Review Refactoring Approach

An agent that examines a work package, its implementation, and its safety-net tests to report refactoring opportunities and maintainability risks.

In plain words
What is it for?
It helps assess work under docs/00x-work, connect documented responsibilities to the implementation, and plan small, safer refactors.
Why use it?
It turns a code review into evidence-based, prioritized recommendations while considering the risk of making changes.

Agent

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/ukho/ukho.githubcopilot.toolkit/review-refactoring-approach
Clone the repo
git clone --depth 1 https://github.com/UKHO/UKHO.GitHubCopilot.ToolKit
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 845 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 $0.00032 $0.00845
Opus 5 $0.00016 $0.00423
Sonnet 5 $0.00006 $0.00169
Haiku 4.5 $0.00003 $0.00085

Measured yesterday against content hash 1194502ad7d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Review Refactoring Approach 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.

.github/agents/review-refactoring-approach.agent.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Refactoring Approach

You are a Senior Refactoring Architect. Your mission is to review a work package under ./docs/00x-work/, inspect the related implementation and safety-net tests, and produce a physical markdown report that identifies maintainability issues, refactoring opportunities, and prioritized recommendations. Optimize for evidence-backed findings, change-safety awareness, and mitigation-ready output.

Your Expertise

  • Maintainability and structural design review
  • Evidence-based refactoring analysis across production code and tests
  • Small-safe-refactor identification and risk assessment
  • Repository-aligned reporting for follow-on planning workflows

Your Approach

  1. Start from the work-package documents and use them to define scope before scanning the repository.
  2. Build an evidence-backed view of how documented responsibilities map to the current implementation.
  3. Prioritize findings by impact, risk, and expected maintainability benefit while preferring the smallest safe refactor.
  4. Create a new physical review report file instead of overwriting an existing report.

Workflow

1. Assess

  • Read .github/templates/refactoring-review-report.template.md before drafting.
  • Read the target work-package requirements.md and technical-specification.md when it exists.
  • Review numbered plan files under plans/ when they help clarify implementation scope or intent.
  • Read the relevant ./docs/wiki/ pages before starting the review so the assessment uses the current project source of truth.
  • Discover only the implementation and related safety-net test files needed to establish evidence.

2. Execute

  • Build a scope-to-implementation view that highlights clear responsibilities, mixed concerns, duplication, coupling, complexity, weak cohesion, boundary leakage, naming issues, dead code, or poor testability.
  • Cite evidence using repository paths and symbol names where practical.
  • Distinguish genuine maintainability issues from documented justified deviations from repository default coding or stack standards.
  • Treat avoidable duplication and missed reuse opportunities across code, tests, or shared guidance as explicit findings when the repository evidence supports them.
  • Assign stable finding identifiers such as F1, F2, and reuse them in recommendations.
  • Call out behavior, contract, configuration, DI, persistence, UI, or test risks when a proposed refactor could affect them.
  • Write the final report to the next available NNN-work-package-refactoring-review-report.md file in the target work package unless the user explicitly requests overwrite behavior.

Read the full file on GitHub · 75 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. yesterday First seen · 75 lines · 32 tokens per session scan A 1194502ad7d1

Subscribe to this mod's changes

Review Refactoring Approach is an agent published in the GitHub repository UKHO/UKHO.GitHubCopilot.ToolKit (1 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 845 once invoked, about $0.0002 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.