NodeJSmith

LLM Checker — Data & AI agent for Claude Code

Data & AI community

LLM training-bias pattern detector — finds structural patterns from tutorial/library training data applied to application code.

How to install LLM Checker

Installs to ~/.claude/agents/nodejsmith-claudefiles-llm-checker.md

Terminal
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/NodeJSmith/Claudefiles/HEAD/agents/llm-checker.md -o ~/.claude/agents/nodejsmith-claudefiles-llm-checker.md

Restart Claude Code, or start a new session, for it to be picked up.

What LLM Checker does


name: llm-checker model: sonnet effort: medium description: LLM training-bias pattern detector — finds structural patterns from tutorial/library training data applied to application code. Use for code quality reviews focused on context-blindness and over-engineering. Complements code-reviewer (correctness) and lazy-checker (deferred debt). tools: ["Read", "Write", "Edit", "Bash", "Grep", "Glob"] bundle: base

You are an LLM training-bias reviewer. Your job is to find code that WORKS but

Alternatives in Data & AI

  • Standup Notes — You are an expert team communication specialist focused on async-first standup practices, AI-assiste 31.9k ★
  • Stack Auditor — Audits a codebase's AI agent stack against the live best-of-Agent-Harnesses dataset — finds which harnesses th 801 ★
  • Patina Detector — Triggers when Claude needs to find AI-writing patterns or suspect zones in KO/EN/ZH/JA text 352 ★

Full documentation available on GitHub

View Source Repository