decompose

A command that splits a large GitHub issue—the project’s tracked work request—into smaller sub-issues.

In plain words
What is it for?
It is for reading an issue, examining the affected code, finding natural boundaries, and proposing two to five independently workable tasks.
Why use it?
It makes work easier to plan and assign when one issue covers several components, requirements, or kinds of work.

Command for Claude Code

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 commands/fotoetienne/gru/decompose
Clone the repo
git clone --depth 1 https://github.com/fotoetienne/gru

Made for: Claude Code.

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,069 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 $0.00013 $0.01069
Opus 5 $0.00006 $0.00535
Sonnet 5 $0.00003 $0.00214
Haiku 4.5 $0.00001 $0.00107

Measured 2d ago against content hash 8b4845461cbc, 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/commands/decompose.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Break a complex GitHub issue into smaller, manageable sub-issues.

Issue: $ARGUMENTS

Workflow:

1. Fetch & Analyze the Issue

  • Use gh issue view $ARGUMENTS to get the full issue details
  • Read the issue title, body, labels, and any comments
  • Understand the full scope of what needs to be done

2. Assess Complexity

Analyze whether the issue should be decomposed:

  • Does it involve multiple distinct components or systems?
  • Does it have multiple acceptance criteria or requirements?
  • Would it take more than a few hours to complete in one go?
  • Does it mix different types of work (e.g., backend + frontend + docs)?

If the issue is straightforward and focused, inform the user that decomposition isn't needed.

3. Explore the Codebase

  • Use the Task tool with subagent_type='Explore' to understand:
    • What code/files are affected by this issue
    • Existing architecture and patterns
    • Dependencies between components
  • This helps identify natural boundaries for breaking up the work

4. Propose Decomposition Plan

  • Create a list of 2-5 smaller sub-issues that:
    • Are independently implementable (minimize dependencies)
    • Each have clear, testable outcomes
    • Follow a logical implementation order
  • Use TodoWrite to present the proposed breakdown
  • Each todo should describe a potential sub-issue with:
    • Clear title (what it does)
    • Brief description (why it's separate)
    • Dependencies (if any)

5. Get User Approval

  • Use AskUserQuestion to confirm:
    • Should we proceed with decomposition?
    • Does the proposed breakdown make sense?
    • Any adjustments needed?

6. Create Sub-Issues

For each approved sub-issue:

  • Use gh issue create with:
    • Clear, specific title
    • Body that includes:
      • Description: What this sub-issue addresses
      • Parent Issue: "Part of #"
      • Blocked by: #X, #Y (links to prerequisite sub-issues if order matters, using the **Blocked by:** #X, #Y convention)
      • Code Areas: File/module references
    • Labels: Copy from parent + add subtask if available
  • Capture the new issue numbers

Read the full file on GitHub · 109 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 · 109 lines · 13 tokens per session scan A 8b4845461cbc

Subscribe to this mod's changes

decompose is a command published in the GitHub repository fotoetienne/gru (11 stars, last pushed 25d ago), licensed Apache-2.0. It adds 13 tokens to every session and 1,069 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 2026-08-30.