What is delphi-dev CLAUDE.md?

Project instructions for a Claude Code plugin that provides Delphi programming guidance through skills, commands, and agents. They explain the repository structure, installation process, and how to test changes.

They are for editing and testing the plugin's Markdown and JSON files, understanding its skills and commands, and reinstalling the plugin to verify changes.

They clarify that the repository contains plugin instructions rather than a Delphi application, preventing contributors from using the wrong development workflow.

How adrianosantostreina/delphi-dev configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to adrianosantostreina/delphi-dev. 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/adrianosantostreina/delphi-dev/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/adrianosantostreina/delphi-dev

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/adrianosantostreina/delphi-dev/claude-md.svg)](https://agentmods.dev/instructions/adrianosantostreina/delphi-dev/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/adrianosantostreina/delphi-dev/claude-md"><img src="https://agentmods.dev/badge/instructions/adrianosantostreina/delphi-dev/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,640 This file is loaded in full into every session.

When invoked 1,640 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01640	$0.01640
Opus 5	$0.00820	$0.00820
Sonnet 5	$0.00328	$0.00328
Haiku 4.5	$0.00164	$0.00164

Measured 3d ago against content hash af700b25ceb0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

delphi-dev CLAUDE.md 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.

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.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this repo is

This repo is not a Delphi project — it is the source of the delphi-dev Claude Code plugin (a marketplace plugin that makes Claude a Delphi expert). The "code" is entirely markdown + JSON consumed by the Claude Code harness at install time. There is no build, lint, or test command.

Test changes by installing the plugin from a local checkout (/plugin marketplace add <path> then /plugin install delphi-dev@delphi-dev) and exercising the affected skill/command/agent in a real session. Changes to .md / .json files only take effect after re-install.

Architecture: how the pieces wire together

Three primitives, each loaded by Claude Code differently:

Skills (skills/<name>/SKILL.md) — auto-activated when their description: frontmatter matches user intent or detected files. They form the always-available knowledge layer. Some skills (delphi-laudo, delphi-spec, delphi-standards, delphi-tests) have a references/ subdirectory the skill loads on demand to keep the base SKILL.md small.
Commands (commands/<name>.md) — explicit slash commands (/audit, /write, etc.). Commands are thin orchestrators that delegate to skills + agents.
Agents (agents/<name>.md) — subagents invoked via the Agent tool for heavier, isolated work (deep audit, full code generation, SPEC writing, test generation).

Key invocation flows worth knowing before editing:

/write → delphi-writer agent. After delivering a class, delphi-writer is expected to auto-invoke delphi-tester in silent mode to generate Teste<Class>.pas. If you change the writer's contract, update the tester contract in the same change.
delphi-claudeignore skill auto-runs when .dpr/.dproj/.pas are detected and creates/maintains .claudeignore at the project root. It must never ignore .pas/.dfm/.dpr/.dpk/.inc/.fmx — the deny-list of source extensions is enforced in skills/delphi-claudeignore/SKILL.md.
delphi-laudo (the audit knowledge skill) and delphi-auditor (the agent) duplicate the 8-dimension scoring model. Keep both in sync — the agent has a fallback protocol used when the skill isn't loaded.

Read the full file on GitHub · 71 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.

3d ago Changed · +1 lines · +31 tokens per session af700b25ceb0
7d ago First seen · 70 lines · 1,609 tokens per session scan A a7046e33e361

Subscribe to this mod's changes

delphi-dev CLAUDE.md is an instructions file published in the GitHub repository adrianosantostreina/delphi-dev (79 stars, last pushed 3d ago), licensed MIT. It adds 1,640 tokens to every session, about $0.0082 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.

Languages

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

delphi-dev: Instructions file for Claude Code