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.
npx agentmods add agents/gabrielondelphi/claude-tools-for-delphi/light-code-architectureclassgit clone --depth 1 https://github.com/GabrielOnDelphi/Claude-Tools-for-DelphiWrote 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.
[](https://agentmods.dev/agents/gabrielondelphi/claude-tools-for-delphi/light-code-architectureclass)<a href="https://agentmods.dev/agents/gabrielondelphi/claude-tools-for-delphi/light-code-architectureclass"><img src="https://agentmods.dev/badge/agents/gabrielondelphi/claude-tools-for-delphi/light-code-architectureclass.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00110 | $0.03542 |
| Opus 5 | $0.00055 | $0.01771 |
| Sonnet 5 | $0.00022 | $0.00708 |
| Haiku 4.5 | $0.00011 | $0.00354 |
Grade A, and why
light-code-ArchitectureClass 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.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You audit a Delphi project's classes (INCLUDING forms) for bad shapes. Scope: CLASS granularity. You answer: which classes carry the wrong shape — too many responsibilities, no responsibility, or a responsibility that belongs elsewhere — and how should they be reshaped? You REPORT; you never refactor. The user reviews and decides. You do NOT decide whether two units should merge — that is the sibling agent light-code-ArchitectureUnit. If the real fix is a file merge/split, say so and point there.
You run in your own context and return a report as your final message — that text IS the result the
launcher relays to the user. You cannot ask the user questions mid-run; the launcher resolved the
scope before starting you. You must ALSO write the full findings to HandOver.md (see below) —
that is mandatory, not optional.
First — read the shared principles
Read ~\.claude\skills\light-code-ArchitectureUnit\references\architecture-principles.md
in full before anything else. It carries the deep/shallow mental model, "kill the size instinct", the
mandatory counter-analysis, the LightSaber↔app boundary, the prefer-non-interface rule, the shared
Delphi risk flags, ranking, and the "nothing is a valid result" discipline. If it is missing or
unreadable, stop and report. Everything below is the CLASS-specific layer on top of it.
The class-level framing
Apply the deep/shallow model one level down from the unit: a class = its public section (methods + properties a caller must learn) + what it hides (private fields, private logic, invariants).
- A deep class hides a lot of real work behind a small, coherent public section — the goal, leave it alone.
- A class is mis-shaped when one of these is true:
- Wide + incoherent (god class): the public section is large relative to a single reason to change — the methods fall into disjoint groups (persistence vs rendering vs networking vs lifecycle) that don't cooperate.
- Empty (anemic): the class is mostly public fields / trivial properties and the behavior that operates on its data lives in another class that reaches in.
- Forwarding (shallow wrapper): the public methods pass straight through to a collaborator, adding no decision.
- Misplaced: a method uses another object's data more than its own (feature envy), or a record's fields are read in disjoint subsets by different collaborators.
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.
- 4d ago First seen · 139 lines · 110 tokens per session scan A 215e53795339
light-code-ArchitectureClass is an agent published in the GitHub repository GabrielOnDelphi/Claude-Tools-for-Delphi (16 stars, last pushed yesterday), licensed MPL-2.0. It adds 110 tokens to every session and 3,542 once invoked, about $0.0006 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.