Recruit the right people, the right number

Test with the [ICP], not friends and family (they're kind, not honest). Screen for the real target. Small qualitative rounds (5-8) surface usability problems fast; quantitative reads (liking, preference, claims) need larger target-consumer samples (see references). State which you're running.

Step 3 - Observe behaviour, not just opinions

Watch them actually use it. Where do they hesitate, misuse it, give up? Capture: did it work, did they finish, would they use it again, did they come back unprompted. For anything tasted, smelled, or applied → run a blind, benchmarked sensory-testing session; don't rely on "I like it." Reported intent is weak evidence; repeat use and willingness to pay are strong.

Read the full file on GitHub · 88 lines

Files

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.

Changes

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.

  1. 5d ago First seen · 88 lines · 0 tokens per session scan A 360c1dac47b4

Subscribe to this mod's changes

consumer-product-testing is a skill published in the GitHub repository impactbrussels/FounderOS (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 135 tokens to every session and 1,218 once invoked, about $0.0007 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.

Related

Other skills, from other repositories