decompose

A planning tool that breaks one large Linear ticket into smaller tasks tied to specific parts of a codebase, with task dependencies and a plan for parallel work.

In plain words
What is it for?
Use it to split a Linear ticket or feature description, identify affected components and source files, and create dependent sub-issues for parallel implementation.
Why use it?
Large tickets can be difficult to split safely, especially when several developers or coding agents work at once. This creates clearer ownership and shows which tasks can start independently.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/stoa-platform/stoa/decompose
Any agent
npx skills add stoa-platform/stoa --skill decompose
Clone the repo
git clone --depth 1 https://github.com/stoa-platform/stoa

Made for: Claude Code, Codex.

Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,213 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00027 $0.04213
Opus 5 $0.00014 $0.02107
Sonnet 5 $0.00005 $0.00843
Haiku 4.5 $0.00003 $0.00421

Measured 2d ago against content hash 562cc47ec54d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

decompose 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 2d 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.

.claude/skills/decompose/SKILL.md · 407 lines

How it starts

The opening of the file, as written. The whole thing — 407 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Decompose — Component-Scoped Ticket Splitter

Target: $ARGUMENTS

Purpose

Split a MEGA ticket (or feature description) into independent, component-scoped sub-issues optimized for parallel execution by multiple Claude Code instances.

Step 1: Gather Source Material

If $ARGUMENTS is a CAB-XXXX ticket ID:

linear.get_issue("CAB-XXXX", includeRelations=true)

Extract: title, description, DoD, estimate, labels, parent.

If $ARGUMENTS is a feature description:

Use the description directly. Proceed without Linear context.

Always read:

  • memory.md — current sprint context
  • Relevant source files — to understand which components are impacted

Step 2: Identify Affected Components

Analyze the feature and map to STOA components:

Component Path Linear Label ID Tech Instance Label
cp-api control-plane-api/ <LABEL_ID_CP_API> Python, FastAPI instance:backend
cp-ui control-plane-ui/ <LABEL_ID_CP_UI> React, Console instance:frontend
portal portal/ <LABEL_ID_PORTAL> React, Portal instance:frontend
gateway stoa-gateway/ <LABEL_ID_GATEWAY> Rust, axum instance:mcp
operator stoa-operator/ (create if needed) Python, kopf instance:backend
e2e e2e/ (create if needed) Playwright instance:qa
docs stoa-docs (separate repo) <LABEL_ID_DOCS> Docusaurus instance:backend
infra charts/, k8s/ <LABEL_ID_INFRA> Helm, K8s instance:backend
keycloak keycloak/, OAuth/IAM (use auth label) Keycloak instance:auth

Instance Dispatch Mapping

Each sub-issue is tagged with an instance:* label for automatic dispatch to parallel tmux windows. See .claude/docs/instance-dispatch.md for the full mapping and cross-component rules.

Instance Label Components tmux Window Scope
instance:backend cp-api, operator, infra, docs Window 2 (BACKEND) control-plane-api/, charts/, k8s/
instance:frontend cp-ui, portal, shared Window 3 (FRONTEND) control-plane-ui/, portal/, shared/
instance:auth keycloak, IAM Window 4 (AUTH) keycloak/, OAuth configs
instance:mcp gateway Window 5 (MCP) stoa-gateway/
instance:qa e2e Window 6 (QA) e2e/

Read the full file on GitHub · 407 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. 2d ago First seen · 407 lines · 27 tokens per session scan A 562cc47ec54d

Subscribe to this mod's changes

decompose is a skill published in the GitHub repository stoa-platform/stoa (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 27 tokens to every session and 4,213 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 2026-08-31.