decompose

A planning workflow that breaks a large body of work into small units that can be implemented, tested, reviewed, and shipped independently.

In plain words
What is it for?
Use it to map an epic, order its tasks into a dependency graph, define acceptance criteria, and check that the smaller units cover the full request.
Why use it?
It makes large projects easier to execute by exposing dependencies and separating work that can happen in parallel.

Command

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/sjarmak/coding-agent-workflows/decompose
Clone the repo
git clone --depth 1 https://github.com/sjarmak/coding-agent-workflows
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 403 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 $0.00019 $0.00403
Opus 5 $0.00010 $0.00201
Sonnet 5 $0.00004 $0.00081
Haiku 4.5 $0.00002 $0.00040

Measured yesterday against content hash ad20d454ccf6, 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 yesterday.

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.

targets/claude/commands/decompose.md · 51 lines

What it actually says

Workflow: Decompose

For work too large for one implement-review pass. Produces a dependency-ordered set of units, each small enough to implement and review on its own.

Inputs

Input Source Description
epic caller The large body of work to break down.
context caller Acceptance criteria, constraints, target architecture.

Steps

1. map

Read the epic and its acceptance criteria. Identify the natural seams, the points where work can be split so each piece is independently testable and reviewable. Split on reasons to change and on what can ship alone, not on line count.

Exit: a list of candidate units with one-line scopes.

2. order (needs: map)

Establish dependencies between units (which must land before which). Flag units that can run in parallel. Each unit should have its own acceptance criteria derived from the epic's.

Exit: a dependency-ordered (DAG) breakdown; parallelizable units marked.

3. review-decomposition (needs: order)

Review the breakdown itself as a gate: does the union of the units actually cover the epic's acceptance criteria? Are any units still too large to implement-review in one pass? Is any "unit" actually two reasons-to-change glued together? Reject and re-split if so. Where a multi-model runtime is available, dispatch review for an independent check; otherwise apply the coverage-and-sizing gate directly.

Exit: a breakdown whose units each fit one implement-review pass and whose union covers the epic.

Hand-off

Each resulting unit is then driven through the implement-review workflow, independently, in dependency order.

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. yesterday First seen · 51 lines · 19 tokens per session scan A ad20d454ccf6

Subscribe to this mod's changes

decompose is a command published in the GitHub repository sjarmak/coding-agent-workflows (2 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 403 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.