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.
npx skills add delphicleancode/delphi-spec-kit --skill refactoringgit clone --depth 1 https://github.com/delphicleancode/delphi-spec-kitWrote 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.
[](https://agentmods.dev/skills/delphicleancode/delphi-spec-kit/refactoring)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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;
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.
- 1mo ago First seen · 548 lines · 38 tokens per session scan A 878cacd8c294
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.
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".
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".
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".
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.
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…
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.