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-manual-processgit 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-manual-process)<a href="https://agentmods.dev/skills/calionauta/stelow/stelow-product-manual-process"><img src="https://agentmods.dev/badge/skills/calionauta/stelow/stelow-product-manual-process/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-manual-process"><img src="https://agentmods.dev/badge/skills/calionauta/stelow/stelow-product-manual-process.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00128 | $0.02405 |
| Opus 5.5 | $0.00051 | $0.00962 |
| Sonnet 5.5 | $0.00026 | $0.00481 |
| Haiku 4.5 | $0.00013 | $0.00241 |
Grade A, and why
stelow-product-manual-process 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Discover the Process — the Valuable Manual Process
Objective: test the execution and usability risk — can you actually deliver the solution? Instead of jumping to full development, experiment with a "valuable manual process".
Tip: only skip this stage if you (1) already have sufficient personal knowledge of the process, or (2) have a strong assumption plus the resources to automate or produce a new simplified solution within the same time and money it would take to discover the process. In general, run this stage.
Don't underestimate the real world: you will probably spend more time and money trying to develop something if you skip this stage without agreed limits.
What to do
Systematize manual or outsourced solutions that let you learn the complete process people will use to solve the problem with the new solution, and how it fits their context. Systematize the process before productizing it.
Sahil Lavingia: "As you complete the first cycle with clients, document every part of the process so that with each subsequent client, you have a guide. This document will be the true MVP of your business — not the minimum viable product we're all trying to build and launch. I'm talking about the valuable manual process that precedes it and will be the foundation for the business you're trying to build. Methodically."
Use the six experimentation principles while running it (see the references of
stelow-product-discovery, file 01-experimentation-principles.md).
Examples of a valuable manual process
Personal assistant (concierge) — do it together with the client, live if possible. Identify and offer the best solution for them and collect feedback as you go.
Artisanal backstage (Flintstoning / Wizard of Oz) — offer a solution that looks automated to the person while you do it manually behind the curtain. Reveals bottlenecks and risks fast.
Repackaging — use another company's product or service under your own packaging. Reveals whether something already solves it well and where the improvement points are.
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 First seen · 263 lines · 128 tokens per session scan A ba60290ce629
stelow-product-manual-process is a skill published in the GitHub repository calionauta/stelow (14 stars, last pushed 9d ago), licensed MIT. It adds 128 tokens to every session and 2,405 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 2026-10-27.
stelow-product-manual-process compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| stelow-product-manual-processcalionauta/stelow | Skill | 14 | 9d ago | MIT | A | 128 | 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 |