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 xonovex/platform --skill user-stories-guidegit clone --depth 1 https://github.com/xonovex/platformWrote 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/xonovex/platform/user-stories-guide)<a href="https://agentmods.dev/skills/xonovex/platform/user-stories-guide"><img src="https://agentmods.dev/badge/skills/xonovex/platform/user-stories-guide/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/xonovex/platform/user-stories-guide"><img src="https://agentmods.dev/badge/skills/xonovex/platform/user-stories-guide.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 | $0.00132 | $0.00980 |
| Opus 5.5 | $0.00053 | $0.00392 |
| Sonnet 5 | $0.00026 | $0.00196 |
| Haiku 4.5 | $0.00013 | $0.00098 |
Grade A, and why
user-stories-guide 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 15d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Stories
A user story is a placeholder for a conversation about user value, not a specification. Write it small, talk it through, confirm it with acceptance criteria, and slice it vertically so every story ships usable value end to end.
Essentials
- Check every story against INVEST - Independent, Negotiable, Valuable, Estimable, Small, Testable, see references/invest-and-smart.md
- Treat the story as the 3 Cs - a Card invites a Conversation, confirmed by a Confirmation test, see references/three-cs.md
- Write who / what / why, then acceptance criteria - "As a / I want / so that" plus acceptance criteria, see references/template-and-acceptance-criteria.md
- Split a too-big story vertically - SPIDR for a quick set, the splitting flowchart for the full decision tree, see references/splitting-spidr.md and references/splitting-flowchart.md
- Refine the backlog continuously - break items down until each is doable within one sprint and ready, see references/backlog-refinement.md
Gotchas
- A walking skeleton is production code with tests linking the main components end to end, not a throwaway prototype or a research spike.
- Never split horizontally ("build the DB", "build the API", "build the UI"); those are tasks/components. Every story is a thin vertical slice.
- A Spike yields knowledge, not shippable value, so it is a last-resort move, not itself a vertically-sliced story.
- The template is a conversation starter, not a mandatory format, no method prescribes a fixed story format.
- Acceptance criteria can later be written as Given-When-Then for automation. That notation is owned by bdd-guide.
- Backlog refinement is an ongoing activity, not a fixed weekly "grooming meeting"; sizing is the Developers' responsibility.
What ships with it
9 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.
- eval-queries.json 4.2 KB
- evals.json 2.2 KB
- references/backlog-refinement.md 1.4 KB
- references/invest-and-smart.md 1.6 KB
- references/splitting-flowchart.md 2.6 KB
- references/splitting-spidr.md 1.7 KB
- references/template-and-acceptance-criteria.md 1.8 KB
- references/three-cs.md 2.2 KB
- SOURCES.md 4.3 KB
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.
- 15d ago First seen · 56 lines · 132 tokens per session scan A e5f7e024fbc2
user-stories-guide is a skill published in the GitHub repository xonovex/platform (6 stars, last pushed 2d ago), licensed MIT. It adds 132 tokens to every session and 980 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 2026-09-08.
Other skills, from other repositories
persona-project-manager
Coordinate projects — track tasks, schedule meetings, and share docs.
recipe-plan-weekly-schedule
Review your Google Calendar week, identify gaps, and add events to fill them.
atmos-modernization
Atmos Modernization: migrate deprecated or legacy Atmos patterns to current names, Native CI, Atmos Pro drift detection, dependencies.components, nametemplate, and declared secrets.
atmos-workflows
Workflow automation: native step types, multi-step workflows, parallel/matrix/wait/container/emulator steps, when: conditions (CEL), require/assert preconditions, output steps, retries, dependencies, and cross-component orchestration.
agentbox-setup
Generate an agentbox.yaml for the current AgentBox workspace. Invoke when the user opens a sandbox without an agentbox.yaml or asks to (re)configure one.
linear-graphql-skill
Operate Linear workspace issues, projects, and teams through Linear GraphQL API using UXC. Use when tasks require querying or creating issues, managing projects, or interacting with Linear workflow. Supports both Personal API Key and OAuth authentication.