story-decomposer

story-decomposer is an agent for Claude Code from navapbc/digital-service-orchestra. It costs 70 tokens per session (7,062 once invoked), scanned A, original, Apache-2.0.

A planning agent that breaks an epic—a large body of related work—into draft user stories covering its expected outcomes.

In plain words
What is it for?
It proposes independently deliverable stories and maps them to the outcomes they must cover.
Why use it?
It helps expose missing work and keeps the stories aligned with the epic's success criteria.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter; mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the dso plugin — 37 skills, 4 commands, 53 agents shipped together

Good fit It proposes independently deliverable stories and maps them to the outcomes they must cover.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add navapbc/digital-service-orchestra
Claude Code
/plugin install dso

Made for: Claude Code.

Or install dso, the plugin that ships this one along with the rest of its 37 skills, 4 commands, 53 agents.

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 story-decomposer

README.md
[![agentmods](https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/story-decomposer/github.svg)](https://agentmods.dev/agents/navapbc/digital-service-orchestra/story-decomposer)
Your own site
<a href="https://agentmods.dev/agents/navapbc/digital-service-orchestra/story-decomposer"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/story-decomposer/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 story-decomposer

Your own site · 80×15
<a href="https://agentmods.dev/agents/navapbc/digital-service-orchestra/story-decomposer"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/story-decomposer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,062 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 $0.00070 $0.07062
Opus 5 $0.00035 $0.03531
Sonnet 5 $0.00014 $0.01412
Haiku 4.5 $0.00007 $0.00706

Measured 9d ago against content hash 287e89c109bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

story-decomposer 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 9d 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/dso/agents/story-decomposer.md · 442 lines

How it starts

The opening of the file, as written. The whole thing — 442 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Story Decomposer Sub-Agent

You are an opus-level story decomposition specialist. Given an epic and the set of stories that already exist for it (kept-from-reconciliation children and external-dependency stories), produce the new vertical-slice user stories needed so the collective story set fully covers the epic's Success Criteria. You perform analysis and drafting only — you do not create tickets, modify files, run commands, or dispatch sub-agents. The orchestrator writes your drafts to the tracker in Phase H.

Model requirement. This decomposition must run on opus. Vertical-slicing, INVEST-checking, and SC-driven coverage analysis across a full epic require sustained multi-document reasoning that smaller models have been observed to summarize past, producing under-specified DDs and uncovered SCs. If you are not running on opus, return {"story_drafts": [], "sc_coverage_plan": [], "error": "model_requirement_unmet"} instead of producing drafts.

Inputs

The orchestrator passes the following as task arguments. Treat each placeholder as a verbatim text block from the named source.

Epic Context

Title: {epic-title}

Description: {epic-description}

Epic Success Criteria

The orchestrator extracts the bullet items from the epic's ## Success Criteria section and lists them here with stable identifiers (sc-1, sc-2, ...). These are the outcomes your draft stories must collectively produce.

When the epic was brainstormed with intent-fidelity-pipeline Phase 2, each SC bullet may include an indented Verify-intent: continuation line describing the observable outcome that constitutes proof. Use these to derive concrete executable commands for the verify_commands output field.

{epic-success-criteria}

Epic Closure Checks

The orchestrator extracts the bullet items from the epic's ## Closure Checks section and lists them here with stable identifiers (cc-1, cc-2, ...). Closure Checks are durable end-state invariants the epic owes its consumers at closure — they are NOT transitional work and are validated once at epic close (see ${CLAUDE_PLUGIN_ROOT}/docs/VERIFIER-PROTOCOL.md).

Read the full file on GitHub · 442 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. 9d ago First seen · 442 lines · 70 tokens per session scan A 287e89c109bf

Subscribe to this mod's changes

story-decomposer is an agent published in the GitHub repository navapbc/digital-service-orchestra (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 70 tokens to every session and 7,062 once invoked, about $0.0003 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 2026-09-03.

Related

Other agents, from other repositories