Delphi Code Refactoring

Delphi Code Refactoring is a skill for Claude Code from delphicleancode/delphi-spec-kit. It costs 38 tokens per session (3,756 once invoked), scanned A, original, MIT.

A set of techniques for reorganising Object Pascal code without changing what the program does. Refactoring makes code easier to read and maintain, while code smells are signs that its structure may cause problems.

In plain words
What is it for?
Use it to split long methods, add guard clauses, improve class designs, review code smells, or prepare difficult code for testing.
Why use it?
It helps reduce confusing or overly long code and prepares older code for new features while preserving its existing behaviour.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to split long methods, add guard clauses, improve class designs, review code smells, or prepare difficult code for testing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/delphicleancode/delphi-spec-kit/refactoring
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.

Any agent
npx skills add delphicleancode/delphi-spec-kit --skill refactoring
Clone the repo
git clone --depth 1 https://github.com/delphicleancode/delphi-spec-kit

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for Delphi Code Refactoring

README.md
[![agentmods](https://agentmods.dev/badge/skills/delphicleancode/delphi-spec-kit/refactoring/github.svg)](https://agentmods.dev/skills/delphicleancode/delphi-spec-kit/refactoring)
Your own site
<a href="https://agentmods.dev/skills/delphicleancode/delphi-spec-kit/refactoring"><img src="https://agentmods.dev/badge/skills/delphicleancode/delphi-spec-kit/refactoring/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for Delphi Code Refactoring

Your own site · 80×15
<a href="https://agentmods.dev/skills/delphicleancode/delphi-spec-kit/refactoring"><img src="https://agentmods.dev/badge/skills/delphicleancode/delphi-spec-kit/refactoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,756 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00038 $0.03756
Opus 5.5 $0.00015 $0.01502
Sonnet 5.5 $0.00008 $0.00751
Haiku 4.5 $0.00004 $0.00376

Measured 1mo ago against content hash 878cacd8c294, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Delphi Code Refactoring 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 1mo 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.

.claude/skills/refactoring/SKILL.md · 548 lines

How it starts

The opening of the file, as written. The whole thing — 548 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Delphi Code Refactoring — Skill

Use this skill when the user requests refactoring, code review or removal of code smells in Object Pascal. Refactoring never changes observable behavior — it only improves the internal structure of the code.

When to Use

  • User asks to "improve", "clean up" or "refactor" existing code
  • When reviewing code and finding code smells
  • When preparing legacy code to receive new functionality
  • Before adding tests to untestable code
  • When answering "why is this code difficult to understand?"

Fundamental Principle

"Refactoring is the art of changing the structure of code without changing its behavior." Always write (or check for) tests before refactoring.


📋 Catalog of Code Smells and Techniques

1. Extract Method — Long Method

Detect: Method with more than 20 lines or that needs comments to explain blocks.

Before:

procedure TInvoiceService.GenerateInvoice(AOrder: TOrder);
var
  LTax, LSubtotal, LTotal: Currency;
  LItem: TOrderItem;
  LLines: TStringList;
begin
  //Calculate subtotal
  LSubtotal := 0;
  for LItem in AOrder.Items do
    LSubtotal += LItem.UnitPrice * LItem.Quantity;

  //Calculates tax
  if AOrder.IsExempt then LTax := 0
  else LTax := LSubtotal * 0.12;

  LTotal := LSubtotal + LTax;

  //Generates report lines
  LLines := TStringList.Create;
  try
    LLines.Add('NOTA FISCAL');
    LLines.Add(Format('Cliente: %s', [AOrder.Customer.Name]));
    for LItem in AOrder.Items do
      LLines.Add(Format('  %s x%d = R$%.2f',
        [LItem.Product.Name, LItem.Quantity, LItem.UnitPrice * LItem.Quantity]));
    LLines.Add(Format('Total: R$%.2f', [LTotal]));
    LLines.SaveToFile(AOrder.InvoicePath);
  finally
    LLines.Free;
  end;
end;

