mental
v0.2.3Never reconstruct where you left off. Local-first continuity for you and your coding agents — resume, decisions, and what's still in the air. CLI, MCP, and Agent Skills for Cursor, Claude Code, Copilot, and Codex.
By Ali FarahatLicense: MIT0 GitHub starsUpdated 6 hours ago
Directory evidence
- Runtimes
- Claude Code and Agent Plugins
- Parsed components
- 2 skill or MCP entries
- Source updated
- Aug 27, 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 plugin
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install mental@agent-plugin-marketplacePaste 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/afaraha8403/mentalClone 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
├── .claude-plugin/plugin.json├── plugin.json├── skills/mental/SKILL.md└── .mcp.json
Included Skills1
Local-first continuity CLI for coding agents (Cursor, Claude Code, Copilot, Codex, MCP). Maintains a project-continuity log via the Mental CLI. Reconstructs where work stands from git, the latest journal handoff, open decisions, and attention residue; records why consequential decisions were made; extracts residue from a meeting dump or plan-progress question; and leaves an exact resume point after substantive work. Use when starting or finishing non-trivial repository work, answering project-orientation questions, ingesting a transcript into residue (never storing the transcript), or recording a decision that git cannot explain.
MCP servers1
- command
- node
- args
- ${CLAUDE_PLUGIN_ROOT}/bin/cli.mjs serve
MCP configuration uses runtime-provided plugin path placeholders such as ${PLUGIN_ROOT} or ${CLAUDE_PLUGIN_ROOT}. Review the manifest for the runtime-specific expansion rules.
Plugin manifests2
{
"name": "mental",
"displayName": "Mental",
"version": "0.2.3",
"description": "Never reconstruct where you left off. Local-first continuity for you and your coding agents — resume, decisions, and what's still in the air. CLI, MCP, and Agent Skills for Cursor, Claude Code, Copilot, and Codex.",
"author": {
"name": "Ali Farahat",
"url": "https://github.com/afaraha8403"
},
"homepage": "https://github.com/afaraha8403/mental#readme",
"repository": "https://github.com/afaraha8403/mental",
"license": "MIT",
"keywords": [
"continuity",
"coding-agents",
"ai-agents",
"cursor",
"claude-code",
"copilot",
"mcp",
"mcp-server",
"agent-skills",
"agent-plugins",
"llm",
"cli",
"local-first",
"journal",
"decisions",
"okf",
"handoff",
"context"
],
"mcpServers": "./.mcp.json"
}{
"$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
"name": "mental",
"version": "0.2.3",
"description": "Never reconstruct where you left off. Local-first continuity for you and your coding agents — resume, decisions, and what's still in the air. CLI, MCP, and Agent Skills for Cursor, Claude Code, Copilot, and Codex.",
"author": {
"name": "Ali Farahat",
"url": "https://github.com/afaraha8403"
},
"homepage": "https://github.com/afaraha8403/mental#readme",
"repository": "https://github.com/afaraha8403/mental",
"license": "MIT",
"keywords": [
"continuity",
"coding-agents",
"ai-agents",
"cursor",
"claude-code",
"copilot",
"mcp",
"mcp-server",
"agent-skills",
"agent-plugins",
"llm",
"cli",
"local-first",
"journal",
"decisions",
"okf",
"handoff",
"context"
]
}For maintainers
If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.
[mental on Agent Plugins Marketplace](https://pluginsmp.com/plugins/mental)