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/skills/light-code-ArchitectureUnit/SKILL.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/skills/gabrielondelphi/claude-tools-for-delphi/light-code-architectureunit)<a href="https://agentmods.dev/skills/gabrielondelphi/claude-tools-for-delphi/light-code-architectureunit"><img src="https://agentmods.dev/badge/skills/gabrielondelphi/claude-tools-for-delphi/light-code-architectureunit.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 5.1 | $0.00073 | $0.00659 |
| Opus 5 | $0.00036 | $0.00329 |
| Sonnet 5 | $0.00015 | $0.00132 |
| Haiku 4.5 | $0.00007 | $0.00066 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/light-code-ArchitectureUnit — Find shallow units (launcher)
This skill is a thin launcher. The audit is done by the light-code-ArchitectureUnit agent in its
own context window, so the whole-project read does not clog the main context — only the ranked report
comes back. Do not map units or analyse them yourself; resolve the scope, then launch the agent.
When to run
- User invokes
/light-code-ArchitectureUnit(with or without args). - User says variants: "find shallow units", "what units should be merged", "which files should be folded together", "audit the module structure".
If the real question is about a class shape (god class, anemic class, misplaced responsibility),
this is the wrong skill — point at /light-code-ArchitectureClass.
Steps
- Resolve scope. From
$args: a path, a folder, or several files. With no argument, the scope is the project's own app source under the project root. Pass--include-lightsaberthrough if the user gave it. You do not need to ask anything — the agent applies the skip rules (LightSaber, third-party, tests, forms) itself. - Launch the
light-code-ArchitectureUnitagent via the Agent tool withsubagent_type: light-code-ArchitectureUnit. Put the resolved scope (and any flags) in the prompt. - Print the agent's returned report verbatim. It is already self-contained (ranked candidates + verdict line). Do not re-analyse or second-guess its verdicts.
That's it. No mapping, no signal-walking, no edits in the skill itself.
Where the rules live (for the agent, not for you)
references/architecture-principles.md— the shared deep/shallow model, counter-analysis discipline, LightSaber boundary, risk flags (read by both this and the ArchitectureClass agent).- The agent's own file (
.claude/agents/light-code-ArchitectureUnit.md) — the unit-specific signals, anti-signals, procedure, report format, and hard rules.
Claude Tools for Delphi — © 2026 Gabriel Moraru, gabrielmoraru.com — MPL-2.0
What ships with it
1 file 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.
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 · +2 lines 479ece0d7c78
- 7d ago First seen · 46 lines · 73 tokens per session scan A 5673390c40d1
light-code-ArchitectureUnit is a skill published in the GitHub repository GabrielOnDelphi/Claude-Tools-for-Delphi (17 stars, last pushed yesterday), licensed MPL-2.0. It adds 73 tokens to every session and 659 once invoked, about $0.0004 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 skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…