Claude-Tools-for-Delphi: Agent for Claude Code

.claude/agents/light-code-StyleChecker.md

light-code-StyleChecker is an agent for Claude Code from GabrielOnDelphi/Claude-Tools-for-Delphi. It costs 50 tokens per session (4,009 once invoked), scanned A, original, MPL-2.0.

A code-review agent for imported or third-party Delphi source files such as Pascal, form, project, and package files. It checks style, common mistakes, resource handling, unsafe casts, and missing cleanup, then applies specified formatting fixes.

In plain words
What is it for?
Use it to scan imported Delphi code, apply the required LightSaber formatting, and produce a severity-ranked report of dangerous patterns and other issues.
Why use it?
It catches risks in external code before it is brought into a project and makes that code follow the project's local conventions. It is intentionally not meant for reviewing the project's own code.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; 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/agents/light-code-StyleChecker.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/agents/gabrielondelphi/claude-tools-for-delphi/light-code-stylechecker/github.svg)](https://agentmods.dev/agents/gabrielondelphi/claude-tools-for-delphi/light-code-stylechecker)
Your own site
<a href="https://agentmods.dev/agents/gabrielondelphi/claude-tools-for-delphi/light-code-stylechecker"><img src="https://agentmods.dev/badge/agents/gabrielondelphi/claude-tools-for-delphi/light-code-stylechecker/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 light-code-StyleChecker

Your own site · 80×15
<a href="https://agentmods.dev/agents/gabrielondelphi/claude-tools-for-delphi/light-code-stylechecker"><img src="https://agentmods.dev/badge/agents/gabrielondelphi/claude-tools-for-delphi/light-code-stylechecker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,009 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 $0.00050 $0.04009
Opus 5.5 $0.00020 $0.01604
Sonnet 5.5 $0.00010 $0.00802
Haiku 4.5 $0.00005 $0.00401

Measured 2mo ago against content hash c3081de1041e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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/agents/light-code-StyleChecker.md · 326 lines

How it starts

The opening of the file, as written. The whole thing — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.

IMPORTANT: This agent is for reviewing IMPORTED or 3RD-PARTY code only. Do NOT use it for our own project code — our code is already clean and this agent's analysis is too superficial for deep reviews. For our own code, use "light-review-Full" instead.

Step 0 — Read Project Conventions First

Before scanning, look for a CLAUDE.md in the project directory (and parents) and read it — imported code must conform to its conventions.

Your Mission

You are a Delphi code-quality auditor. Analyze imported pas/dfm/dpr/dpk source for style violations and dangerous patterns (resource leaks, unsafe casts, missing try/finally), and produce a severity-ranked report that fixes the most critical issues first.

Mandatory Reformatting — apply these, don't just flag them

Beyond the severity-ranked findings below, you also bring imported code into our house style. These transformations (§1–§8) are applied directly (Edit the file), then noted in a short "Reformatting applied" block at the top of your report. They are not optional suggestions.

1. Unit header (LightSaber format)

Every .pas file must start with a header comment box, exactly in the shape used by C:\Projects\LightSaber\LightCore.pas. If a file has no such header, add one. If it already has a usable header, leave it.

Shape (reuse the exact 110-char rule lines from LightCore.pas — { + 109 = on top, 110 - for the separator, 109 = + } to close):

unit Some.Unit;

{=============================================================================================================
   2026.06.13
   www.GabrielMoraru.com
--------------------------------------------------------------------------------------------------------------
   - One line on what this unit does
   - A second line if needed
=============================================================================================================}

interface

Careful when converting (* … *) to { … } or the reverse. A { } comment self-terminates at the first }, so flipping a header that contains JSON braces or a {$…} directive to { } breaks the compile (E2029/E2038/E2052). If a 3rd-party header already uses (* *), leave it (* *). When adding a brand-new header to a file that has none, use (* *) if the description text could contain {, }, or $; otherwise { } is fine. This matches the project rule: headers with braces/directives use (* *).

Read the full file on GitHub · 326 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. 2mo ago First seen · 326 lines · 50 tokens per session scan A c3081de1041e

Subscribe to this mod's changes

light-code-StyleChecker is an agent published in the GitHub repository GabrielOnDelphi/Claude-Tools-for-Delphi (23 stars, last pushed 28d ago), licensed MPL-2.0. It adds 50 tokens to every session and 4,009 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 agents, from other repositories

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

thermo-nuclear-code-quality-review-subagent

Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.

michael-denyer/pstack-claude · 68 tokens

review-obsidian-guidelines

Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.

uphy/obsidian-reminder · 63 tokens

karimo-implementer

Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.

opensesh/KARIMO · 49 tokens

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens