KushalP1

2 mods across 1 repository, 1 stars between them.

context-doctor

01

KushalP1/context-doctor

Skill Claude CodeCodex

Keep the LLM context window lean and fast. Use when the conversation grows long, large content is pasted or produced by tools, the user asks "what's eating my context/tokens", asks to reduce cost or latency of LLM calls, or asks to profile/optimize/compact a conversation. Also triggers on "context doctor", "token…

1 yesterday A 84 tokens original MIT

context-doctor

02

KushalP1/context-doctor

MCP server Claude CodeCodexCursor +2

Profile and optimize LLM context windows. See what's eating your tokens and fix it — works with Claude, GPT, Gemini, and any MCP-capable AI app. Runs locally from the context-doctor npm package.

1 yesterday A tokens not measured original MIT