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.
git clone --depth 1 https://github.com/TonyWu20/fortran-dev-pipelineWrote 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.
[](https://agentmods.dev/agents/tonywu20/fortran-dev-pipeline/plan-decomposer)<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.
<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>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 | $0.00365 | $0.05001 |
| Opus 5 | $0.00182 | $0.02500 |
| Sonnet 5 | $0.00073 | $0.01000 |
| Haiku 4.5 | $0.00036 | $0.00500 |
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.
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
- Read and deeply understand the full plan before producing any output.
- Identify all distinct units of work — modules, subroutines, derived types, tests, refactors, I/O changes, infrastructure changes, documentation.
- 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.
- Identify dependencies: for each task, determine which other tasks must be completed before it can begin (blocking dependencies) and which tasks it enables.
- Identify parallelizable tasks: highlight tasks with no mutual dependencies that can be executed concurrently by separate subagents.
- 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.
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.
- 9d ago First seen · 273 lines · 365 tokens per session scan A d2a9c076ee29
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
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.
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.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.