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.
git clone --depth 1 https://github.com/matteocervelli/llmsWrote 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/commands/matteocervelli/llms/user-story-new)<a href="https://agentmods.dev/commands/matteocervelli/llms/user-story-new"><img src="https://agentmods.dev/badge/commands/matteocervelli/llms/user-story-new/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/commands/matteocervelli/llms/user-story-new"><img src="https://agentmods.dev/badge/commands/matteocervelli/llms/user-story-new.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 | $0.00010 | $0.00601 |
| Opus 5.5 | $0.00004 | $0.00240 |
| Sonnet 5.5 | $0.00002 | $0.00120 |
| Haiku 4.5 | $0.00001 | $0.00060 |
Grade A, and why
user-story-new 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 1mo 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create New User Stories from Feature
Create user stories from a feature description following INVEST criteria.
Usage
/user-story-new [feature-description]
Examples
/user-story-new "Dashboard analytics for CEO"
/user-story-new "User authentication with OAuth"
/user-story-new
What it does
- Feature Extraction - Asks questions to extract feature details
- Story Generation - Decomposes feature into 2-8 user stories
- Validation - Validates stories against INVEST criteria
- Technical Annotation - Adds tech context and implementation hints
- File Creation - Creates YAML files and Markdown documentation
- GitHub Sync - Creates GitHub issues (if enabled)
Result
- YAML story files in
stories/yaml-source/ - Markdown documentation in
stories/generated-docs/ - GitHub issues (if enabled)
- Validation scores and technical annotations
Activate the user-story-generator skill to create user stories from the provided feature description.
Use the user-story-generator skill located in .claude/skills/user-story-generator/SKILL.md.
Parameters
- feature-description (optional): Brief description of the feature. If omitted, the skill will ask for it interactively.
Workflow
The skill will:
- Accept or ask for feature description
- Extract feature details through Q&A (persona, requirements, priority)
- Show extracted JSON and ask for confirmation
- Generate 2-8 user stories following INVEST criteria
- Validate each story (silent qa-validator-agent)
- Add technical annotations (silent technical-annotator-agent)
- Create YAML source files
- Generate Markdown documentation
- Create GitHub issues if enabled
- Present comprehensive summary
File References
- Skill:
.claude/skills/user-story-generator/SKILL.md - Scripts:
.claude/skills/story-validator/scripts/validate_story_invest.py,.claude/skills/user-story-generator/scripts/generate_story_from_yaml.py,.claude/skills/user-story-generator/scripts/github_sync.py - Templates:
.claude/skills/user-story-generator/templates/story-template.yaml,.claude/skills/user-story-generator/templates/story-template.md - Config:
.claude/skills/user-story-generator/config/automation-config.yaml,.claude/skills/user-story-generator/config/personas.yaml
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.
- 1mo ago First seen · 78 lines · 10 tokens per session scan A 33c723256d69
user-story-new is a command published in the GitHub repository matteocervelli/llms (25 stars, last pushed 5mo ago), licensed MIT. It adds 10 tokens to every session and 601 once invoked, about $0.0000 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 2026-09-03.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
add-note
Add an internal or external note to a ConnectWise PSA ticket.
sync-linear
Sync current work with Linear ticket status.
dispatcher
Use when you want the orchestrator to pick the next repo to work on across your whole portfolio — it enumerates candidate repos below the confinement root, resolves free/busy from each repo's session.lock lease, ranks the FREE ones by backlog priority × staleness × readiness, recommends the single most worthwhile one…
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.