decompose

A workflow for researching a large or unclear User Story—a description of a desired product change—and breaking it into smaller tasks in YouTrack, a project-management tool.

In plain words
What is it for?
Use it before solving a large YouTrack issue to check the current code, record research, identify dependencies, and create actionable subtasks.
Why use it?
It turns a vague request into an investigated, ordered plan based on the code and its dependencies. It also pauses for approval before major stages and before creating tasks.

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/vmkteam/claude-plugins/decompose
Any agent
npx skills add vmkteam/claude-plugins --skill decompose
Clone the repo
git clone --depth 1 https://github.com/vmkteam/claude-plugins

Made for: Claude Code, Codex.

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,090 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 $0.00046 $0.02090
Opus 5 $0.00023 $0.01045
Sonnet 5 $0.00009 $0.00418
Haiku 4.5 $0.00005 $0.00209

Measured 2d ago against content hash 6e0ceae141df, 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.

plugins/developer/skills/decompose/SKILL.md · 246 lines

How it starts

The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/decompose — исследование и декомпозиция задачи

Исследование User Story или крупной задачи, анализ кода, декомпозиция на подзадачи с созданием в YouTrack. Подключения к системам из .claude/memory/project-index.md.

Использование

/decompose US-264
/decompose PLF-850

Артефакты

docs/llm/tasks/{TASK_ID}/
├── research.md      — исследование, анализ кода, зависимости, решения

Flow

PREFLIGHT → FETCH → RESEARCH → ⏸ HITL → DECOMPOSE → ⏸ HITL → CREATE → ⏸ HITL

0. PREFLIGHT — актуальность базовой ветки

Перед workflow проверить, что локальный базовый бранч синхронизирован с origin — иначе research пойдёт по устаревшему коду.

Имя базовой ветки — из project-index.md (base_branch, по умолчанию devel).

BASE={base_branch}
git fetch origin $BASE --quiet
LOCAL=$(git rev-parse $BASE 2>/dev/null || echo none)
REMOTE=$(git rev-parse origin/$BASE)

Если LOCAL != REMOTE — ⏸ HITL: Обновить (git checkout $BASE && git pull --ff-only, вернуться на исходную ветку) / Продолжить (на свой риск) / Отмена.


1. FETCH — прочитать задачу

Получить задачу из YouTrack:

pcurl @{yt_profile} 'https://{yt_host}/api/issues/{TASK_ID}?fields=idReadable,summary,description,created,updated,reporter(login,name),assignee(login,name),tags(name),comments(author(login,name),text,created),customFields(name,value(name))' -s

Получить связанные задачи:

pcurl @{yt_profile} 'https://{yt_host}/api/issues/{TASK_ID}?fields=idReadable,summary,links(direction,linkType(name),issues(idReadable,summary,resolved))' -s

Найти существующие subtasks:

pcurl @{yt_profile} 'https://{yt_host}/api/issues?query=subtask+of:+{TASK_ID}&fields=idReadable,summary,customFields(name,value(name))&$top=30' -s

Создать директорию: mkdir -p docs/llm/tasks/{TASK_ID}/

2. RESEARCH — глубокое исследование (plan mode)

Войти в plan mode. Не писать код — только анализ.

2a. Анализ кода (параллельно)

Запустить агентов (subagent_type=Explore) для параллельного исследования:

Read the full file on GitHub · 246 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 · 246 lines · 46 tokens per session scan A 6e0ceae141df

Subscribe to this mod's changes

decompose is a skill published in the GitHub repository vmkteam/claude-plugins (7 stars, last pushed 4mo ago), licensed MIT. It adds 46 tokens to every session and 2,090 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens