Claude-Tools-for-Delphi: Skill for Claude Code

.claude/skills/light-review-FakeTest/SKILL.md

light-review-FakeTest is a skill for Claude Code from GabrielOnDelphi/Claude-Tools-for-Delphi. It costs 90 tokens per session (2,676 once invoked), scanned A, original, MPL-2.0.

An auditor for Delphi DUnitX or DUnit test suites, which are collections of automated checks for Delphi code. It looks for tests that pass without proving the behavior they claim to test.

In plain words
What is it for?
Use it to establish a test baseline, inspect existing tests for fake or weak checks, and optionally prove problems with a safe mutation of the product code.
Why use it?
It helps distinguish a genuinely verified green test run from tests that contain no meaningful assertions or would stay green even if the product code were broken.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is GabrielOnDelphi/Claude-Tools-for-Delphi's own configuration. It tells Claude Code how to work on Claude-Tools-for-Delphi itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Claude-Tools-for-Delphi configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/GabrielOnDelphi/Claude-Tools-for-Delphi/main/.claude/skills/light-review-FakeTest/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/GabrielOnDelphi/Claude-Tools-for-Delphi

Made for: Claude Code.

Wrote 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.

agentmods badge for light-review-FakeTest

README.md
[![agentmods](https://agentmods.dev/badge/skills/gabrielondelphi/claude-tools-for-delphi/light-review-faketest/github.svg)](https://agentmods.dev/skills/gabrielondelphi/claude-tools-for-delphi/light-review-faketest)
Your own site
<a href="https://agentmods.dev/skills/gabrielondelphi/claude-tools-for-delphi/light-review-faketest"><img src="https://agentmods.dev/badge/skills/gabrielondelphi/claude-tools-for-delphi/light-review-faketest/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.

agentmods 80×15 button for light-review-FakeTest

Your own site · 80×15
<a href="https://agentmods.dev/skills/gabrielondelphi/claude-tools-for-delphi/light-review-faketest"><img src="https://agentmods.dev/badge/skills/gabrielondelphi/claude-tools-for-delphi/light-review-faketest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,676 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

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 →

  • high YARA Match · line 3
    YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).
    Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
  • high Prompt Injection · line 97
    Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
    Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00090 $0.02676
Opus 5 $0.00045 $0.01338
Sonnet 5 $0.00018 $0.00535
Haiku 4.5 $0.00009 $0.00268

Measured 8d ago against content hash 0a3c301b58b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

light-review-FakeTest 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 8d 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.

.claude/skills/light-review-FakeTest/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/light-review-FakeTest — Test-Integrity Auditor

This skill answers one question: is the suite's green real, or do some tests pass without testing anything? A "fake" test is one that stays green even when the product code it names is broken — zero assertions, Assert.Pass-only, a tautology, a setup-only check, a tautological helper, a vague "something errored" check, or a negative test with no probe.

Scope: this audits EXISTING tests for honesty — whether each one can fail. It does NOT measure code coverage or find missing tests; a suite of 100%-honest tests can still under-test the product. Coverage gaps are a different job — say so if the user conflates the two.

You (the main thread) orchestrate. You do NOT audit the tests yourself — the light-review-FakeTest agent does the per-test analysis. Your job: resolve the scope, establish the green baseline, launch the auditor (sharded if large), optionally run a mutation proof, then summarize.

Parse $args

$args may contain a path (file / folder / several files) and/or a mode keyword:

  • default — baseline run + static audit.
  • static or --no-run — skip the build+run baseline; static audit only (use when the build infra isn't here or the user just wants the read).
  • deep or mutation — after the static audit, PROVE the findings with a git-safe mutation pass (Step 4). Opt-in because it edits product code (and reverts it) and rebuilds repeatedly.

Step 1 — Resolve the test scope

Build the test set — the list of test .pas units to audit:

  • Explicit file(s) → use as-is.
  • A folder → Glob <folder>/**/*.pas, then keep only units that are actually tests: Grep them for DUnitX.TestFramework or TestFramework (the framework uses), plus [Test] or a TTestCase descendant. Drop helpers/fixtures that contain no tests (still note them — the auditor may need them to resolve helpers).
  • No argument → discover. Look for a Tests\ or UnitTesting\ folder under the project; if none, Grep the repo for DUnitX.TestFramework|TestFramework to find test units. Present the discovered set and proceed. If you find more than ~25 test units, print the count and ask whether to audit all or narrow.
  • No test units found at all → say so and stop. There is nothing to audit; do not invent a scope.

Read the full file on GitHub · 108 lines

Changes

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.

  1. 8d ago Changed · +2 lines 0a3c301b58b4
  2. 12d ago First seen · 106 lines · 90 tokens per session scan A 2c4047e82ba1

Subscribe to this mod's changes

light-review-FakeTest is a skill published in the GitHub repository GabrielOnDelphi/Claude-Tools-for-Delphi (18 stars, last pushed 5d ago), licensed MPL-2.0. It adds 90 tokens to every session and 2,676 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 2026-08-30.