plan-decomposer

plan-decomposer is an agent for Claude Code from TonyWu20/fortran-dev-pipeline. It costs 365 tokens per session (5,001 once invoked), scanned A, original, MIT.

An agent that breaks a Fortran scientific-software implementation plan into separate tasks for other agents. Fortran is a programming language often used for scientific and numerical computing.

In plain words
What is it for?
Use it to divide a CASTEP feature plan into delegatable work covering code, tests, input/output, refactoring, documentation, and infrastructure.
Why use it?
It prevents unrelated work from being mixed into one task and makes dependencies between tasks explicit. The input specifically targets CASTEP modules, a scientific software codebase.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions CLAUDE.md; mentions subagents.

Part of the fortran-dev-pipeline plugin — 7 skills, 6 agents, 2 hooks shipped together

Good fit Use it to divide a CASTEP feature plan into delegatable work covering code, tests, input/output, refactoring, documentation, and infrastructure.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/tonywu20/fortran-dev-pipeline/plan-decomposer
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/TonyWu20/fortran-dev-pipeline

Made for: Claude Code.

Or install fortran-dev-pipeline, the plugin that ships this one along with the rest of its 7 skills, 6 agents, 2 hooks.

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 plan-decomposer

README.md
[![agentmods](https://agentmods.dev/badge/agents/tonywu20/fortran-dev-pipeline/plan-decomposer/github.svg)](https://agentmods.dev/agents/tonywu20/fortran-dev-pipeline/plan-decomposer)
Your own site
<a href="https://agentmods.dev/agents/tonywu20/fortran-dev-pipeline/plan-decomposer"><img src="https://agentmods.dev/badge/agents/tonywu20/fortran-dev-pipeline/plan-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.

agentmods 80×15 button for plan-decomposer

Your own site · 80×15
<a href="https://agentmods.dev/agents/tonywu20/fortran-dev-pipeline/plan-decomposer"><img src="https://agentmods.dev/badge/agents/tonywu20/fortran-dev-pipeline/plan-decomposer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 365 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,001 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00365 $0.05001
Opus 5 $0.00182 $0.02500
Sonnet 5 $0.00073 $0.01000
Haiku 4.5 $0.00036 $0.00500

Measured 9d ago against content hash d2a9c076ee29, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

plan-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 9d 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.

agents/plan-decomposer.md · 273 lines

How it starts

The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert scientific software project planner specializing in Fortran codebases (DFT, EDFT, numerical methods). You decompose complex plans into well-scoped, delegatable subtasks applying the Single Responsibility Principle at the task level — ensuring each delegated unit of work has exactly one clearly defined concern and one reason to change.

Your primary input is a plan file provided by the user. You will also consider any project context available (e.g., CLAUDE.md, codebase structure, architecture documentation) to produce accurate, grounded decompositions.

Core Responsibilities

  1. Read and deeply understand the full plan before producing any output.
  2. Identify all distinct units of work — modules, subroutines, derived types, tests, refactors, I/O changes, infrastructure changes, documentation.
  3. Apply SRP at the task level: each task should correspond to a single, coherent concern. A task should not mix, for example, adding a new subroutine AND writing its tests AND updating its caller — these are separate responsibilities.
  4. Identify dependencies: for each task, determine which other tasks must be completed before it can begin (blocking dependencies) and which tasks it enables.
  5. Identify parallelizable tasks: highlight tasks with no mutual dependencies that can be executed concurrently by separate subagents.
  6. Produce a structured, actionable output as described below.

Project Context Awareness

If a CLAUDE.md or memory context is available, use it to:

  • Align task boundaries with the project's module/file structure.
  • Respect stated architectural patterns (e.g., TDD: separate "write failing test" tasks from "implement" tasks).
  • Use correct terminology and file paths from the project.
  • Flag any plan items that may conflict with established conventions.

Read any available CLAUDE.md files and project documentation to understand module structure, required patterns, build system (Make/CMake/fpm), testing approach (pFUnit, standalone test programs), and file placement conventions before producing the task breakdown.

Read the full file on GitHub · 273 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. 9d ago First seen · 273 lines · 365 tokens per session scan A d2a9c076ee29

Subscribe to this mod's changes

plan-decomposer is an agent published in the GitHub repository TonyWu20/fortran-dev-pipeline (5 stars, last pushed 4mo ago), licensed MIT. It adds 365 tokens to every session and 5,001 once invoked, about $0.0018 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.