create-stories-from-epic

create-stories-from-epic is a command for Claude Code from quay/ai-helpers. It costs 19 tokens per session (4,091 once invoked), scanned A, original, MIT.

A command workflow that reads a JIRA epic and drafts smaller child stories for review before creating them in JIRA. JIRA is a system for tracking software work; an epic is a large piece of work made up of smaller issues.

In plain words
What is it for?
Use it to fetch an epic, extract its requirements and context, write a planning file, generate child stories, and create them in JIRA after approval.
Why use it?
It turns a broad requirement into independently implementable tasks while keeping a review step before changes are made.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the TodoWrite tool.

Part of the jira plugin — 2 skills, 6 commands shipped together

Good fit Use it to fetch an epic, extract its requirements and context, write a planning file, generate child stories, and create them in JIRA after approval.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/quay/ai-helpers/create-stories-from-epic
Install

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.

Clone the repo
git clone --depth 1 https://github.com/quay/ai-helpers

Made for: Claude Code.

Or install jira, the plugin that ships this one along with the rest of its 2 skills, 6 commands.

Wrote 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.

agentmods badge for create-stories-from-epic

README.md
[![agentmods](https://agentmods.dev/badge/commands/quay/ai-helpers/create-stories-from-epic/github.svg)](https://agentmods.dev/commands/quay/ai-helpers/create-stories-from-epic)
Your own site
<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.

agentmods 80×15 button for create-stories-from-epic

Your own site · 80×15
<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>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,091 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 4d ago against content hash 57de1efb5674, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

plugins/jira/commands/create-stories-from-epic.md · 531 lines

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

Read the full file on GitHub · 531 lines

Changes

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.

  1. 4d ago First seen · 531 lines · 19 tokens per session scan A 57de1efb5674

Subscribe to this mod's changes

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.