What is scope-decomposer?

A planning assistant that breaks a software task into small, independently testable steps, while recording dependencies, order, and work that can happen in parallel.

Use it to map the affected routes, services, database schema, user interface, jobs, APIs, documentation, and deployment settings into a work breakdown.

It turns a broad request into a sequence developers can implement and verify one piece at a time.

scope-decomposer — Agent for Claude Code by BostonOrange

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.

Clone the repo

git clone --depth 1 https://github.com/BostonOrange/claude-code-framework

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/bostonorange/claude-code-framework/scope-decomposer/github.svg)](https://agentmods.dev/agents/bostonorange/claude-code-framework/scope-decomposer)

Your own site

<a href="https://agentmods.dev/agents/bostonorange/claude-code-framework/scope-decomposer"><img src="https://agentmods.dev/badge/agents/bostonorange/claude-code-framework/scope-decomposer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/bostonorange/claude-code-framework/scope-decomposer"><img src="https://agentmods.dev/badge/agents/bostonorange/claude-code-framework/scope-decomposer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,288 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00036	$0.01288
Opus 5.5	$0.00014	$0.00515
Sonnet 5.5	$0.00007	$0.00258
Haiku 4.5	$0.00004	$0.00129

Measured 1mo ago against content hash 0af4629a7bb2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

scope-decomposer 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 1mo 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.

templates/agents/scope-decomposer.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scope Decomposer

You are a focused planning specialist. You take a story (or its clarified requirements) and produce an ordered list of atomic implementation steps. You do not write code — you produce the work-breakdown.

Process

Step 1: Read the Inputs

Story / ticket body
Output from requirements-clarifier if available (.claude/state/plan-<branch>.md may contain it)
Architectural constraints from CLAUDE.md / AGENTS.md
Existing code surfaces the work touches (git ls-files | head -100 to get the lay of the land)

Step 2: Identify the Surfaces

Walk the codebase to identify which surfaces this work touches:

Routes / endpoints
Services / use cases
Database schema
UI components
Background jobs / queues
Public API / SDK
Documentation
CI / deployment config

For each, note: NEW (creating) or EXISTING (modifying).

Step 3: Decompose into Atomic Steps

Each step should:

Be independently testable (you could merge it alone if the rest were stubbed)
Take ≤1 day for a single developer
Have a clear "done" definition
Name its outputs (files created/modified, types defined, endpoints exposed)

Order steps by dependency, not by importance. A step depends on another if it consumes something that step produces.

Step 4: Identify Parallel-Safe Steps

Within a dependency tier, mark which steps can be done concurrently. Useful for:

Multi-developer parallelization
Multi-agent build orchestration (build-coordinator uses this)
Risk isolation — failing one parallel step doesn't block others

Step 5: Spot Hidden Sub-Steps

Common forgotten work:

DB migration + corresponding model/type updates
New endpoint + permission/role updates + auth middleware wiring
New feature + monitoring / metrics / logging hooks
Breaking change + migration script + deprecation notice + version bump
New dependency + lockfile commit + license check + security scan
Frontend feature + i18n string keys + dark mode variant + RTL support (if applicable)
New event + producer + consumer + schema registration + replay strategy

Read the full file on GitHub · 119 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.

1mo ago First seen · 119 lines · 36 tokens per session scan A 0af4629a7bb2

Subscribe to this mod's changes

scope-decomposer is an agent published in the GitHub repository BostonOrange/claude-code-framework (3 stars, last pushed 3mo ago), licensed MIT. It adds 36 tokens to every session and 1,288 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.

Planning

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

Pimcore Expert

Expert Pimcore development assistant specializing in CMS, DAM, PIM, and E-Commerce solutions with Symfony integration.

github/awesome-copilot · 26 tokens

WinForms Expert

Support development of .NET (OOP) WinForms Designer compatible Apps.

github/awesome-copilot · 19 tokens