po-split-story

po-split-story is a skill for Claude Code, Codex from abrahamFerga/scrum-skills. It costs 113 tokens per session (1,753 once invoked), scanned A, original, MIT.

A story-splitting method for breaking a large user story or epic into smaller pieces that can be completed and delivered independently within one sprint. A sprint is a short, fixed period in which a development team completes planned work.

In plain words
What is it for?
Fetch or accept a story from Jira, Azure DevOps, or pasted text, diagnose why it is too large, and apply established patterns to divide it into smaller stories.
Why use it?
Large stories make planning and progress unclear and may hide work that was never agreed on. Splitting them exposes the scope and produces more manageable work items.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

Good fit Fetch or accept a story from Jira, Azure DevOps, or pasted text, diagnose why it is too large, and apply established patterns to divide it into smaller stories.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/abrahamferga/scrum-skills/po-split-story
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.

Any agent
npx skills add abrahamFerga/scrum-skills --skill po-split-story
Clone the repo
git clone --depth 1 https://github.com/abrahamFerga/scrum-skills

Made for: Claude Code, Codex.

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 po-split-story

README.md
[![agentmods](https://agentmods.dev/badge/skills/abrahamferga/scrum-skills/po-split-story/github.svg)](https://agentmods.dev/skills/abrahamferga/scrum-skills/po-split-story)
Your own site
<a href="https://agentmods.dev/skills/abrahamferga/scrum-skills/po-split-story"><img src="https://agentmods.dev/badge/skills/abrahamferga/scrum-skills/po-split-story/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 po-split-story

Your own site · 80×15
<a href="https://agentmods.dev/skills/abrahamferga/scrum-skills/po-split-story"><img src="https://agentmods.dev/badge/skills/abrahamferga/scrum-skills/po-split-story.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,753 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 $0.00113 $0.01753
Opus 5 $0.00056 $0.00877
Sonnet 5 $0.00023 $0.00351
Haiku 4.5 $0.00011 $0.00175

Measured 11d ago against content hash 93c877470d84, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

po-split-story 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 11d 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.

skills/po-split-story/SKILL.md · 214 lines

How it starts

The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Story Splitting

Purpose

A story that cannot fit in one Sprint is a planning liability — it blocks commitment, obscures progress, and almost always hides scope nobody agreed to. This skill applies the nine proven splitting patterns to turn one large story into multiple small ones, each independently valuable and completable in a single Sprint.


Tool detection

  1. Check for active mcp__azure-devops__* tools → $PM_TOOL = ado
  2. Check for active mcp__jira__* tools → $PM_TOOL = jira
  3. If both → ask which tool to use
  4. If neither → $PM_TOOL = manual

Step 1 — Fetch the story

Ask: "Which story needs splitting? Provide the ID or paste the content."

  • ADO: use wit_get_work_item — read title, description, acceptance criteria, story points, and parent
  • Jira: use the get-issue tool — read summary, description, acceptance criteria, story points, and epic link
  • Manual: accept pasted content

If the item is an Epic, treat the whole Epic as the input. Store as $STORY.


Step 2 — Diagnose why it is too large

Before splitting, understand what makes it large. This determines which pattern fits best.

Ask yourself — and the PO if needed:

  • Does it cover multiple user types? → split by persona
  • Does it span multiple workflow steps end-to-end? → split by workflow
  • Does it handle many data variations or edge cases? → split by data
  • Does it cover both the happy path and error handling? → split happy/unhappy
  • Does it need to work across multiple channels (web, mobile, API)? → split by interface
  • Does it include both basic and high-performance versions? → split by performance
  • Does it bundle create, read, update, delete? → split by operation (CRUD)
  • Does it mix a core feature with validation, logging, or notifications? → split cross-cutting concerns
  • Does it depend on a system integration that is not ready? → defer the integration, stub it first

Step 3 — Apply the best-fit pattern

Read the full file on GitHub · 214 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. 11d ago First seen · 214 lines · 113 tokens per session scan A 93c877470d84

Subscribe to this mod's changes

po-split-story is a skill published in the GitHub repository abrahamFerga/scrum-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 113 tokens to every session and 1,753 once invoked, about $0.0006 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 2026-08-31.