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

.claude/skills/light-review-Full/SKILL.md

light-review-Full is a skill for Claude Code from GabrielOnDelphi/Claude-Tools-for-Delphi. It costs 103 tokens per session (4,030 once invoked), scanned A, original, MPL-2.0.

A three-stage Delphi code-review process that finds bugs, rechecks the findings, verifies the fixes, and compiles the project. Delphi is a programming language.

In plain words
What is it for?
Use it for a full review of Delphi files or a project when you want findings, fixes, verification, compilation, documentation checks, and a recorded review result.
Why use it?
The staged process filters out false positives and checks that accepted fixes work, while also checking documentation for claims that became outdated.

Skill for Claude Code

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

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-review-Full/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-review-Full

README.md
[![agentmods](https://agentmods.dev/badge/skills/gabrielondelphi/claude-tools-for-delphi/light-review-full/github.svg)](https://agentmods.dev/skills/gabrielondelphi/claude-tools-for-delphi/light-review-full)
Your own site
<a href="https://agentmods.dev/skills/gabrielondelphi/claude-tools-for-delphi/light-review-full"><img src="https://agentmods.dev/badge/skills/gabrielondelphi/claude-tools-for-delphi/light-review-full/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-review-Full

Your own site · 80×15
<a href="https://agentmods.dev/skills/gabrielondelphi/claude-tools-for-delphi/light-review-full"><img src="https://agentmods.dev/badge/skills/gabrielondelphi/claude-tools-for-delphi/light-review-full.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,030 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Rogue Agent · line 128
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Agent Snooping · line 235
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
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 $0.00103 $0.04030
Opus 5 $0.00051 $0.02015
Sonnet 5 $0.00021 $0.00806
Haiku 4.5 $0.00010 $0.00403

Measured 3d ago against content hash 52330c85b971, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

light-review-Full 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 3d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/review-log.py, scripts/test-review-log.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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-review-Full/SKILL.md · 257 lines

How it starts

The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Delphi Review — Pipeline Orchestrator

This skill runs a three-stage review pipeline. You (the main thread) are the orchestrator. You do NOT review code yourself. You launch three sub-agents in strict sequence, thread each agent's output into the next agent's prompt, then sync the project docs and print one consolidated summary.

The three review stages are:

  1. light-review-step1 — finds correctness bugs, reports them, applies the fixes it is confident about.
  2. light-review-step2 — counter-analyzes stage-1's findings, drops false positives, applies the fixes that survive.
  3. light-review-step3 — verifies stage-2's fixes hold up, reverts the bad ones, compiles the project.

After the three stages, two closing steps keep the project honest. Step 5 keeps the docs honest: a fix that changes observable behavior can leave CLAUDE.md (or another MD) describing the old code, so it runs the light-md-DriftUpdate skill to catch that drift — it edits an MD file only when a doc claim genuinely contradicts the changed code; no drift means no edit. Step 6 then records a dated review-log entry — when the review ran, what survived, and a ship-readiness verdict — so that across sessions you can see at a glance whether the code still needs another pass.

Each stage runs in its own isolated sub-agent context. A sub-agent cannot see the previous stage's session — so you must pass each stage's report forward in the next stage's prompt. That is the whole reason this skill exists: without it, the stages have nothing to chain through.

Step 1 — Resolve the input

The user may pass a single .pas file, a folder, or several files. Build the review set — the list of .pas files to review:

  • 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 review all or narrow the scope.
  • No argument → review the .pas files with uncommitted changes. Run git status --porcelain and keep the .pas files it lists (modified, added, or renamed). This is what "the code I just changed" means in practice and needs no branch-name guessing. If that list is empty, tell the user there is nothing to review and stop — do NOT fall back to reviewing the whole repository.

Read the full file on GitHub · 257 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 3d ago Changed · +103 tokens per session 52330c85b971
  2. 7d ago Changed · +10 lines f00facc2e223
  3. 11d ago First seen · 247 lines · 0 tokens per session scan A ffa1a7bd8567

Subscribe to this mod's changes

light-review-Full is a skill published in the GitHub repository GabrielOnDelphi/Claude-Tools-for-Delphi (18 stars, last pushed 4d ago), licensed MPL-2.0. It adds 103 tokens to every session and 4,030 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.

Related

Other skills, from other repositories

no-bare-casts

Writing as in TypeScript or TSX production code, modifying a file that contains a bare as cast, silencing a type error with a cast, encountering as unknown as, or reviewing a cast site.

prisma/orm · 52 tokens

pr-to-go-linter

Generate a new pkg/linters analyzer from a merged or open PR pattern.

github/gh-aw · 22 tokens

code-review-csharp

Perform structured code reviews of C# source code covering naming conventions, performance, security, readability, and .NET best practices. Trigger phrases include "review this C# code", "check my C# for best practices", "analyze this C# class", "find issues in my C# code".

pnp/copilot-prompts · 66 tokens

solid-principles

SOLID principles checklist with Java examples. Use when a class has too many responsibilities, an abstraction leaks, or a dependency points the wrong way, and when the user asks about Single Responsibility, Open/Closed, Liskov, Interface Segregation or Dependency Inversion. For naming, duplication and method length…

decebals/claude-code-java · 73 tokens

splitting-oversized-modules

Split an oversized Python module (a thousand-plus-line logic.py, models.py, api.py, or its test file) into a package of one module per concern, mechanically and provably without changing behavior. Use on a request to split / break up / decompose a god module or move functions out of one, once a human has agreed to…

PostHog/posthog-foss · 197 tokens

go-concurrency-safety

L1 supplement - audits Go-specific concurrency hazards in node client code: map iteration non-determinism, goroutine leaks, mutex ordering, panic boundaries, context cancellation.

PlamenTSV/plamen · 40 tokens