Borrowing it
Nothing to install: this file belongs to opensupplyhub/open-supply-hub. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/opensupplyhub/open-supply-hub/main/.agent/skills/user-story-writer/SKILL.mdgit clone --depth 1 https://github.com/opensupplyhub/open-supply-hubWrote 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/opensupplyhub/open-supply-hub/user-story-writer)<a href="https://agentmods.dev/skills/opensupplyhub/open-supply-hub/user-story-writer"><img src="https://agentmods.dev/badge/skills/opensupplyhub/open-supply-hub/user-story-writer/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/opensupplyhub/open-supply-hub/user-story-writer"><img src="https://agentmods.dev/badge/skills/opensupplyhub/open-supply-hub/user-story-writer.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 | $0.00000 | $0.01788 |
| Opus 5.5 | $0.00000 | $0.00715 |
| Sonnet 5.5 | $0.00000 | $0.00358 |
| Haiku 4.5 | $0.00000 | $0.00179 |
Grade A, and why
user-story-writer 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 2mo 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Story Writer
You draft, review, improve, and file OS Hub user stories. The source of truth is the format and the four tests defined below in this skill — cite the specific test a draft violates when flagging it, so the user learns as you work.
The format
As a [specific persona]
I want to [outcome]
So that [value, chain completed]
What is hard today: [user's reality, NOT the proposed fix]
Good vs bad — worked examples
GOOD (brand data contributor):
As a brand data contributor,
I want to get better data back from OS Hub than what I put in,
So that contributing becomes a data quality investment, not just a disclosure exercise.
What is hard today: uploaders don't get meaningfully better data back. There's no signal of what improved or why — so the incentive disappears. If uploading doesn't make my own data better, it's just overhead.
Why it works: specific persona; names a value and what it's competing with (investment vs. disclosure); the pain reframes the whole problem in one sentence; doesn't prescribe a feature.
BAD (Lawrenceburg, before rewrite):
As a facility owner contributing to OS Hub,
I want to add all certifications, standards, regulations, and affiliations,
So that I can show our capabilities on my OS Hub profile.
What is hard today: there are thousands — an email box for missing ones will help.
Why it fails: "add" is a mechanism, not an outcome; "show capabilities" leaves the chain hanging; "email box" jumps to a feature instead of describing reality. The persona is also wrong — it's a claimed-profile owner, not a contributor.
The core shift — start with the outcome:
"The 'so that' should be the story. The thing they want to do was showing up in our 'so that' — we were prescribing a really narrow thing that accomplished the outcome, as opposed to starting with the outcome and brainstorming how to achieve it."
REWRITE:
As a facility owner contributing to OS Hub,
I want brands sourcing for facilities with my certifications to find me,
So that I'm considered for procurement opportunities I'm qualified for, and OS Hub becomes a real sourcing channel — not just a directory.
What is hard today: my certifications aren't surfaced in a way brands can search or filter against. I miss being shortlisted for opportunities I'd win, and I have no signal whether contributing produces business value.
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.
- 2mo ago First seen · 163 lines · 0 tokens per session scan A 84144704f095
user-story-writer is a skill published in the GitHub repository opensupplyhub/open-supply-hub (22 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,788 tokens. 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.
user-story-writer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| user-story-writeropensupplyhub/open-supply-hub | Skill | 22 | yesterday | MIT | A | 0 | 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 |