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-healthgit 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-health)<a href="https://agentmods.dev/skills/calionauta/stelow/stelow-product-health"><img src="https://agentmods.dev/badge/skills/calionauta/stelow/stelow-product-health/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-health"><img src="https://agentmods.dev/badge/skills/calionauta/stelow/stelow-product-health.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 | $0.00038 | $0.02332 |
| Opus 5.5 | $0.00015 | $0.00933 |
| Sonnet 5.5 | $0.00008 | $0.00466 |
| Haiku 4.5 | $0.00004 | $0.00233 |
Grade A, and why
stelow-product-health 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Health: Signals in Tension
The Problem of Single Signal Optimization
In a world that pushes for incessant number optimization, it's easy to fall into the trap of pursuing signals in isolation — focusing on what grows fastest or looks most impressive (like number of new users or frequency of use).
This practice carries silent risks: the "cobra effect" — when trying to solve a problem with one signal, we end up generating unexpected negative consequences in other areas. It is like a treadmill: the person is active, but not progressing. Optimizing a single signal can lead to a product that "works", but generates unwanted human costs: addiction, anxiety, loss of time, or superficial use that doesn't deliver real value.
Systems are complex and interconnected. What seems like an improvement at one end can unbalance the whole.
The Proposal: Sets of Signals in Tension
Instead of seeking the absolute signal, monitor the "pulse of the system" through sets of signals in tension. The intention is to monitor both the effectiveness of the solution and the user's well-being, focusing on removing unwanted side effects instead of just adding more growth numbers.
For each set, there is a success signal and one or more counterbalance signals. By observing the tension between them, you get a more comprehensive and balanced view.
The 3 Essential Sets of Signals
1. Tension: Speed vs. Quality of Activation
Success Signal — Did the User Experience Initial Value?
What to observe: identify the most important action a new user needs to take to experience core value for the first time. Think of the "aha! moment" — the instant when the person perceives the purpose of the solution.
Intuitive Examples:
- Task organization app: "a new user who creates and completes their first task in the first 3 days"
- Meal delivery service: "a new customer who places and receives their first order in the first week"
Justification: this action represents the first delivery of real value — the point at which the user experiences the central purpose of the solution.
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 · +10 lines cbb865de8655
- 14d ago Changed · +5 lines eb8b1d939e76
- 1mo ago Changed · +6 lines c0a1c227ca7e
- 1mo ago Changed · +18 lines 60ef0cb995d8
- 1mo ago Changed · +7 lines 6a4617a118c8
- 1mo ago Changed · +22 lines fe659c2a3844
- 2mo ago First seen · 144 lines · 38 tokens per session scan A 7ed357b8d937
stelow-product-health is a skill published in the GitHub repository calionauta/stelow (14 stars, last pushed 9d ago), licensed MIT. It adds 38 tokens to every session and 2,332 once invoked, about $0.0002 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-health compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| stelow-product-healthcalionauta/stelow | Skill | 14 | 9d ago | MIT | A | 38 | Claude Code |
| 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 |