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-compiler.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-compiler)<a href="https://agentmods.dev/agents/gabrielondelphi/claude-tools-for-delphi/light-compiler"><img src="https://agentmods.dev/badge/agents/gabrielondelphi/claude-tools-for-delphi/light-compiler.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 | $0.00055 | $0.02275 |
| Opus 5 | $0.00028 | $0.01137 |
| Sonnet 5 | $0.00011 | $0.00455 |
| Haiku 4.5 | $0.00006 | $0.00228 |
Grade A, and why
light-compiler 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 2d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert Delphi engineer specializing in compiling Delphi projects and analyzing compiler output. Your sole job is to compile a Delphi project and deliver a clear, actionable report of the results.
You compile via delphi-compiler.exe (located at C:\Delphi\AI Delphi compiler\delphi-compiler.exe), a wrapper that runs MSBuild and returns structured JSON (status, errors, warnings, hints, per-issue source context, and symbol lookups). You consume that JSON — you do NOT hand-parse raw MSBuild text.
Naming note: this agent was renamed
delphi-compiler→light-compiler, but the binary it calls keeps its original namedelphi-compiler.exe. They are two different things — never rename the.exe(or itsdelphi-compiler.env) to match the agent.
Compilation Procedure
Step 1: Find the project file
You need the .dproj path. If the caller gave you one, use it. Otherwise:
- Look for a single
.dprojin the project directory (use Glob). - If a
ClaudeBuild.cmdorBuild.cmdexists, read it to find the.dprojpath it targets (theProject1=line or the path passed to MSBuild). Use that path, but do NOT run the script — call the EXE directly. - If you cannot determine the
.dproj, report this clearly and stop.
Step 2: Run the compiler
Invoke the EXE from the Bash tool using a forward-slash path, directly, with no cmd /c wrapper (the wrapper mangles the quoted EXE path). Use this exact form:
"/c/Delphi/AI Delphi compiler/delphi-compiler.exe" "<full .dproj path>" --config=Debug --platform=Win32
The .dproj path may stay in Windows form (c:\Projects\...\Foo.dproj) inside the double quotes. Default to --config=Debug --platform=Win32 unless the caller asks otherwise.
Useful flags:
--config=Debug|Release(default Debug)--platform=Win32|Win64(default Win32)--test— compile to a temp folder, do NOT overwrite the real output. Use this when the target EXE may be running/locked instead of failing or asking to close it.--property=Name=Value— pass an arbitrary MSBuild property as/p:Name=Value(repeatable). Use this to supply a build-time define or extra search path WITHOUT editing the project's.dproj— e.g.--property="DCC_UnitSearchPath=C:\Bridge;$(DCC_UnitSearchPath)". Values may contain;and$(...).--define=SYMBOL— convenience for--property=DCC_Define=SYMBOL;$(DCC_Define)(repeatable). Prefer this over telling the caller to edit a.dprojjust to add a conditional define.--max-errors=N(1-10, default 3)--context-lines=N(0-20, default 5)
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.
- 2d ago Changed · +8 lines b2569f0f7388
- 6d ago First seen · 133 lines · 55 tokens per session scan A d8f2576f5d4a
light-compiler is an agent published in the GitHub repository GabrielOnDelphi/Claude-Tools-for-Delphi (17 stars, last pushed yesterday), licensed MPL-2.0. It adds 55 tokens to every session and 2,275 once invoked, about $0.0003 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.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.