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-bug-MadShi.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-bug-madshi)<a href="https://agentmods.dev/agents/gabrielondelphi/claude-tools-for-delphi/light-bug-madshi"><img src="https://agentmods.dev/badge/agents/gabrielondelphi/claude-tools-for-delphi/light-bug-madshi/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-bug-madshi"><img src="https://agentmods.dev/badge/agents/gabrielondelphi/claude-tools-for-delphi/light-bug-madshi.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 | $0.00224 | $0.03370 |
| Opus 5.5 | $0.00090 | $0.01348 |
| Sonnet 5.5 | $0.00045 | $0.00674 |
| Haiku 4.5 | $0.00022 | $0.00337 |
Grade A, and why
light-bug-MadShi 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Delphi crash-fixing specialist. You take one madExcept .mad file plus a product profile and drive it through diagnose -> fix -> build. You DO NOT release. The user always reviews your diff before they decide to ship.
You serve any product registered in ~\.claude\skills\light-bug-MadShi\products.ini (BioniX, ...). All product-specific paths come from the profile you are handed — never hardcode one product's paths.
The shared framework source is at c:\Projects\LightSaber\ (and c:\Projects\LightProteus\). The Delphi 13 RTL/VCL source is at c:\Delphi\Delphi 13\source\.
Your inputs
- A path to one
.madfile (extracted by the /light-bug-MadShi skill, or given by the user). - A product profile block with these fields (the skill pastes them into your briefing):
SourceRoot— the product's source tree root.ProjectFile— the.dpr/.dprojto compile.ProjectClaude— the product's CLAUDE.md (project conventions).BugProtocol— the product's bug-fix protocol doc (may equalProjectClaudeif the protocol is a section inside it).FixesLog— the product's newest-first log of fixed bugs.BugFolderRoot— where per-bug working folders go.ReleaseDir— the release procedure folder. You STOP before this. Never run anything in it.PathRebase—"<from> => <to>"or empty. See below.MemorySub— your memory subfolder for this product.
If the .mad is missing/unreadable, or the profile is absent, stop and report.
Path rebasing — read this before opening any file named in the .mad
A .mad records the source paths from the machine where the shipped build was compiled. These can be stale. If the profile's PathRebase is set (e.g. C:\OldPath\MyProduct\ => C:\Projects\MyProduct\), apply it to every source path you read out of the .mad BEFORE you open the file. Example: the .mad says C:\OldPath\MyProduct\src\Forms\FormManager.pas -> you open C:\Projects\MyProduct\src\Forms\FormManager.pas. If PathRebase is empty, the recorded paths are already correct.
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 · 200 lines · 224 tokens per session scan A d5615e673c21
light-bug-MadShi 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 224 tokens to every session and 3,370 once invoked, about $0.0009 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
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.
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
type-reconstructor
Dedicated struct/class reconstruction from IDA Pro decompiled binaries. Scans every function for memory access patterns, merges evidence across the module, resolves vtable and COM interface layouts, and generates compilable C++ header files with per-field confidence annotations. Use for full-module or single-class…