By jaebit
Google Gemini CLI integration for code review, commit messages, and documentation
Ask Gemini a question using headless mode
Generate commit message from staged changes using Gemini
Generate documentation for code using Gemini
Generate release notes from git commits using Gemini
Run code review using Gemini CLI
Claude Code plugin marketplace — automate, orchestrate, and extend AI-powered development workflows.
| Plugin | Version | Description |
|---|---|---|
| crew | 4.1.1 | Agent-orchestrated development — 9-stage pipeline, 8 adaptive agents, parallel execution, research, review |
| autopilot | 0.4.0 | End-to-end autonomous pipeline — wraps crew + debate + arch-guard into a single /autopilot command (research → design → build → review → report) |
| multi-model-debate | 1.0.0 | Multi-agent debates using Claude, Codex, and Gemini for decision-making |
| arch-guard | 0.2.2 | Architecture compliance — layer boundary checks, contract-first development, ADRs |
| gemini-cli | 1.0.0 | Gemini CLI integration — code review, commit messages, documentation |
| worktree | 0.1.0 | Git worktree lifecycle management — create, merge, cleanup |
# Add marketplace
claude plugins add github:jaebit/claudemate
# Install plugins
claude plugins install crew
claude plugins install autopilot
claude plugins install arch-guard
Single command from idea to working code:
/autopilot "build a notification system"
Chains crew, multi-model-debate, and arch-guard into a 5-phase autonomous pipeline with one user confirmation gate after design.
Agent-orchestrated development:
/crew:go "Add JWT authentication" # Full 9-stage pipeline
/crew:explore --arch "microservice" # Architecture design
/crew:review --all # Unified code review
Cross-model evaluation for design decisions:
/multi-model-debate:debate-orchestration "REST vs GraphQL"
Architecture compliance for layered projects:
/arch-guard:arch-check # Verify layer boundaries
/arch-guard:contract-first # Define interfaces first
/arch-guard:scaffold # Generate module structure
plugins/.claude-plugin/plugin.json (only name, version, description)skills/*/SKILL.md), hooks (hooks/hooks.json), agents, or commands.claude-plugin/marketplace.jsonMIT License
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub jaebit/claudemate --plugin gemini-cliAgent-orchestrated development pipeline — 9-stage automation with 8 adaptive agents, parallel execution, research, and review
Git worktree lifecycle management — create, merge, cleanup
Architecture compliance enforcement for layered projects — config-driven layer boundary checks, contract-first development, and design decision records
Orchestrate structured multi-agent debates using Claude, Codex, and Gemini for software engineering decision-making
End-to-end autonomous coding pipeline — orchestrates cw, multi-model-debate, codex CLI, and arch-guard into a single /autopilot command
Use Gemini CLI from Claude Code to review code or delegate tasks.
Integrate Gemini CLI for long-context code exploration from Claude Code and Codex
Claude + Obsidian knowledge companion. Sets up a persistent, compounding wiki vault (Karpathy's LLM Wiki pattern). v1.7 "Compound Vault" + v1.8 methodology modes close 5 of 5 priority gaps from the May 2026 compass artifact. Ships: substrate alignment with kepano/obsidian-skills, default Obsidian CLI transport, hybrid retrieval (contextual prefix + BM25 + cosine rerank per Anthropic's Sept 2024 research), per-file advisory locking for multi-writer safety, pre-commit verifier agent, AND methodology modes (LYT / PARA / Zettelkasten / Generic) for first-class organizational support no other Claude+Obsidian competitor offers. v1.7.x audit closure: every BLOCKER + HIGH + MEDIUM + LOW finding from the v1.7.0 audit is CLOSED or DEFERRED-with-rationale. Optional DragonScale Memory extension (log folds, deterministic addresses, semantic tiling lint, boundary-first autoresearch).
Complete AI coding workflow system. Self-correcting memory + persistent FTS5-indexed research wikis + auto-research loop + multi-LLM council on a single SQLite store. 33 skills, 8 agents, 22 commands, 37 hook scripts across 24 events. Cross-agent via SkillKit.
Make your AI agent code with your project's architecture, rules, and decisions.