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 calionauta/stelow --skill stelow-product-discoverygit clone --depth 1 https://github.com/calionauta/stelowWrote 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/calionauta/stelow/stelow-product-discovery)<a href="https://agentmods.dev/skills/calionauta/stelow/stelow-product-discovery"><img src="https://agentmods.dev/badge/skills/calionauta/stelow/stelow-product-discovery/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/skills/calionauta/stelow/stelow-product-discovery"><img src="https://agentmods.dev/badge/skills/calionauta/stelow/stelow-product-discovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00133 | $0.02945 |
| Opus 5.5 | $0.00053 | $0.01178 |
| Sonnet 5.5 | $0.00027 | $0.00589 |
| Haiku 4.5 | $0.00013 | $0.00295 |
Grade A, and why
stelow-product-discovery 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 10d 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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product with Short Learning Cycles — Router
This guide replaces speculation with evidence, step by step. Core principle: experiment before building. Reduce uncertainty with small, fast, cheap experiments.
"Life is too short to build something that nobody wants." — Ash Maurya
The method has 8 stages, not necessarily linear. This skill routes; the content of each stage lives in the skill or reference named in the map below. Read the target, not this page, once you know which stage you are in.
Stage map
| # | Stage | Where it lives | Artifact it produces |
|---|---|---|---|
| 1 | Find and understand the audience | stelow-product-audience-market |
interview notes |
| 2 | Define the market | stelow-product-audience-market |
GPN story (group, purpose, needs) |
| 3 | Define and prioritize solutions | stelow-product-solutions |
prioritized solution list |
| 4 | Develop and evaluate the offer | stelow-product-offer |
offer definition |
| 5 | Assess commitment | stelow-product-launch-validation |
pre-sales / waitlist counts |
| 6 | Discover the process | stelow-product-manual-process |
manual delivery script |
| 7 | Evolve to a viable business | stelow-product-viable-business |
product-market fit verdict + channel |
| 8 | The pulse of the system | stelow-product-health |
signal tension read |
Before any stage, the reliability rules for evidence live in the Evidence section of this file, below. Read it when a stage result looks convincing but weak.
Reference files
None. Stages 1 through 8 all resolve to skills, and the evidence rules live in this file. The method's sources (Maurya, Kagan, Savoia, Lavingia, Hormozi, Ulwick, NFX and others) are credited where they are used, in the skill that applies them — there is no central bibliography, because a list of books nobody opens is not a reference.
Domain skills
These are not stages. They are cuts you reach for by topic, in any order, when the question is about that domain rather than about where you are in the method:
What ships with it
7 files 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.
- 10d ago Changed · +65 lines · -4 tokens per session f9d219672c7c
- 14d ago Changed · +5 lines 319a348838ac
- 1mo ago Changed 427a69620dc2
- 1mo ago Changed · +6 lines 883979ffa4cb
- 1mo ago Changed · +18 lines e7134819163a
- 1mo ago Changed · +7 lines c590d5a3f2a2
- 1mo ago Changed · +22 lines d5f204f9fa60
- 2mo ago First seen · 171 lines · 137 tokens per session scan A 9a0252686db0
stelow-product-discovery is a skill published in the GitHub repository calionauta/stelow (14 stars, last pushed 9d ago), licensed MIT. It adds 133 tokens to every session and 2,945 once invoked, about $0.0005 per session on Opus 5.5. 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.
stelow-product-discovery compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| stelow-product-discoverycalionauta/stelow | Skill | 14 | 9d ago | MIT | A | 133 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |