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/sensory-testingnpx skills add impactbrussels/FounderOS --skill sensory-testinggit 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/sensory-testing)<a href="https://agentmods.dev/skills/impactbrussels/founderos/sensory-testing"><img src="https://agentmods.dev/badge/skills/impactbrussels/founderos/sensory-testing.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 | $0.00138 | $0.01312 |
| Opus 5 | $0.00069 | $0.00656 |
| Sonnet 5 | $0.00028 | $0.00262 |
| Haiku 4.5 | $0.00014 | $0.00131 |
Grade A, and why
sensory-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.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sensory Testing
People can say they'd buy your product and still spit out the first bite. For anything tasted, smelled, felt, or applied to the body, opinion surveys and interviews aren't enough - you need sensory evidence, gathered under conditions that stop the result from lying to you. This is the discipline food, beverage, and personal-care companies use, scaled down so a first-time founder can run it. Proof before hype: a blind, controlled test beats a founder's own palate every time.
The method
Built on the Founder OS scaffold (High tier - this drives formulation and launch decisions). Full protocols, scales, and sample sizes in references/sensory-methods.md.
Step 1 - Decide what question you're actually asking
Match the test to the decision. The three families (see references for protocols):
| Your question | Test family | Example method |
|---|---|---|
| "Are these two versions different at all?" | Discrimination | Triangle test, duo-trio, paired-comparison |
| "How do they differ - describe the profile" | Descriptive | Trained-panel profiling / QDA, CATA |
| "Do target consumers like it / which do they prefer?" | Affective (acceptance) | 9-point hedonic scale, paired preference, JAR |
Discrimination and descriptive use small trained/screened panels; acceptance needs untrained target consumers (your [ICP]) - never mix the two jobs.
Step 2 - Control the bias, or don't bother
A sloppy taste test produces confident nonsense. Non-negotiables (details in references):
- Blind & coded - samples labelled with random 3-digit codes, never "A/B" or brand names.
- Randomised & balanced serving order (counterbalance to cancel first-sample bias).
- Consistent conditions - same temperature, portion, vessel, lighting; neutral palate cleanser (water/cracker) between samples; separated tasting so people don't influence each other.
- Blind to your hope - whoever runs it shouldn't telegraph the "right" answer.
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.
- 5d ago First seen · 95 lines · 0 tokens per session scan A 52daf2553898
sensory-testing is a skill published in the GitHub repository impactbrussels/FounderOS (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 138 tokens to every session and 1,312 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.
Other skills, from other repositories
bio-ortholog-inference
Pull pre-computed ortholog calls from public databases (OrthoDB, Ensembl Compara, OMA browser, eggNOG, PANTHER, KEGG Orthology, HomoloGene) via their REST APIs. Use when orthologs are already curated upstream, when the question is "what is the X ortholog of Y" rather than "how to infer orthology de novo", when…
bio-differential-expression-batch-correction
Handles batch effects in bulk RNA-seq via design-matrix inclusion (the correct path for DE), ComBat/ComBat-seq for visualization, SVA for unknown latent factors, RUVSeq for negative-control-gene-anchored unwanted variation, and limma::removeBatchEffect for plotting only. Encodes the Nygaard 2016 cardinal sin against…
admet_genetic
ADMET-guided genetic molecule optimization workflow from seed SMILES; use when the agent needs to build or run an RDKit/SA-Score/ADMET-AI GA pipeline for molecule optimization, enforce molecule lineage logs, render optimization-history HTML dashboards, and write candidate triage reports.
bioprobench
Score an LLM's biological-protocol reasoning on the BioProBench benchmark: protocol QA, step ordering, error detection, protocol generation, and LLM-judged error reasoning; or generate the responses.
figure-rhetoric
Evaluate whether figures and plots in a manuscript effectively communicate the claims they support. Audits chart-type fit, axis design, visual hierarchy, data density, caption interpretation, perceptual accuracy, and narrative arc across 8 dimensions. Triggers on: "do my figures work", "check my plots", "are my graphs…
manuscript-provenance
Computational provenance audit verifying every number, table, and figure in a manuscript derives from code, not manual entry. Triggers on: "check provenance", "verify reproducibility", "audit my pipeline", "are my numbers from code", "provenance audit". Companion to manuscript-review (prose audit).