Agent Plugins Marketplace
All plugins

context-mode

v1.9.0

Context window optimization for Claude Code / Cowork. Sandboxes tool output, compresses what returns with a self-learning 3-stage pipeline, and routes tools automatically — reducing context consumption by 30–60% in typical sessions, more in research-heavy ones.

Claude Code4 Skills1 MCP serverstdio

By Scott ConverseLicense: ELv22 GitHub starsUpdated 3 days ago

Directory evidence

Runtimes
Claude Code
Parsed components
5 skill or MCP entries
Source updated
Sep 20, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology

Install context-mode for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install context-mode-3@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/scottconverse/context-mode

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.

Plugin files

context-mode/
├── .claude-plugin/plugin.json
├── skills/context-mode/SKILL.md
├── skills/ctx-doctor/SKILL.md
├── skills/ctx-purge/SKILL.md
├── skills/ctx-stats/SKILL.md
└── .mcp.json

Included Skills4

context-modeskills/context-mode/SKILL.md

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.

ctx-doctorskills/ctx-doctor/SKILL.md

Run context-mode diagnostics. Checks runtimes, hooks, FTS5, plugin registration, npm and marketplace versions. Trigger: /context-mode:ctx-doctor

ctx-purgeskills/ctx-purge/SKILL.md

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

ctx-statsskills/ctx-stats/SKILL.md

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

MCP servers1

context-modestdio
command
node
args
${CLAUDE_PLUGIN_ROOT}/start.js
env.CLAUDE_PLUGIN_DATA
${CLAUDE_PLUGIN_DATA}
env.NODE_PATH
${CLAUDE_PLUGIN_DATA}/node_modules

MCP configuration uses runtime-provided plugin path placeholders such as ${PLUGIN_ROOT} or ${CLAUDE_PLUGIN_ROOT}. Review the manifest for the runtime-specific expansion rules.

Plugin manifests1

.claude-plugin/plugin.json
{
  "name": "context-mode",
  "version": "1.9.0",
  "description": "Context window optimization for Claude Code / Cowork. Sandboxes tool output, compresses what returns with a self-learning 3-stage pipeline, and routes tools automatically — reducing context consumption by 30–60% in typical sessions, more in research-heavy ones.",
  "author": {
    "name": "Scott Converse"
  },
  "homepage": "https://scottconverse.github.io/context-mode/",
  "repository": "https://github.com/scottconverse/context-mode",
  "license": "ELv2",
  "keywords": [
    "mcp",
    "context-window",
    "sandbox",
    "fts5",
    "bm25",
    "compression",
    "self-learning"
  ],
  "mcpServers": {
    "context-mode": {
      "command": "node",
      "args": [
        "${CLAUDE_PLUGIN_ROOT}/start.js"
      ],
      "env": {
        "CLAUDE_PLUGIN_DATA": "${CLAUDE_PLUGIN_DATA}",
        "NODE_PATH": "${CLAUDE_PLUGIN_DATA}/node_modules"
      }
    }
  },
  "skills": "./skills/"
}

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[context-mode on Agent Plugins Marketplace](https://pluginsmp.com/plugins/context-mode-3)