Production-ready agents, skills, hooks, commands, rules, and MCP configurations optimized for development with sudocode.
This is a sudocode-flavored fork of everything-claude-code.
This plugin now fully supports Windows, macOS, and Linux. All hooks and scripts have been rewritten in Node.js for maximum compatibility.
The plugin automatically detects your preferred package manager (npm, pnpm, yarn, or bun) with the following priority:
- Environment variable:
CLAUDE_PACKAGE_MANAGER - Project config:
.claude/package-manager.json - package.json:
packageManagerfield - Lock file: Detection from package-lock.json, yarn.lock, pnpm-lock.yaml, or bun.lockb
- Global config:
~/.claude/package-manager.json - Fallback: First available package manager
To set your preferred package manager:
# Via environment variable
export CLAUDE_PACKAGE_MANAGER=pnpm
# Via global config
node scripts/setup-package-manager.js --global pnpm
# Via project config
node scripts/setup-package-manager.js --project bun
# Detect current setting
node scripts/setup-package-manager.js --detectOr use the /setup-pm command in Claude Code.
This repo is a Claude Code plugin - install it directly or copy components manually.
Sudocode Integration: This fork adds first-class support for sudocode - a git-native spec and issue management system. Items marked with 🆕 are new sudocode-specific additions. Items marked with ✨ have been enhanced with sudocode integration.
everything-sudocode/
|-- .claude-plugin/ # Plugin and marketplace manifests
| |-- plugin.json # Plugin metadata and component paths
| |-- marketplace.json # Marketplace catalog for /plugin marketplace add
|
|-- agents/ # Specialized subagents for delegation
| |-- spec-writer.md # Extract requirements into structured specs
| |-- issue-planner.md # Break specs into atomic issues with dependencies
| |-- feedback-reviewer.md # Triage feedback, update specs, create follow-ups
| |-- planner.md # Feature planning (sudocode: plan→issues conversion)
| |-- architect.md # System design (sudocode: ADR→spec conversion)
| |-- tdd-guide.md # Test-driven development (sudocode: criteria→tests)
| |-- code-reviewer.md # Quality review (sudocode: feedback provision)
| |-- security-reviewer.md # Vulnerability analysis
| |-- build-error-resolver.md
| |-- e2e-runner.md # Playwright E2E testing
| |-- refactor-cleaner.md # Dead code cleanup
| |-- doc-updater.md # Documentation sync
|
|-- skills/ # Workflow definitions and domain knowledge
| |-- sudocode-workflow/ # Full lifecycle: Capture→Plan→Execute→Close
| |-- spec-writing-patterns/ # Templates for Feature, ADR, Research, Bug specs
| |-- issue-planning-patterns/ # Dependency patterns: Foundation, Pipeline, Diamond
| |-- feedback-patterns/ # Feedback types, templates, anchoring techniques
| |-- coding-standards/ # Language best practices
| |-- backend-patterns/ # API, database, caching patterns
| |-- frontend-patterns/ # React, Next.js patterns
| |-- continuous-learning/ # Auto-extract patterns (sudocode: spec suggestions)
| |-- strategic-compact/ # Compaction suggestions (sudocode: aware boundaries)
| |-- tdd-workflow/ # TDD methodology (sudocode: criteria→tests→feedback)
| |-- security-review/ # Security checklist
| |-- eval-harness/ # Verification evaluation (sudocode: results→feedback)
| |-- verification-loop/ # Continuous verification (sudocode: issue output)
|
|-- commands/ # Slash commands for quick execution
| |-- spec.md # /spec - Create/update specs from requirements
| |-- discuss-spec.md # /discuss-spec - Review spec for ambiguities
| |-- plan-issues.md # /plan-issues - Break spec into issues
| |-- discuss-issue.md # /discuss-issue - Review issue context before implementing
| |-- implement.md # /implement - Start work with feedback on completion
| |-- feedback.md # /feedback - Process accumulated spec feedback
| |-- tdd.md # /tdd - Test-driven development
| |-- plan.md # /plan - Implementation planning
| |-- e2e.md # /e2e - E2E test generation
| |-- code-review.md # /code-review - Quality review
| |-- build-fix.md # /build-fix - Fix build errors
| |-- refactor-clean.md # /refactor-clean - Dead code removal
| |-- learn.md # /learn - Extract patterns mid-session
| |-- checkpoint.md # /checkpoint - Save verification state
| |-- verify.md # /verify - Run verification loop
| |-- setup-pm.md # /setup-pm - Configure package manager
|
|-- rules/ # Always-follow guidelines (copy to ~/.claude/rules/)
| |-- sudocode.md # Plan with specs, break into issues, leave feedback
| |-- security.md # Mandatory security checks
| |-- coding-style.md # Immutability, file organization
| |-- testing.md # TDD, 80% coverage requirement
| |-- git-workflow.md # Commit format, PR process
| |-- agents.md # When to delegate to subagents
| |-- performance.md # Model selection, context management
|
|-- hooks/ # Trigger-based automations
| |-- hooks.json # All hooks config (PreToolUse, PostToolUse, Stop, etc.)
