agentmods.dev

decompose-issue

decompose-issue is a skill for Claude Code from YoungjaeDev/my-claude-plugins. It costs 192 tokens per session (3,805 once invoked), scanned B, original, MIT.

A work-planning skill that turns a large GitHub task into smaller, linked issues and maps the proposed architecture and workflow.

In plain words
What is it for?
Use it to break down implementation work, identify project components, suggest a milestone, and create GitHub issues.
Why use it?
It helps teams make broad work easier to estimate, assign, and complete in separate pieces.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; names the AskUserQuestion tool.

Not installable on its own: it reads a path above its own folder, which only exists inside its repository. The line is **CRITICAL — DO NOT include Mermaid in milestone description.** GitHub milestone pages do not render Mermaid; the raw code shows as plain text. Mermaid belongs .

Part of the dev plugin — 12 skills shipped together

not rated 2 changed today B scan 192 tokens original MIT
View the source file YoungjaeDev/my-claude-plugins
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 YoungjaeDev/my-claude-plugins
Claude Code
/plugin install dev

Made for: Claude Code.

Or install dev, the plugin that ships this one along with the rest of its 12 skills.

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 decompose-issue

README.md
[![agentmods](https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/decompose-issue.svg)](https://agentmods.dev/skills/youngjaedev/my-claude-plugins/decompose-issue)
Your own site
<a href="https://agentmods.dev/skills/youngjaedev/my-claude-plugins/decompose-issue"><img src="https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/decompose-issue.svg" alt="Measured on agentmods" height="20"></a>
Per session 192 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,805 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 5.1 $0.00192 $0.03805
Opus 5 $0.00096 $0.01903
Sonnet 5 $0.00038 $0.00761
Haiku 4.5 $0.00019 $0.00380

Measured today against content hash b5a1881ae34a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

decompose-issue scanned grade B with 1 finding 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 today.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat > .claude/state/project-tracking-${SLUG}.json << 'STATEEOF'
plugins/dev/skills/decompose-issue/SKILL.md · 326 lines

How it starts

The opening of the file, as written. The whole thing — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Decompose Work

Cross-runtime interactive input

Every confirmation below runs through a capability-aware interactive-input gate, not one hardcoded tool. Read each AskUserQuestion mention as this gate:

  • Claude Code — use AskUserQuestion.
  • Codex — use request_user_input when that tool is exposed. When it is not, ask ONE concise blocking question only where a wrong assumption would be costly (e.g. creating GitHub issues); otherwise proceed on a documented safe default and state the assumption.

Full policy: AGENTS.md → "Cross-runtime interactive input policy".

Break down large work items into manageable, independent issues. Follow project guidelines in @CLAUDE.md.

Workflow

  1. Check issue numbers: Run gh issue list to view current issue numbers
  2. Discover available components:
    • Scan .claude/agents/ for custom agents (read YAML frontmatter)
    • Detect test frameworks (jest.config., pytest.ini, vitest.config., pyproject.toml, etc.)
  3. Check TDD applicability (if user hasn't specified):
    • Analyze work type: code implementation vs docs/infra/config
    • If test framework detected + code work → Ask: "Create issues with TDD approach?"
    • If no test framework → Inform: "TDD not required. (Reason: No test framework detected)"
    • If non-code work (docs/infra) → Inform: "TDD not required. (Reason: Non-code work)"
    • If TDD selected: Add <!-- TDD: enabled --> marker to each issue body
  4. Analyze work: Understand core requirements and objectives
  5. Decompose work: Split major tasks into context-completable units - each issue should be completable in a single Claude session without context switching. Group related features together rather than splitting by individual functions
  6. Analyze dependencies: Identify prerequisite tasks
  7. Suggest milestone name: Propose a milestone to group decomposed tasks
  8. Check related PRs (optional): Run gh pr list --state closed --limit 20 for similar work references (skip if none)
  9. Output decomposed issues: Display issues with proposed milestone name

Read the full file on GitHub · 326 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. today Changed · +4 lines · +63 tokens per session b5a1881ae34a
  2. 5d ago First seen · 322 lines · 129 tokens per session scan B bb784eca8c81

Subscribe to this mod's changes

decompose-issue is a skill published in the GitHub repository YoungjaeDev/my-claude-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 192 tokens to every session and 3,805 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

PlanningProject management
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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 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

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 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