Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Monitors Claude Code sessions with metacognitive feedback on code quality, writing, and learning — reviews changes, prompts reflection on intent and clarity, and enforces structured evaluation via lifecycle hooks.
npx claudepluginhub cloud-atlas-ai/superego --plugin superegoTemporarily disable superego evaluation for this session.
Enable superego for this project/session.
Initialize superego for this project.
Manage superego prompts for this project. Available actions:
Remove superego from this project (inverse of init).
Metacognitive review of software development work. Use when writing code, reviewing PRs, or making architectural decisions.
Learning coach reviewing teaching approaches. Use when an AI is helping someone learn or understand concepts, to ensure teaching is hands-on and verifiable.
Collaborative review of written content. Use when drafting blog posts, documentation, essays, or other written material.
Matches all tools
Hooks run on every tool call, not just specific ones
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Metacognitive advisor that monitors Claude Code and provides feedback
Self-evolving Claude Code system that learns from corrections, manages context, and improves every session
Codex CLIにセカンドオピニオンを求めるスキル。「codexと相談して」「codexに聞いて」で発動する。
Self-improving Claude Code plugin — learns from corrections across sessions via reflexio
Maintain programming skills by ensuring humans write a minimum percentage of code
Open-source, local-first Claude Code plugin for token reduction, context compression, and cost optimization using hybrid RAG retrieval (BM25 + vector search), reranking, AST-aware chunking, and compact context packets.
Unified Hi-Fi Control - Control Roon playback and HQPlayer audio pipeline
Metacognitive advisor that monitors Claude Code and provides feedback
Simple task tracking for LLM sessions - ownership-based workflow for multi-agent coordination
Simple task tracking for LLM sessions - ownership-based workflow for multi-agent coordination
oh-task, oh-merge, oh-notes, oh-plan, oh-review, oh-ci, oh-conflict, and jira-plan skills for autonomous GitHub issue workflows, batch PR merging, PR feedback handling, CI fix, conflict resolution, and task planning (GitHub + Jira). Includes signal_completion custom tool for structured completion signaling.
A metacognitive advisor for AI coding assistants. Monitors conversations, evaluates the assistant's approach, and provides feedback before finishing.
Supported platforms:
When you use Claude Code (or OpenCode) with superego enabled:
This creates feedback loops where Claude can course-correct both during work and before presenting results.
# 1. Install the plugin
/plugin marketplace add cloud-atlas-ai/superego
/plugin install superego@superego
# 2. Initialize in your project (installs binary if needed)
/superego:init
The /superego:init command detects if the binary is missing and offers to install it via Homebrew or Cargo.
Superego provides metacognitive feedback—but feedback without strategic context is incomplete. For the full power of aligned AI development, combine superego with Open Horizons MCP:
# Add OH MCP marketplace
/plugin marketplace add cloud-atlas-ai/oh-mcp-server
/plugin install oh-mcp@oh-mcp-server
# Configure
/oh-mcp:setup
What you get:
Learn more: OH MCP Server | Open Horizons
| Command | Description |
|---|---|
/superego:init | Initialize superego for this project (offers binary install if needed) |
/superego:status | Check if plugin, binary, and project are configured |
/superego:prompt | Manage prompts: list, switch (code/writing), show current |
/superego:review | On-demand review of changes (staged, pr, or file) |
/superego:enable | Enable superego (offers init if not set up) |
/superego:disable | Temporarily disable for current session |
/superego:remove | Remove superego from project |
claude plugin marketplace update superego # Refresh cache
claude plugin update superego@superego # Update plugin
# Restart Claude Code to apply
If you prefer to install the sg binary manually instead of via /superego:init:
# Homebrew (macOS)
brew install cloud-atlas-ai/superego/superego
# Cargo (cross-platform)
cargo install superego
# From source
git clone https://github.com/cloud-atlas-ai/superego.git
cd superego && cargo install --path .
Then run sg init in your project to create .superego/.
OpenCode support is in alpha. It uses a TypeScript plugin that runs entirely within OpenCode—no separate binary needed.
# 1. Download plugin to your project
mkdir -p .opencode/plugin
curl -L -o .opencode/plugin/superego.js \
https://github.com/cloud-atlas-ai/superego/releases/latest/download/index.js
# 2. Start OpenCode and initialize
opencode
# Ask: "use superego init"
Or install globally:
mkdir -p ~/.config/opencode/plugin
curl -L -o ~/.config/opencode/plugin/superego.js \
https://github.com/cloud-atlas-ai/superego/releases/latest/download/index.js
See opencode-plugin/README.md for build-from-source instructions and detailed configuration.
Codex support uses a skill that the agent can invoke at decision points.
# 1. Install the skill
mkdir -p ~/.codex/skills/superego
curl -L -o ~/.codex/skills/superego/SKILL.md \
https://raw.githubusercontent.com/cloud-atlas-ai/superego/main/codex-skill/SKILL.md
# 2. In Codex, ask the agent to set up:
# "$superego init"
The $superego init command installs the binary, creates .superego/, and adds AGENTS.md guidance automatically.
After setup, the agent calls $superego at decision points to evaluate the conversation.
See codex-skill/ for details.