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-refine)<a href="https://agentmods.dev/commands/matteocervelli/llms/user-story-refine"><img src="https://agentmods.dev/badge/commands/matteocervelli/llms/user-story-refine/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-refine"><img src="https://agentmods.dev/badge/commands/matteocervelli/llms/user-story-refine.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 | $0.00009 | $0.00734 |
| Opus 5.5 | $0.00004 | $0.00294 |
| Sonnet 5.5 | $0.00002 | $0.00147 |
| Haiku 4.5 | $0.00001 | $0.00073 |
Grade A, and why
user-story-refine 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refine and Validate User Stories
Validate and refine existing user stories against INVEST criteria.
Usage
/user-story-refine <story-id>
/user-story-refine backlog
/user-story-refine --all
Examples
/user-story-refine US-0001
/user-story-refine backlog
/user-story-refine --all
What it does
- Load Stories - Loads specified story or multiple stories
- Validate - Runs INVEST validation on each story
- Report Issues - Presents validation issues with severity
- Suggest Fixes - Provides specific, actionable suggestions
- Apply Fixes - Optionally applies auto-fixes with user approval
- Regenerate - Updates Markdown documentation
Result
- Validation scores for each story
- List of issues found (critical/warnings)
- Specific fix suggestions
- Updated YAML files (if fixes applied)
- Regenerated Markdown documentation
Activate the story-validator skill to validate and refine user stories.
Use the story-validator skill located in .claude/skills/story-validator/SKILL.md.
Parameters
- story-id: Specific story to validate (e.g., US-0001)
- backlog: Validate all stories with status "backlog"
- --all: Validate all stories regardless of status
Validation Criteria (INVEST)
- Independent - Can be developed separately
- Negotiable - Open to discussion
- Valuable - Delivers business value
- Estimable - Can be estimated
- Small - Fits within a sprint (≤8 points)
- Testable - Has clear acceptance criteria
Scoring
- 0-49: Fail - Requires significant improvement
- 50-69: Needs work - Has issues to address
- 70-84: Good - Minor improvements possible
- 85-100: Excellent - High quality story
Auto-Fix Capabilities
The skill can automatically fix:
- Missing story points (estimates based on complexity)
- Empty "so that" benefits (generates from context)
- Incomplete acceptance criteria (adds standard scenarios)
- Vague descriptions (suggests clarifications)
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 · 106 lines · 9 tokens per session scan A a4628baede6c
user-story-refine is a command published in the GitHub repository matteocervelli/llms (25 stars, last pushed 5mo ago), licensed MIT. It adds 9 tokens to every session and 734 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.