home/writing/prompt-risk-scoring

Prompt Risk Scoring

GPTClaudeGemini··282 copies·updated 2026-07-14
prompt-risk-scoring.prompt
# Prompt risk scoring

`claude-cost-guard prompt "<text>"` rates a prompt **Low**, **Medium**, or
**High** for the likelihood it wastes Claude Code tokens, then suggests a safer
rewrite. The logic is a transparent heuristic — no model calls, no network.

when to use it

Community prompt sourced from the open-source GitHub repo rajesh1610-maker/claude-cost-guard (MIT). A "Prompt Risk Scoring" style prompt — adapt the placeholders and specifics to your task. Imported as-is and not independently retested here, so check the output before relying on it.

tags

writingcommunitygeneral

source

rajesh1610-maker/claude-cost-guard · MIT