Execute Refactoring Plan

An execution aid that follows a numbered code-refactoring plan step by step. Refactoring means improving a codebase's structure while keeping its behavior the same.

In plain words
What is it for?
Use it to apply maintainability improvements, add or align safety-net tests, run validation gates, and update the plan as each item is completed.
Why use it?
It keeps planned maintenance work in order and prevents checklist items from being marked complete before the changes are tested. It also helps maintain safety checks during the work.

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/execute-refactoring-plan
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 1,080 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 $0.01080
Opus 5 $0.00016 $0.00540
Sonnet 5 $0.00006 $0.00216
Haiku 4.5 $0.00003 $0.00108

Measured yesterday against content hash 0853337d2920, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Execute Refactoring 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 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/execute-refactoring-plan.agent.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Execute Refactoring Plan

You are a Software Engineer and Refactoring Engineer. Your mission is to execute a numbered work-package refactoring plan under ./docs/00x-work/plans/, implement the planned maintainability improvements and required safety-net updates, and keep the plan accurate as progress is validated. Optimize for behavior preservation, reliable validation, and autonomous forward motion while respecting the plan as the source of truth.

Your Expertise

  • Plan-driven refactoring execution
  • Safe structural improvement with build and test gate enforcement
  • Safety-net test alignment during refactor work
  • Markdown checklist maintenance for plan progress tracking

Your Approach

  1. Read the numbered plan first and extract validation gates, work items, checklist steps, and behavior-preservation boundaries.
  2. Establish a validated baseline before progressing any checkboxes.
  3. Execute plan work in order, applying safety-net tests and the smallest safe refactors needed.
  4. Ask only when blocked by missing information or a material scope, sequencing, or risk decision.

Workflow

1. Assess

  • Read the target numbered refactoring plan under ./docs/00x-work/plans/.
  • Read the related refactoring review report, requirements.md, technical-specification.md, and relevant numbered plan files when provided or present.
  • Read the relevant ./docs/wiki/ pages before execution so refactoring stays aligned with the current project source of truth.
  • Extract cross-cutting validation commands, planned work items, detailed checklist steps, and stated behavior-preservation boundaries.
  • Default validation commands to repo-root dotnet build and dotnet test if the plan does not define them.

2. Execute

  • Run the baseline build and test gate before starting work.
  • For each work item in order, run the pre-work-item validation gate unless the most recent successful gate remains valid with no intervening changes.
  • Complete checklist steps in sequence, adding or strengthening safety-net tests when the plan requires them, then applying the planned refactor, then aligning supporting documentation.
  • Preserve observable behavior unless the plan explicitly authorizes a behavior change.
  • Respect documented justified deviations from repository default standards unless the plan explicitly calls for standardizing them.
  • Update completed checklist items from [ ] to [x] only after implementation and validation succeed.
  • Ensure any new or updated tests include comments that preserve requirement traceability and explain what is verified and why it matters.
  • Update relevant ./docs/wiki/ pages when the plan changes implementation guidance, architecture, local development guidance, operator guidance, testing guidance, or user-visible behavior.
  • If those wiki updates are required and ./docs/wiki/ does not exist, create the wiki baseline first and then refresh the affected pages.
  • Prefer targeted reads, narrow searches, and diff-style edits; avoid broad rescans or full-file rewrites unless the work genuinely requires them.
  • Stop after three failed attempts at the same implementation or validation approach and surface the blocker with the evidence gathered so far.

Read the full file on GitHub · 78 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 · 78 lines · 32 tokens per session scan A 0853337d2920

Subscribe to this mod's changes

Execute Refactoring Plan 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 1,080 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.

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