refactoring-economics
v0.1.1Refactor agent-maintained code where it measurably lowers what coding agents spend on future changes: git-hotspot targeting with agent share, a repeated-run token measurement harness over the agent's own usage stream, Fowler-catalog refactorings ordered by what shrinks the read set, tool-driven execution with a per-step gate, and a break-even model priced per token class with a safety factor.
By WebgripLicense: MIT0 GitHub starsUpdated 3 days ago
Directory evidence
- Runtimes
- Claude Code
- Parsed components
- 1 skill or MCP entry
- Source updated
- Oct 4, 2026
- Manifest status
- Canonical path parsed
The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →
Install refactoring-economics for Claude Code
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install refactoring-economics@agent-plugin-marketplacePaste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.
The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.
Get the source manually
git clone https://github.com/webgrip/ai-skillsClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is skills/refactoring-economics/.
Plugin files
├── .claude-plugin/plugin.json└── SKILL.md
Included Skills1
Refactors and splits agent-maintained code so coding agents spend fewer tokens on future changes, and proves it - git-hotspot targeting with agent share, a repeated-run harness that measures the same change before and after from the agent's own usage stream, Fowler-catalog refactorings ordered by what shrinks the agent's read set, tool-driven execution with a per-step gate, and a break-even model per token class. Use when agents burn tokens or keep re-reading a large file; when asked to split a big file or class so agents spend less; whether refactoring will cut agent token cost or pay for itself; to measure what a change costs an agent before and after a refactoring; which files or modules to refactor first so AI agents spend fewer tokens; to reproduce the martinfowler.com refactoring-economic-benefit experiment; or to plan refactoring an AI-built codebase. Not for behaviour changes or general code review.
Plugin manifests1
{
"name": "refactoring-economics",
"displayName": "Refactoring Economics",
"description": "Refactor agent-maintained code where it measurably lowers what coding agents spend on future changes: git-hotspot targeting with agent share, a repeated-run token measurement harness over the agent's own usage stream, Fowler-catalog refactorings ordered by what shrinks the read set, tool-driven execution with a per-step gate, and a break-even model priced per token class with a safety factor.",
"version": "0.1.1",
"license": "MIT",
"author": {
"name": "Webgrip",
"url": "https://forgejo.webgrip.dev/webgrip"
},
"keywords": [
"refactoring",
"technical-debt",
"token-cost",
"agentic-coding",
"claude-code",
"hotspots",
"measurement",
"roi",
"code-health",
"fowler"
],
"homepage": "https://forgejo.webgrip.dev/webgrip/ai-skills/src/branch/main/skills/refactoring-economics",
"repository": "https://forgejo.webgrip.dev/webgrip/ai-skills"
}For maintainers
If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.
[refactoring-economics on Agent Plugins Marketplace](https://pluginsmp.com/plugins/refactoring-economics)