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

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

light-code-StyleChecker is a skill for Claude Code from GabrielOnDelphi/Claude-Tools-for-Delphi. It costs 65 tokens per session (797 once invoked), scanned A, original, MPL-2.0.

A checker for imported Delphi source code, looking for style violations, common mistakes, and risky patterns such as resource leaks, unsafe type conversions, or missing cleanup.

In plain words
What is it for?
Scanning selected Delphi files or folders from external libraries and reporting issues for the user to inspect.
Why use it?
Third-party code can contain problems that are easy to miss, while a full review may be unnecessary. This gives that code a focused audit.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

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-StyleChecker/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-StyleChecker

README.md
[![agentmods](https://agentmods.dev/badge/skills/gabrielondelphi/claude-tools-for-delphi/light-code-stylechecker.svg)](https://agentmods.dev/skills/gabrielondelphi/claude-tools-for-delphi/light-code-stylechecker)
Your own site
<a href="https://agentmods.dev/skills/gabrielondelphi/claude-tools-for-delphi/light-code-stylechecker"><img src="https://agentmods.dev/badge/skills/gabrielondelphi/claude-tools-for-delphi/light-code-stylechecker.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 797 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 $0.00065 $0.00797
Opus 5 $0.00032 $0.00398
Sonnet 5 $0.00013 $0.00159
Haiku 4.5 $0.00006 $0.00080

Measured 4d ago against content hash ee3e8a133f24, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

light-code-StyleChecker 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 4d 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-StyleChecker/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/light-code-StyleChecker — 3rd-party Code Style Audit

This is a thin launcher. Your only job is to resolve the input scope and launch the light-code-StyleChecker agent. You do NOT review code yourself.

Scope reminder: this skill is for IMPORTED / 3RD-PARTY Delphi code only. For our own project code, the right tool is /light-review-Full (deeper, real correctness review). If the user points this at our own code, say so and suggest /light-review-Full — then proceed only if they confirm.

Step 1 — Resolve the input

The argument is in $args. The user may pass a single .pas file, a folder, or several files. Build the scan set:

  • One or more explicit file paths → use them as-is.
  • A folder → Glob <folder>/**/*.pas for the file list. If the result is large (more than ~25 files), tell the user the count and ask whether to scan all or narrow the scope.
  • No argument → ask the user which imported file or folder to scan. Do NOT default to the whole repository, and do NOT fall back to git status — 3rd-party code is usually already committed, so a git-diff scope would miss it.

Print the resolved scan set as a short list before launching, so the user can see the scope.

Step 2 — Launch the agent

Call the Agent tool with subagent_type: "light-code-StyleChecker". Pass it the full scan set in one prompt. Tell it plainly that this is imported / 3rd-party code to audit for style compliance, common mistakes, and dangerous patterns.

The agent reads the project CLAUDE.md for conventions, scans the files, reports findings, and applies the safe fixes it is confident about. It also applies four mandatory reformatting passes on imported code: a LightSaber-format unit header, Embarcadero keyword casing, if/then/else layout, and no line wrapping. Relay its final report to the user — do not re-derive or second-guess it.

Step 3 — Summary

Print a short summary (the agent's full report is already in the transcript — do not re-paste it): how many files scanned, how many issues found, how many fixed vs. flagged for a human decision.

Read the full file on GitHub · 61 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. 4d ago Changed · +2 lines ee3e8a133f24
  2. 8d ago First seen · 59 lines · 65 tokens per session scan A 38150e7f499d

Subscribe to this mod's changes

light-code-StyleChecker is a skill published in the GitHub repository GabrielOnDelphi/Claude-Tools-for-Delphi (17 stars, last pushed yesterday), licensed MPL-2.0. It adds 65 tokens to every session and 797 once invoked, about $0.0003 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.