By jleechanorg
Orchestrate 145+ production-tested slash commands for PR automation, multi-agent coding, and autonomous development workflows across any git repo. Includes adversarial code review gates, TDD enforcement, memory-augmented command execution, and cloud deployment integration.
Breadth-first research on a topic and ingest results into the LLM wiki. Usage: /wiki-bfs <topic> [--layers N] [--ingest]. Wiki path resolves from .wiki-default in CWD, then ~/.wiki-default, then ~/llm_wiki/wiki. --wiki flag always wins.
Enhanced command wrappers provide memory pattern integration for improved execution quality and consistency.
Claude Commands Directory
Babysit — orchestration loop to monitor PRs, CI, and test evidence generation
/4layer - Four-Layer Minimal Repro Testing Protocol
Reference documentation for understanding and using the custom agent system
Specialist consultant for consolidating duplicate logic, reusing existing modules, and reducing codebase fragmentation. Defaults to Claude Code CLI, with fallbacks to Codex CLI and Cursor CLI if unavailable.
Specialized AI agent for comprehensive code analysis, security review, and quality assessment. Expert in multi-language code review with focus on bugs, security vulnerabilities, performance issues, and best practices.
Design, test, and optimize AI prompts for NPCs, world generation, quest creation, and narrative elements. Use for any Gemini API prompt engineering.
Anti Gravity CLI-powered pair programming coder. Delegates implementation to the agy CLI with --dangerously-skip-permissions for independent code generation. Works with any pair-verifier teammate.
/4layer - Four-Layer Minimal Repro Testing Protocol
Use when proving, rejecting, or deleting backend adjustment registry entries with real LLM evidence and independent disabled-adjustment worktrees.
Token-efficient second opinion slash command /advice. Extracts decision point + artifact (≤150 lines), then fans out in parallel: (1) Opus subagent reviewer with fallback chain codex→agy→cursor, (2) /research on the decision topic, (3) /secondo multi-model opinion. Use instead of advisor() which ships the full conversation uncached.
Generate a full agento PR status report — 6-point green checks, zero-touch rate, display inline, and post to Slack
Reference WorldArchitect agent routing priority and modal lock patterns.
Uses power tools
Uses Bash, Write, or Edit tools
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 claimnpx claudepluginhub jleechanorg/claude-commands --plugin claude-commandsBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
No model invocation
Executes directly as bash, bypassing the AI model
No model invocation
Executes directly as bash, bypassing the AI model
Runs pre-commands
Contains inline bash commands via ! syntax
Runs pre-commands
Contains inline bash commands via ! syntax
A comprehensive collection of workflow automation commands for Claude Code that transform your development process through intelligent command composition and orchestration.
The YAML frontmatter at the top of this template provides command metadata and should remain intact for downstream tooling.
To install Claude Commands in Claude Code CLI, first register the marketplace:
/plugin marketplace add jleechanorg/claude-commands
Then browse available commands with /plugin and install:
/plugin install claude-commands@claude-commands
After installation, restart your Claude Code CLI session for the plugin to take effect.
To verify successful installation, run /help to check that commands appear.
Let Claude Code analyze and set up what you need by asking:
"I want to use commands from https://github.com/jleechanorg/claude-commands - analyze what's available and set up the ones useful for my project"
git clone https://github.com/jleechanorg/claude-commands.git
cp -r claude-commands/.claude/commands/* ./.claude/commands/
See INSTALL.md for detailed setup, troubleshooting, and platform-specific instructions.
⚠️ PROTOTYPE WIP REPOSITORY - This is an experimental command system exported from a working development environment. Use as reference but expect adaptation needed for your specific setup.
Complete collection of 174 slash commands across 22 categories
Interactive setup wizard for configuring any repository with Claude Code best practices, based on Boris Cherny's workflow
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use
Git and PR workflows with code review, onboarding, and PR enhancement
Claude Code workflow patterns: prompting, CLAUDE.md maintenance, multi-agent orchestration
PROJECT.md-first autonomous development with hybrid auto-fix documentation. 8-agent pipeline, auto-orchestration, docs auto-update on commit (true vibe coding). Knowledge base system with 90% faster repeat research. Strict mode enforces SDLC best practices automatically. Works for ANY Python/JavaScript/TypeScript/Go project.