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-review-DelphiExceptions/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-review-delphiexceptions)<a href="https://agentmods.dev/skills/gabrielondelphi/claude-tools-for-delphi/light-review-delphiexceptions"><img src="https://agentmods.dev/badge/skills/gabrielondelphi/claude-tools-for-delphi/light-review-delphiexceptions/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-review-delphiexceptions"><img src="https://agentmods.dev/badge/skills/gabrielondelphi/claude-tools-for-delphi/light-review-delphiexceptions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 369 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00107 | $0.10437 |
| Opus 5 | $0.00053 | $0.05219 |
| Sonnet 5 | $0.00021 | $0.02087 |
| Haiku 4.5 | $0.00011 | $0.01044 |
Grade A, and why
light-review-DelphiExceptions 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 — 379 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/light-review-DelphiExceptions - try..except Auditor
Every except block gets one question:
If this code failed because of a bug of ours, would we ever find out?
A block that catches Exception catches our own access violations too. madExcept then never sees them, never mails a report, and the bug lives forever in every copy the users run. The opposite mistake costs just as much: letting a read-only folder crash the program and fill the mailbox with reports about a problem that is not ours to fix.
Both mistakes come from the same habit - writing on E: Exception do because it is shorter than naming the classes that can actually happen.
Scope: except blocks. try..finally never catches anything, so it is out of scope. Unit-test code is out of scope.
Files in this skill folder (c:\Users\<you>\.claude\skills\light-review-DelphiExceptions\):
| File | What it is | When it is read |
|---|---|---|
SKILL.md |
This file: the five searches, the exception-class split, the verdict table, the report format. | Always |
references/the-eleven-rules.md |
The argument and the evidence behind each of the eleven rules - the Delphi runtime library facts, the madExcept behaviour, the LightSaber routines. | When a block touches one of the eleven; the index below says which |
scripts/find-bare-catches.py |
The scanner for search 3. Blanks comments and string literals, then walks tokens to find every except with no on ... do handler and sort it into six piles. |
Run, never read - and never retyped |
scripts/test-find-bare-catches.py |
The scanner's self-test: seventeen Delphi blocks with the right answer written on each except line. |
After any change to the scanner - it must print All green. |
evals/evals.json |
The three test prompts this skill is checked against, and what each one must produce. | Before publishing a change |
Default is REPORT ONLY. The skill changes nothing unless $args contains fix.
Step 1 - Find every block
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.
- 3d ago Changed · -283 lines 5a76620ec912
- 5d ago Changed · +80 lines · +3 tokens per session 7ec4bcfca21f
- 6d ago First seen · 582 lines · 104 tokens per session scan A c9418affdcf3
light-review-DelphiExceptions is a skill published in the GitHub repository GabrielOnDelphi/Claude-Tools-for-Delphi (18 stars, last pushed 4d ago), licensed MPL-2.0. It adds 107 tokens to every session and 10,437 once invoked, about $0.0005 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 2026-09-05.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
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.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
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…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.