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/quay/ai-helpersWrote 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/quay/ai-helpers/create-stories-from-epic)<a href="https://agentmods.dev/commands/quay/ai-helpers/create-stories-from-epic"><img src="https://agentmods.dev/badge/commands/quay/ai-helpers/create-stories-from-epic/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/quay/ai-helpers/create-stories-from-epic"><img src="https://agentmods.dev/badge/commands/quay/ai-helpers/create-stories-from-epic.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 | $0.00019 | $0.04091 |
| Opus 5 | $0.00010 | $0.02046 |
| Sonnet 5 | $0.00004 | $0.00818 |
| Haiku 4.5 | $0.00002 | $0.00409 |
Grade A, and why
create-stories-from-epic 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 4d 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 — 531 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Child Stories from Epic
Fetch the epic from JIRA: $ARGUMENTS
Your Task
Analyze the epic and generate a set of child stories that together fulfill all requirements defined in the epic. Each story must be independently implementable by Claude.
Process
Step 1: Fetch Epic from JIRA
Retrieve the complete epic information from JIRA:
acli jira workitem view $ARGUMENTS
Extract from JIRA output:
- Epic Title - The summary field (displayed at top of output)
- Epic Description - The description section (under "Description" heading)
- Epic Name - The epic name field (customfield_12311141)
- Component - Component tags if present
- Labels - Any labels applied
- Linked Issues - Child stories already created, if any
- Comments - Additional context from comments
Parse the description: The epic description should be in markdown format and may contain:
- Overview/Context section
- Scope (in-scope and out-of-scope)
- Technical Approach
- Success Criteria
- Dependencies
- Testing Strategy
- etc.
Save epic content:
Create .claude/plans/$ARGUMENTS-epic.md with:
- Epic title as H1
- Full epic description from JIRA
- Link to JIRA issue:
https://issues.redhat.com/browse/$ARGUMENTS
This file serves as the source for story generation.
Step 2: Analyze the Epic
From the fetched epic content, identify:
- All functional requirements
- All technical requirements
- Dependencies between components
- Success criteria
- Architectural decisions
- Scope (in-scope and out-of-scope items)
Step 3: Decompose into Stories
Break down the epic into logical, independently deliverable units of work:
- Each story should represent a cohesive piece of functionality
- Order stories to respect dependencies (foundational work first)
- Aim for stories that can be completed in a focused coding session
- Consider technical layers (data model, API, worker, UI)
- Consider phases (MVP, enhancements, testing, documentation)
Step 4: Generate Stories
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.
- 4d ago First seen · 531 lines · 19 tokens per session scan A 57de1efb5674
create-stories-from-epic is a command published in the GitHub repository quay/ai-helpers (3 stars, last pushed 22d ago), licensed MIT. It adds 19 tokens to every session and 4,091 once invoked, about $0.0001 per session on Opus 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 2026-09-04.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
sync-linear
Sync current work with Linear ticket status.
add-note
Add an internal or external note to a ConnectWise PSA ticket.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
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.