Claude-Tools-for-Delphi: Skill for Claude Code

.claude/skills/light-code-ArchitectureClass/SKILL.md

light-code-ArchitectureClass is a skill for Claude Code from GabrielOnDelphi/Claude-Tools-for-Delphi. It costs 94 tokens per session (748 once invoked), scanned A, original, MPL-2.0.

A review tool for finding poorly shaped classes in Delphi projects, including forms. Delphi is a programming language and development environment; the tool looks for classes with too many responsibilities, misplaced behavior, or shared mutable state.

In plain words
What is it for?
Use it to audit for god classes, anemic data classes, oversized configuration records, singletons, or downcast-based holders, then consider suggestions such as extracting a class or moving a method.
Why use it?
It highlights design problems that can make code difficult to change or reason about. The tool reports and ranks possible reshaping ideas without altering the project.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is GabrielOnDelphi/Claude-Tools-for-Delphi's own configuration. It tells Claude Code how to work on Claude-Tools-for-Delphi itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Claude-Tools-for-Delphi configures →

Reuse

Borrowing it

Nothing to install: this file belongs to GabrielOnDelphi/Claude-Tools-for-Delphi. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/GabrielOnDelphi/Claude-Tools-for-Delphi/main/.claude/skills/light-code-ArchitectureClass/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/GabrielOnDelphi/Claude-Tools-for-Delphi

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 light-code-ArchitectureClass

README.md
[![agentmods](https://agentmods.dev/badge/skills/gabrielondelphi/claude-tools-for-delphi/light-code-architectureclass.svg)](https://agentmods.dev/skills/gabrielondelphi/claude-tools-for-delphi/light-code-architectureclass)
Your own site
<a href="https://agentmods.dev/skills/gabrielondelphi/claude-tools-for-delphi/light-code-architectureclass"><img src="https://agentmods.dev/badge/skills/gabrielondelphi/claude-tools-for-delphi/light-code-architectureclass.svg" alt="Measured on agentmods" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 748 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 $0.00094 $0.00748
Opus 5 $0.00047 $0.00374
Sonnet 5 $0.00019 $0.00150
Haiku 4.5 $0.00009 $0.00075

Measured 2d ago against content hash ab1318c4e0c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

light-code-ArchitectureClass 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.

.claude/skills/light-code-ArchitectureClass/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/light-code-ArchitectureClass — Find ill-shaped classes (launcher)

This skill is a thin launcher. The audit is done by the light-code-ArchitectureClass agent in its own context window, so the whole-project class read does not clog the main context — only the ranked report comes back. Do not map or analyse classes yourself; resolve the scope, then launch the agent.

When to run

  • User invokes /light-code-ArchitectureClass (with or without args).
  • User says variants: "is this a god class", "review the class design", "find anemic classes", "which classes carry too many responsibilities", "audit the class shapes".

If the real question is whether two units/files should merge, this is the wrong skill — point at /light-code-ArchitectureUnit.

Steps

  1. Resolve scope. From $args: a path, a folder, or several files. With no argument, the scope is the project's own app source classes under the project root, including form and frame classes. Pass --include-lightsaber through if the user gave it. You do not need to ask anything — the agent applies the skip rules (LightSaber, third-party, tests) itself.
  2. Launch the light-code-ArchitectureClass agent via the Agent tool with subagent_type: light-code-ArchitectureClass. Put the resolved scope (and any flags) in the prompt.
  3. Print the agent's returned report verbatim. It is already self-contained (ranked candidates + verdict line). Do not re-analyse or second-guess its verdicts.

The agent ALSO writes a self-contained HandOver.md to the project root automatically, so a fresh session can implement the reshapes from that file alone. Mention the path when you relay the report.

That's it. No mapping, no signal-walking, no edits in the skill itself.

Where the rules live (for the agent, not for you)

  • ../light-code-ArchitectureUnit/references/architecture-principles.md — the shared deep/shallow model, counter-analysis discipline, LightSaber boundary, risk flags (read by both this and the ArchitectureUnit agent).
  • The agent's own file (.claude/agents/light-code-ArchitectureClass.md) — the class-specific signals, anti-signals, procedure, report format, the mandatory HandOver.md write, and hard rules.

Read the full file on GitHub · 52 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 Changed · +2 lines ab1318c4e0c0
  2. 6d ago First seen · 50 lines · 94 tokens per session scan A 9cc101b6a47c

Subscribe to this mod's changes

light-code-ArchitectureClass is a skill published in the GitHub repository GabrielOnDelphi/Claude-Tools-for-Delphi (17 stars, last pushed yesterday), licensed MPL-2.0. It adds 94 tokens to every session and 748 once invoked, about $0.0005 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 2026-08-30.