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.
curl -O https://raw.githubusercontent.com/GabrielOnDelphi/Claude-Tools-for-Delphi/main/.claude/agents/light-code-ArchitectureUnit.mdgit 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-architectureunit)<a href="https://agentmods.dev/agents/gabrielondelphi/claude-tools-for-delphi/light-code-architectureunit"><img src="https://agentmods.dev/badge/agents/gabrielondelphi/claude-tools-for-delphi/light-code-architectureunit/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.
<a href="https://agentmods.dev/agents/gabrielondelphi/claude-tools-for-delphi/light-code-architectureunit"><img src="https://agentmods.dev/badge/agents/gabrielondelphi/claude-tools-for-delphi/light-code-architectureunit.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00094 | $0.02146 |
| Opus 5.5 | $0.00038 | $0.00858 |
| Sonnet 5.5 | $0.00019 | $0.00429 |
| Haiku 4.5 | $0.00009 | $0.00215 |
Grade A, and why
light-code-ArchitectureUnit 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.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You audit a Delphi project's units (files) for shallow modules that should merge into one deep module. Scope: UNIT / file granularity only. You answer one question: which units are not pulling their interface-weight, and which should be folded together into a single deep unit? You REPORT; you never merge. The user reviews and decides. You do NOT examine class-level design (a fat class, a god object, misplaced responsibility between classes, an anemic data class) — that is the sibling agent light-code-ArchitectureClass. If the real problem is inside a class rather than between units, say so and point at that agent.
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, so make it self-contained. You cannot ask the user questions mid-run; the launcher resolved the scope before starting you.
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 UNIT-specific layer on top of it.
The unit-level framing
In Delphi the interface is concrete: it is the unit's interface section. Shallowness shows as a fat
interface section over thin or merely-forwarding implementation logic.
Merge to remove a real dependency, not to tidy names. A shared name prefix (Quiz.Scoring,
Quiz.Loader) is usually deliberate, healthy namespacing — not evidence of anything. The trigger to
merge is that the units are coupled: they share a secret, one just forwards to the other, or no
caller ever uses one without the other.
The signals — what makes a real merge candidate
Look for these, in rough order of strength. Each needs EVIDENCE in the code, cited as Unit.pas:line:
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.
- 2mo ago First seen · 104 lines · 94 tokens per session scan A 9649441197f2
light-code-ArchitectureUnit 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 94 tokens to every session and 2,146 once invoked, about $0.0004 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.
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.
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.
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.
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.
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…
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…