15Low
The skill uses dogmatic language to rigidly enforce
Behavior Analysis
Mismatch detected — The skill's name and description imply it actively 'uses' or 'helps implement' TDD. However, the skill is purely an instructional document explaining the TDD methodology, rather than an interactive tool that assists in generating tests or code, or executing TDD steps.
Claims to do
Test-Driven Development (TDD): Write the test first. Watch it fail. Write minimal code to pass.
Actually does
This skill provides a comprehensive guide to the Test-Driven Development (TDD) methodology, detailing the Red-Green-Refactor cycle. It instructs users on writing tests, running them with `npm test`, writing minimal code, and refactoring, using TypeScript/JavaScript examples. It does not execute code or interact with external systems.
Skill Info
NameFleron/Claude-plugins/tdd
Registrygithub
Version5662b3e1543f
PURLpkg:github/Fleron/Claude-plugins@5662b3e1543f?skill=tdd
Installs455,628
Source
SHA-256b3b7c241f488...
SHA-1dcc7480fce11...
MD5947da0885e91...
TLSHaa12ea689db7...
ssdeep192:zVNplrg8...
Size9,885 bytes
Install
Assessments (1)
AI Agent Traps ↗Dogmatic language may lead to rigid agent behaviorlowbiased language
The skill uses highly authoritative and dogmatic language ('MANDATORY', 'Iron Law', 'No exceptions', 'Delete means delete') to enforce TDD principles. This could lead the agent to rigidly adhere to TDD, potentially overriding more flexible approaches or even human input, which could be seen as a form of oversight evasion or social engineering of the human via the agent's output.
80% confidenceline 30
MANDATORY. Never skip. NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST Delete means delete
Description Mismatchlowdescription mismatch
The skill's name and description imply it actively 'uses' or 'helps implement' TDD. However, the skill is purely an instructional document explaining the TDD methodology, rather than an interactive tool that assists in generating tests or code, or executing TDD steps.
85% confidence
Skill content is entirely descriptive text, code examples, and diagrams. No executable commands or API calls are made by the skill itself, only instructions for the user to run `npm test`.
Badge
Markdown
[](https://mondoo.com/ai-agent-security/skills/github/Fleron/Claude-plugins/tdd)HTML
<a href="https://mondoo.com/ai-agent-security/skills/github/Fleron/Claude-plugins/tdd"><img src="https://mondoo.com/ai-agent-security/api/badge/github/Fleron/Claude-plugins/tdd.svg" alt="Mondoo Skill Check" /></a>Image URL
https://mondoo.com/ai-agent-security/api/badge/github/Fleron/Claude-plugins/tdd.svgSecure your AI agents
Skills can read files, run commands, and access credentials. Mondoo helps organizations manage the security risks of AI agent skills across their entire fleet.
- Continuous scanning of skills across all registries
- Policy enforcement before skills reach your agents
- Integration with your existing security workflow