context-mode-ops

Context Mode is an MCP server that intercepts large tool outputs (test results, logs, docs, web snapshots) and returns only concise summaries to Claude, reducing context consumption by up to 98% and extending session longevity.

An MCP server that reduces context window consumption by sandboxing raw tool output (98% reduction) and maintains session continuity across conversation compactions using SQLite-backed event tracking with FTS5/BM25 search.

Context management skill that addresses the "other half of the context problem" by helping AI agents efficiently load, manage, and scope project context for more effective code assistance.

A read-only stats skill for the context-mode system that displays how much context window was saved during the current session, including token consumption, context savings ratio, and per-tool breakdown.

A context management skill that solves the problem of MCP tool calls dumping raw data into AI agent context windows, helping agents maintain efficient context usage during conversations.

Upgrade skill for Context Mode, a tool that solves the other half of the context problem by transforming raw MCP tool call data into structured, token-efficient context for AI agents like Claude Code, Cursor, and Copilot.

Permanently deletes all indexed content from the knowledge base, providing a clean-slate reset for the context management system.

Compresses and manages MCP tool call output to prevent context window bloat. Reduces excessive context consumption from Playwright snapshots, GitHub issues, and access logs that can waste 40% or more of available context within 30 minutes.

A slash command plugin for Context Mode that indexes local files and directories into a persistent FTS5 knowledge base, allowing agents to later search and retrieve specific content without consuming context window space with raw file data.

A slash command plugin for Context Mode that searches previously indexed file and directory content stored in a persistent FTS5 knowledge base, enabling agents to retrieve relevant information without flooding the context window with raw data.