code-review

A checklist for reviewing existing Delphi code for correctness, security, performance, maintainability, and memory handling. It includes checks for edge cases, SQL injection, duplicated code, naming, and leaked objects.

In plain words
What is it for?
Use it when auditing Delphi files, diffs, or pull requests before merging changes.
Why use it?
It gives code reviews a consistent way to find bugs, unsafe input handling, slow database access, and cleanup problems.

Skill for Claude CodeCodex

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 skills/secondlifes/delphi-expert/code-review
Any agent
npx skills add SecondLifes/delphi-expert --skill code-review
Clone the repo
git clone --depth 1 https://github.com/SecondLifes/delphi-expert

Made for: Claude Code, Codex.

Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,049 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 95% copy Near-identical to another mod 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 $0.00060 $0.01049
Opus 5 $0.00030 $0.00524
Sonnet 5 $0.00012 $0.00210
Haiku 4.5 $0.00006 $0.00105

Measured 2d ago against content hash db65a053dd1b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-review 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.

Origin

This is a copy

95% identical to Delphi Code Review — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/code-review/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Delphi Code Review — Skill

Quick Checklist

Corretude

  • Code does what it's supposed to do
  • Edge cases handled (nil, empty list, zero value)
  • Error handling implemented with specific exceptions
  • No obvious bugs

Security

  • Parameterized SQL queries (without string concatenation)
  • Validated and sanitized input
  • No hardcoded credentials or passwords
  • No SQL injection via Format or concatenation in queries

Performance

  • No N+1 queries (avoid loop with query inside)
  • No unnecessary loops
  • Large objects released as early as possible
  • TObjectList with OwnsObjects configured correctly

Code Quality

  • Self-descriptive names following Pascal Guide
  • DRY — no duplicate code
  • SOLID — principles respected
  • Methods ≤ 20 lines
  • Guard clauses instead of deep nesting

Memory Management

  • try/finally with Free for temporary objects
  • Interfaces for automatic reference counting
  • Assigned() before accessing references that may be nil
  • Destructor Destroy with override freeing owned fields
  • No memory leaks in exception paths

Pascal Nomenclature

  • PascalCase for all identifiers
  • Prefix T in classes, I in interfaces, E in exceptions
  • Prefix F in private fields, A in parameters, L in local variables
  • Units: Projeto.Camada.Dominio.Funcionalidade.pas
  • Components: 3-letter prefix (btn, edt, lbl, etc.)

Tests

  • Unit tests for new code
  • Edge cases tested
  • Readable and maintainable tests

Documentation

  • XMLDoc for public methods and properties
  • Comments in Portuguese when necessary
  • Do not comment self-explanatory code

Anti-Patterns to Flag

//❌ Magic numbers
if ACustomer.Age > 18 then

//✅ Named constants
const MINIMUM_AGE = 18;
if ACustomer.Age > MINIMUM_AGE then

//❌ with statement
with AQuery do begin
  SQL.Text := '...';
  Open;
end;

//✅ Explicit reference
AQuery.SQL.Text := '...';
AQuery.Open;

//❌ Generic Catch
except
  on E: Exception do ShowMessage(E.Message);

//✅ Specific exceptions
except
  on E: EFDDBEngineException do
    raise EDatabaseException.Create('Falha: ' + E.Message);

//❌ Logic in OnClick
procedure TfrmMain.btnSaveClick(Sender: TObject);
begin
  //50 lines of business logic here
end;

//✅ Delegate for Service
procedure TfrmMain.btnSaveClick(Sender: TObject);
begin
  FService.SaveCustomer(GetFormData);
end;

// ❌ Memory leak
function GetItems: TStringList;
begin
  Result := TStringList.Create;
  LoadItems(Result); //if LoadItems throws exception, leak!
end;

//✅ Safe
function GetItems: TStringList;
begin
  Result := TStringList.Create;
  try
    LoadItems(Result);
  except
    Result.Free;
    raise;
  end;
end;

Read the full file on GitHub · 145 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. 2d ago First seen · 145 lines · 60 tokens per session scan A db65a053dd1b

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository SecondLifes/delphi-expert (3 stars, last pushed 22d ago), licensed MIT. It adds 60 tokens to every session and 1,049 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to Delphi Code Review, differing in 4 lines, and is treated as a copy.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens