Context Mode
Plugin Verified ActiveMCP server that saves 98% of your context window with session continuity. Sandboxed code execution in 11 languages, FTS5 knowledge base with BM25 ranking, and automatic state restore across compactions.
To drastically reduce context window usage and maintain session state across LLM interactions, enabling longer and more productive agent sessions.
Features
- Reduces context window usage by up to 98%
- Provides session continuity across compactions and restarts
- Sandboxes code execution in 11 languages
- Indexes content using FTS5 with BM25 ranking
- Supports multiple platforms with automatic hook registration
Use Cases
- Working with large codebases or datasets without losing context
- Maintaining state across complex, multi-turn LLM interactions
- Analyzing large log files or API responses efficiently
- Ensuring consistent agent behavior after conversation compactions
Non-Goals
- Replacing the LLM's core reasoning capabilities
- Acting as a cloud analytics dashboard or telemetry service
- Storing user data outside of the local machine
Installation
/plugin install context-mode@mksglu-context-modeContains 6 extensions
Skill (6)
Use context-mode tools (ctx_execute, ctx_execute_file) instead of Bash/cat when processing large outputs. Triggers: "analyze logs", "summarize output", "process data", "parse JSON", "filter results", "extract errors", "check build output", "analyze dependencies", "process API response", "large file analysis", "page snapshot", "browser snapshot", "DOM structure", "inspect page", "accessibility tree", "Playwright snapshot", "run tests", "test output", "coverage report", "git log", "recent commits", "diff between branches", "list containers", "pod status", "disk usage", "fetch docs", "API reference", "index documentation", "call API", "check response", "query results", "find TODOs", "count lines", "codebase statistics", "security audit", "outdated packages", "dependency tree", "cloud resources", "CI/CD output". Also triggers on ANY MCP tool output that may exceed 20 lines. Subagent routing is handled automatically via PreToolUse hook.
Run context-mode diagnostics. Checks runtimes, hooks, FTS5, plugin registration, npm and marketplace versions. Trigger: /context-mode:ctx-doctor
Open the context-mode Insight analytics dashboard in the browser. Shows personal metrics: session activity, tool usage, error rate, parallel work patterns, project focus, and actionable insights. First run installs dependencies (~30s). Subsequent runs open instantly. Trigger: /context-mode:ctx-insight
Purge the context-mode knowledge base. Permanently deletes all indexed content and resets session stats. This is destructive and cannot be undone. Trigger: /context-mode:ctx-purge
Show how much context window context-mode saved this session. Displays token consumption, context savings ratio, and per-tool breakdown. Read-only — shows stats only, no reset capability. To wipe the knowledge base entirely, use ctx_purge instead. Trigger: /context-mode:ctx-stats
Update context-mode from GitHub and fix hooks/settings. Pulls latest, builds, installs, updates npm global, configures hooks. Trigger: /context-mode:ctx-upgrade
Quality Score
VerifiedTrust Signals
Similar Extensions
Claude Hud
100Real-time statusline HUD for Claude Code - displays context usage, tool activity, agent tracking, and todo progress
Ruflo Agent
99Agent runtimes for ruflo — local WASM-sandboxed agents (rvagent: 10 wasm_agent_*/wasm_gallery_* MCP tools, built on @ruvector/rvagent-wasm + @ruvector/ruvllm-wasm per ADR-070) plus Anthropic Claude Managed Agents as a cloud backend (managed_agent_* MCP tools per ADR-115). One interface, local-vs-cloud runtimes.
Seatbelt Sandboxer
95Generate minimal macOS Seatbelt sandbox configurations for applications
Msapps Vm Disk Cleanup
93Fix disk-full errors in Cowork VMs and Claude Code sandboxes — clean caches, temp files, and reclaim space automatically