MCP server Claude CodeCodexCursor +2
MCP server "attune-ai" as configured in Smart-AI-Memory/attune-ai. Runs locally from the python Python package. Needs 2 environment variables to run.
Plugin Claude Code
Bundles 1 command, 6 agents, 1 hook · 402 tokens together
Persistent memory and receipt-verified workflows for Claude Code — /spec plans, reviews, and executes with quality gates; plus security audits, code reviews, test generation, and release prep from /attune.
Plugin Claude Code
Bundles 4 skills · 186 tokens together
Read and explore .help/ documentation with progressive depth. Lightweight runtime companion to attune-ai's built-in authoring — no AI keys required.
Command Claude Code
Create and manage custom AI agents.
Agent Claude Code
Documentation generation subagent.
Agent Claude Code
Multi-agent release readiness assessment.
Agent Claude Code
Anthropic Agent SDK integration.
Agent Claude Code
Persistent agent state and recovery.
Agent Claude Code
Behavioral test generation subagent.
Command Claude Code
AI-powered developer workflows with Socratic discovery.
Command Claude Code
Guided brainstorming with structured discovery and plan output.
Command Claude Code
Batch API processing with 50% cost savings.
Command Claude Code
Code review and bug prediction — find quality issues, style violations, and likely bugs.
Command Claude Code
Multi-pass deep code review — security, quality, and test gaps.
Command Claude Code
Developer tools — debug, commit, PR, code review, refactoring.
Command Claude Code
Generate documentation from source code — docstrings, README sections, API references.
Command Claude Code
Auto-diagnose and fix failing tests — identifies root causes and applies fixes.
Command Claude Code
Quick reference for all Attune commands.
Command Claude Code
The /pipeline command has been replaced by /spec.
Command Claude Code
Planning, brainstorming, architecture, and refactoring strategies.
Command Claude Code
Code-level refactoring analysis and roadmap generation.
Command Claude Code
Release preparation, security scanning, and publishing.
Command Claude Code
Store, retrieve, search, and manage persistent memory across sessions.
Command Claude Code
Scan code for security vulnerabilities — eval/exec, path traversal, secrets, injection.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: