refactor-plan

A step-by-step plan for restructuring code or system design while keeping its behavior unchanged. It covers testing, smaller phases, and ways to recover if a phase fails.

In plain words
What is it for?
Use it before changes such as separating a monolith, upgrading a framework, or extracting a service.
Why use it?
It turns a complex refactoring into reviewable, verifiable work and reduces the risk of breaking the application.

Command

Part of the codebase-maintenance plugin — 8 skills, 4 commands, 3 agents shipped together

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 commands/yeaight7/agent-powerups/refactor-plan
Clone the repo
git clone --depth 1 https://github.com/yeaight7/agent-powerups

Or install codebase-maintenance, the plugin that ships this one along with the rest of its 8 skills, 4 commands, 3 agents.

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 198 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00018 $0.00198
Opus 5 $0.00009 $0.00099
Sonnet 5 $0.00004 $0.00040
Haiku 4.5 $0.00002 $0.00020

Measured 2d ago against content hash de9e599ac67b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

refactor-plan 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 2d 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.

plugins/codebase-maintenance/commands/refactor-plan.md · 21 lines

What it actually says

Refactoring Plan

You are a senior software architect. Draft a comprehensive, step-by-step plan for refactoring the requested code or architecture.

Target

$ARGUMENTS

Planning Requirements

  1. Goal Definition: Clarify the end state of the refactoring (e.g., decoupling a monolith, upgrading a core framework, extracting a service).
  2. Safety Net: Define the testing strategy required before any code is modified.
  3. Execution Phases: Break the refactoring into isolated, verifiable phases. Each phase must leave the system in a deployable state.
  4. Rollback Strategy: Provide a clear rollback or fallback mechanism for each phase in case of unexpected failures.

Do not write the final refactored code yet. Focus exclusively on delivering a structured, low-risk execution plan that a developer can follow systematically.

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. 2d ago First seen · 21 lines · 18 tokens per session scan A de9e599ac67b

Subscribe to this mod's changes

refactor-plan is a command published in the GitHub repository yeaight7/agent-powerups (6 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 18 tokens to every session and 198 once invoked, about $0.0001 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.