| |-- memory-persistence/ # Session lifecycle hooks
| |-- strategic-compact/ # Compaction suggestions
|
|-- scripts/ # Cross-platform Node.js scripts
| |-- lib/ # Shared utilities
| | |-- utils.js # Cross-platform file/path/system utilities
| | |-- package-manager.js # Package manager detection and selection
| |-- hooks/ # Hook implementations
| | |-- session-start.js # Load context on session start
| | |-- session-end.js # Save state on session end
| | |-- pre-compact.js # Pre-compaction state saving
| |-- setup-package-manager.js # Interactive PM setup
|
|-- tests/ # Test suite
| |-- lib/ # Library tests
| |-- hooks/ # Hook tests
| |-- run-all.js # Run all tests
|
|-- contexts/ # Dynamic system prompt injection contexts
| |-- dev.md # Development mode context
| |-- review.md # Code review mode context
| |-- research.md # Research/exploration mode context
|
|-- examples/ # Example configurations and sessions
| |-- CLAUDE.md # Example project-level config
| |-- user-CLAUDE.md # Example user-level config
|
|-- mcp-configs/ # MCP server configurations
| |-- mcp-servers.json # GitHub, Supabase, Vercel, Railway, etc.
|
|-- marketplace.json # Self-hosted marketplace config (for /plugin marketplace add)
The core sudocode workflow integrated throughout this plugin:
Spec (requirements) → Issues (work breakdown) → Implementation → Feedback
↑ |
└──────────────────── (learnings improve specs) ───────────────┘
| Component | Purpose | Sudocode Tools |
|---|---|---|
| Specs | Persistent requirements, decisions, context | upsert_spec, show_spec |
| Issues | Atomic work items with dependencies | upsert_issue, ready, link |
| Tasks | Session-scoped runtime tracking | Claude Code native |
| Feedback | Implementation learnings → spec improvements | add_feedback |
The easiest way to use this repo - install as a Claude Code plugin:
# Add this repo as a marketplace
/plugin marketplace add sudocode-ai/everything-sudocode
# Install the plugin
/plugin install everything-sudocode@everything-sudocodeOr add directly to your ~/.claude/settings.json:
{
"extraKnownMarketplaces": {
"everything-sudocode": {
"source": {
"source": "github",
"repo": "sudocode-ai/everything-sudocode"
}
}
},
"enabledPlugins": {
"everything-sudocode@everything-sudocode": true
}
}This gives you instant access to all commands, agents, skills, and hooks.
If you prefer manual control over what's installed:
# Clone the repo
git clone https://github.com/sudocode-ai/everything-sudocode.git
# Copy agents to your Claude config
cp everything-sudocode/agents/*.md ~/.claude/agents/
# Copy rules
cp everything-sudocode/rules/*.md ~/.claude/rules/
# Copy commands
cp everything-sudocode/commands/*.md ~/.claude/commands/
# Copy skills
cp -r everything-sudocode/skills/* ~/.claude/skills/Copy the hooks from hooks/hooks.json to your ~/.claude/settings.json.
Copy desired MCP servers from mcp-configs/mcp-servers.json to your ~/.claude.json.
Important: Replace YOUR_*_HERE placeholders with your actual API keys.
Subagents handle delegated tasks with limited scope. Example:
---
name: code-reviewer
description: Reviews code for quality, security, and maintainability
tools: Read, Grep, Glob, Bash
model: opus
---
You are a senior code reviewer...Skills are workflow definitions invoked by commands or agents:
# TDD Workflow
1. Define interfaces first
2. Write failing tests (RED)
3. Implement minimal code (GREEN)
4. Refactor (IMPROVE)
5. Verify 80%+ coverageHooks fire on tool events. Example - warn about console.log:
{
"matcher": "tool == \"Edit\" && tool_input.file_path matches \"\\\\.(ts|tsx|js|jsx)$\"",
"hooks": [{
"type": "command",
"command": "#!/bin/bash\ngrep -n 'console\\.log' \"$file_path\" && echo '[Hook] Remove console.log' >&2"
}]
}Rules are always-follow guidelines. Keep them modular:
~/.claude/rules/
security.md # No hardcoded secrets
coding-style.md # Immutability, file limits
testing.md # TDD, coverage requirements
The plugin includes a comprehensive test suite:
# Run all tests
node tests/run-all.js
# Run individual test files
node tests/lib/utils.test.js
node tests/lib/package-manager.test.js
node tests/hooks/hooks.test.jsContributions are welcome and encouraged.
This repo is meant to be a community resource. If you have:
- Useful agents or skills
- Clever hooks
- Better MCP configurations
- Improved rules
Please contribute! See CONTRIBUTING.md for guidelines.
- Language-specific skills (Python, Go, Rust patterns)
- Framework-specific configs (Django, Rails, Laravel)
- DevOps agents (Kubernetes, Terraform, AWS)
- Testing strategies (different frameworks)
- Domain-specific knowledge (ML, data engineering, mobile)
Critical: Don't enable all MCPs at once. Your 200k context window can shrink to 70k with too many tools enabled.
Rule of thumb:
- Have 20-30 MCPs configured
- Keep under 10 enabled per project
- Under 80 tools active
Use disabledMcpServers in project config to disable unused ones.
These configs work for my workflow. You should:
- Start with what resonates
- Modify for your stack
- Remove what you don't use
- Add your own patterns
MIT - Use freely, modify as needed, contribute back if you can.
Originally forked from https://github.com/affaan-m/everything-claude-code