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/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/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="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 | $0.00087 | $0.00621 |
| Opus 5.5 | $0.00035 | $0.00248 |
| Sonnet 5.5 | $0.00017 | $0.00124 |
| Haiku 4.5 | $0.00009 | $0.00062 |
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 1mo 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 — 43 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.
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
Autopilot for Delphi — Claude clicks, types and reads inside your running VCL / FMX app.
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.
- 1mo ago Changed · -5 lines · +14 tokens per session 955fe21c2456
- 1mo ago Changed · +2 lines 479ece0d7c78
- 2mo 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 (23 stars, last pushed 28d ago), licensed MPL-2.0. It adds 87 tokens to every session and 621 once invoked, about $0.0003 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 skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
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"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…