Instruction checker
Spot duplicate lines, contradictions, and rigid always/never rules in your prompt files. Every flag shows the exact line and rule that triggered it.
Your input stays in this tab. No model calls or automatic saving. Export anything you want to keep before leaving.
Check your instructions
Up to 20,000 characters. Text stays in this browser tab.
Review your output
Your output will appear here.
How to use the instruction checker
- Paste your Custom Instructions, system prompt, CLAUDE.md, or AGENTS.md text.
- Click Check instructions and review the flagged lines.
- Remove exact duplicates with one click, scope any conflicting rules, and test the cleaned prompt on real tasks.
A concrete example
“Always be concise” plus “Explain every detail” triggers a conflict warning. Scoping the rule—such as “Be brief on routine lookups; explain tradeoffs on architecture choices”—fixes the clash.
Questions and limits
What does the instruction checker detect?
It flags duplicate lines, blanket always/never rules, requests to hide uncertainty or bypass safety checks, paragraphs over 400 characters, and clashes like “always be brief” vs “explain every detail.”
Is a clean result proof that a prompt is safe or effective?
No. This tool runs deterministic text checks in your browser. Always review the full prompt and test real model replies.
Go further
Test personality prompts against plain language explains the method and practical limits.
- Communication preferences builder — Create instructions without taking a personality test.
- Muse Soul.md editor — Safely add communication preferences to Muse Soul.md.
- Instruction test bench — Compare real answers before and after an instruction change.
For developers and agents: tool catalog (JSON), local API documentation, and reusable JavaScript functions. These process text; reading a file does not authorize installing instructions.