After:

procedure TInvoiceService.GenerateInvoice(AOrder: TOrder);
var
  LSubtotal, LTax: Currency;
begin
  LSubtotal := CalculateSubtotal(AOrder);
  LTax      := CalculateTax(AOrder, LSubtotal);
  SaveInvoiceFile(AOrder, LSubtotal + LTax);
end;

function TInvoiceService.CalculateSubtotal(AOrder: TOrder): Currency;
var LItem: TOrderItem;
begin
  Result := 0;
  for LItem in AOrder.Items do
    Result := Result + (LItem.UnitPrice * LItem.Quantity);
end;

function TInvoiceService.CalculateTax(AOrder: TOrder; ASubtotal: Currency): Currency;
const
  STANDARD_TAX_RATE = 0.12;
begin
  if AOrder.IsExempt then Result := 0
  else Result := ASubtotal * STANDARD_TAX_RATE;
end;

procedure TInvoiceService.SaveInvoiceFile(AOrder: TOrder; ATotal: Currency);
var
  LLines: TStringList;
  LItem: TOrderItem;
begin
  LLines := TStringList.Create;
  try
    LLines.Add('NOTA FISCAL');
    LLines.Add(Format('Cliente: %s', [AOrder.Customer.Name]));
    for LItem in AOrder.Items do
      LLines.Add(Format('  %s x%d = R$%.2f',
        [LItem.Product.Name, LItem.Quantity, LItem.UnitPrice * LItem.Quantity]));
    LLines.Add(Format('Total: R$%.2f', [ATotal]));
    LLines.SaveToFile(AOrder.InvoicePath);
  finally
    LLines.Free;
  end;
end;

Read the full file on GitHub · 548 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. 1mo ago First seen · 548 lines · 38 tokens per session scan A 878cacd8c294

Subscribe to this mod's changes

Delphi Code Refactoring is a skill published in the GitHub repository delphicleancode/delphi-spec-kit (56 stars, last pushed 6mo ago), licensed MIT. It adds 38 tokens to every session and 3,756 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.

Related

Other skills, from other repositories

audit-pr

Audit a whole PR against the delivery contract and return MERGE-READY or evidenced blockers with the full URL. Consumes the current review-change REVIEW-PASS receipt instead of re-running review axes; posts a SHA-bound ready comment; never edits or merges. Triggers: "audit-pr", "is this PR ready", "merge gate".

gtrabanco/agentic-workflow · 71 tokens

fold-findings

Repair persisted fix-now findings in compatible atomic batches: root-cause fixes, green gate, commit/push, and per-row folded: yes updates. Never reclassify or substitute backlog notes. Triggers: "fold-findings", "fix the review findings", "repair audit blockers".

gtrabanco/agentic-workflow · 65 tokens

review-change

Review a change with only applicable internal axes, classify every finding, persist fix-now work, and return one evidence-backed decision. Findings only; --adversarial N uses isolated reviewers; --synthesize fuses supplied reviewer tables. Triggers: "review-change", "review this change", "adversarial review".

gtrabanco/agentic-workflow · 67 tokens

review-perf

Internal performance review pass of the agentic-workflow review pack — composed in-turn by review-change and product-audit; not a menu entry. Checks the changed paths for algorithmic and resource regressions: N+1s, hot-path allocations, asset weight, and leaks. Findings only; never edits code.

gtrabanco/agentic-workflow · 67 tokens

review-code

Internal correctness + simplification review pass of the agentic-workflow review pack — composed in-turn by review-change and product-audit; not a menu entry. Checks correctness, error handling, duplication, dead code, and simplification opportunities against the project's own conventions. Findings only; never edits…

gtrabanco/agentic-workflow · 63 tokens

review-debt

Internal tech-debt transform pass of the agentic-workflow review pack — composed in-turn by review-change and product-audit; not a menu entry. Transforms the synthesized findings table into explicit debt items, each with a re-trigger condition; it does not rescan the diff. Findings only; never edits code.

gtrabanco/agentic-workflow · 68 tokens