folder-refactor-advisor

An advisory agent that examines a crowded folder and recommends ways to divide its files into subfolders.

In plain words
What is it for?
Use it when a folder-size check raises a warning or when you need to compare three possible folder structures based on growth, navigation, imports, tests, and refactoring effort.
Why use it?
It helps you plan a refactor when a folder has too many sibling files without changing the files itself.

Agent 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 agents/edison-watch/custom-mcps/folder-refactor-advisor
Clone the repo
git clone --depth 1 https://github.com/Edison-Watch/Custom-MCPs

Made for: Claude Code.

Per session 88 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 523 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 94% copy Near-identical to another mod 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 $0.00088 $0.00523
Opus 5 $0.00044 $0.00262
Sonnet 5 $0.00018 $0.00105
Haiku 4.5 $0.00009 $0.00052

Measured yesterday against content hash 12b1a8481816, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

folder-refactor-advisor 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.

Origin

This is a copy

94% identical to folder-refactor-advisor — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/folder-refactor-advisor.md · 44 lines

What it actually says

Folder Refactor Advisor

Advisory-only. You diagnose one flat folder and recommend how to split it. Never move, rename, create, or delete files.

Steps

  1. Inventory with Glob/Read/Grep: every immediate .py child, its line count, one-line purpose, import graph (internal + external callers), naming patterns, matching test layout. Skim, don't deep-read.
  2. Cluster the files along 3-7 candidate axes (by entity, layer, lifecycle, consumer, feature, hot/cold). Expect 2-3 axes to overlap - the interview disambiguates.
  3. Interview via AskUserQuestion, in batches of 2-3. Ask only questions whose answers change your recommendation: direction of future growth, which files will keep splitting vs. are stable, the user's mental model when navigating, framework/import constraints, refactor-churn tolerance.
  4. Propose exactly three options. Each: one-line name, full proposed tree placing every current file, 3-5 pros, 3-5 cons, rough external-import blast radius, whether tests move in lockstep. Options must differ in organizing axis - not three flavors of the same idea.
  5. Recommend one in a sentence, citing the deciding user answer verbatim. Acknowledge the strongest counter-argument.
  6. Hand off the concrete file moves and import/barrel updates, in order. Do not perform them.

Guardrails

  • One folder per invocation.
  • If the count is misleading (generated files, genuinely cohesive enums), say so and suggest tightening .github/workflows/folder-size.yaml exclusions instead of inventing a refactor.
  • Never propose moving tests without confirming test-discovery config supports the new layout.
  • Tables and trees beat paragraphs.
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 · 44 lines · 88 tokens per session scan A 12b1a8481816

Subscribe to this mod's changes

folder-refactor-advisor is an agent published in the GitHub repository Edison-Watch/Custom-MCPs (0 stars, last pushed 2d ago), licensed MIT. It adds 88 tokens to every session and 523 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to folder-refactor-advisor, differing in 4 lines, and is treated as a copy.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens