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-bug-MadShi/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-bug-madshi)<a href="https://agentmods.dev/skills/gabrielondelphi/claude-tools-for-delphi/light-bug-madshi"><img src="https://agentmods.dev/badge/skills/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/skills/gabrielondelphi/claude-tools-for-delphi/light-bug-madshi"><img src="https://agentmods.dev/badge/skills/gabrielondelphi/claude-tools-for-delphi/light-bug-madshi.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00165 | $0.01820 |
| Opus 5.5 | $0.00066 | $0.00728 |
| Sonnet 5.5 | $0.00033 | $0.00364 |
| Haiku 4.5 | $0.00016 | $0.00182 |
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 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/light-bug-MadShi — Delphi crash-triage pipeline (multi-product)
Do this in order, whichever of the three routes reached this skill: Gabriel typed the name; the general light-bug skill saw a .mad file or the words "crash report" and routed here at its Step 0; or light-bug-BioniX came here with the product already fixed to BioniX. Be terse. Each step is a single tool call unless noted.
The pipeline is product-driven. Every product is one block in c:\Users\<you>\.claude\skills\light-bug-MadShi\products.ini (mbox list + source paths + fix-log location + memory subfolder). Read that file first — it is the single source of routing facts.
Step 0 — Resolve the product and the argument
Parse $args:
- A
.madpath (an existing file ending.mad): skip listing. Decide the product by reading the first ~2 KB of the file and matching itsexecutableline against each block'sExeMatchinproducts.ini. If a product word is ALSO given, trust that. Go to step 4 with this path. - A product word (
bionix->[BioniX];myproduct->[ExampleProduct]; match case-insensitively): use that block. Go to step 1. - Nothing / unclear: ask with
AskUserQuestionwhich product (one option per block inproducts.ini). Then go to step 1.
Read the chosen block. Keep every field — you will pass them all to the agent in step 4.
Step 1 — List recent .mad candidates across the product's mbox(es)
Split the block's Mboxes on |, trim each, and pass them all as one array to the extractor. It merges newest-first and removes duplicates:
$mboxes = @('<path1>','<path2>','<path3>') # from the block's Mboxes field
& 'c:\Users\<you>\.claude\skills\light-bug-MadShi\Tools\extract-mad.ps1' -MboxPath $mboxes -List -OutPrefix '<OutPrefix>'
Do NOT add -ExecutionPolicy Bypass (the auto-mode classifier blocks it; the script runs without it).
Each stdout line is tab-separated:
index<TAB>date<TAB>from<TAB>subject<TAB>sizeBytes<TAB>exeVersion<TAB>status<TAB>sourceMbox
statusisok,stub(attachment manually deleted), orinvalid(decode failed / under 1 KB).sourceMboxis the leaf name of the mbox the report came from.- Stderr carries progress.
What ships with it
3 files 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 922acd25435b
- 1mo ago Changed · +10 lines 63f75079afac
- 2mo ago First seen · 96 lines · 165 tokens per session scan A 50871b84920b
light-bug-MadShi 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 165 tokens to every session and 1,820 once invoked, about $0.0007 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
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
ci-fixer
CI failures - read error, minimal fix, verify.
diagnosing-missing-recordings
Diagnoses why a session recording is missing or was not captured. Use when a user asks why a session has no replay, why recordings aren't appearing, or wants to troubleshoot session replay capture issues for a specific session ID or across their project. Covers SDK diagnostic signals, project settings, sampling…