delphi

delphi is a skill for Claude Code, Codex from danieleteti/delphi-ai-skills. It costs 155 tokens per session (5,647 once invoked), scanned A, original, Apache-2.0.

A guide for writing, reviewing, and fixing Delphi or Object Pascal code, including language features, the standard library, memory handling, strings, and version differences. Delphi is a programming language and development environment, while the RTL and VCL are its built-in libraries and UI framework.

In plain words
What is it for?
Use it when working on Delphi source files, console programs, desktop interfaces, services, libraries, generics, managed values, or resource and lifetime handling.
Why use it?
It helps avoid compile errors and memory bugs caused by guessing which language features or library APIs are available in a particular Delphi version.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md; mentions AGENTS.md; mentions Gemini CLI.

Good fit Use it when working on Delphi source files, console programs, desktop interfaces, services, libraries, generics, managed values, or resource and lifetime handling.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/danieleteti/delphi-ai-skills/delphi
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.

Any agent
npx skills add danieleteti/delphi-ai-skills --skill delphi
Clone the repo
git clone --depth 1 https://github.com/danieleteti/delphi-ai-skills

Made for: Claude Code, Codex.

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 delphi

README.md
[![agentmods](https://agentmods.dev/badge/skills/danieleteti/delphi-ai-skills/delphi/github.svg)](https://agentmods.dev/skills/danieleteti/delphi-ai-skills/delphi)
Your own site
<a href="https://agentmods.dev/skills/danieleteti/delphi-ai-skills/delphi"><img src="https://agentmods.dev/badge/skills/danieleteti/delphi-ai-skills/delphi/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 delphi

Your own site · 80×15
<a href="https://agentmods.dev/skills/danieleteti/delphi-ai-skills/delphi"><img src="https://agentmods.dev/badge/skills/danieleteti/delphi-ai-skills/delphi.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 155 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,647 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 $0.00155 $0.05647
Opus 5 $0.00077 $0.02823
Sonnet 5 $0.00031 $0.01129
Haiku 4.5 $0.00015 $0.00565

Measured 12d ago against content hash 54148e82c53a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

delphi 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 12d 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.

skills/delphi/SKILL.md · 356 lines

How it starts

The opening of the file, as written. The whole thing — 356 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Delphi / Object Pascal — language and RTL guide

The foundation the DMVCFramework skills sit on. Nothing here assumes a framework or a project layout — it applies to a console app, a VCL form, a service, a library.

Everything below was copied from the Delphi 13 Florence RTL/VCL source on disk, or confirmed on the official docwiki. Version boundaries were checked release by release, not recalled.


When in doubt about an API — verify it, never guess

A plausible-but-wrong RTL identifier costs the user a compile error and their trust. Do not answer from memory. Verify, in this order:

  1. Read the shipped source — the tree of the release you are targeting. It is on every developer machine, one tree per installed release:

    C:\Program Files (x86)\Embarcadero\Studio\<n>.0\source\rtl\sys\      System.pas, System.SysUtils.pas, System.Types.pas
    C:\Program Files (x86)\Embarcadero\Studio\<n>.0\source\rtl\common\   System.Classes.pas, System.Generics.*, System.IOUtils.pas,
                                                                        System.Rtti.pas, System.Threading.pas, System.JSON.pas, …
    C:\Program Files (x86)\Embarcadero\Studio\<n>.0\source\vcl\          Vcl.Forms.pas, Vcl.Controls.pas, …
    

    <n> is the product version: 37 = 13 Florence, 23 = 12 Athens, 22 = 11 Alexandria. The layout is identical in every tree, so targeting 12 Athens means reading …\Studio\23.0\source\rtl\common\System.Classes.pas, not the 37.0 copy of the same file.

    Which tree matters. The RTL grows release by release: a type, an overload or a parameter that is in the 13 Florence source may simply not exist in 12 Athens or 11 Alexandria. Once the target is known (see Establish the target, below), verify against that tree. When the target's tree is not installed — you are on 13 Florence but writing for a customer's 12 Athens — check the symbol against the matching docwiki (step 2), which is versioned, and say which release you confirmed it on.

Read the full file on GitHub · 356 lines

Files

What ships with it

6 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. 12d ago First seen · 356 lines · 155 tokens per session scan A 54148e82c53a

Subscribe to this mod's changes

delphi is a skill published in the GitHub repository danieleteti/delphi-ai-skills (18 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 155 tokens to every session and 5,647 once invoked, about $0.0008 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.