By thedotmack
MCP server configuration for Agent SOP integration providing Standard Operating Procedures (SOPs) for AI agents with markdown-based workflow definitions, RFC 2119 compliance, and SOP authoring skills.
Use when writing or creating new Standard Operating Procedures (SOPs) for AI agents. Covers effective SOP writing, clarity principles, and actionable instruction design.
Use when updating, versioning, deprecating, or maintaining existing Standard Operating Procedures. Covers keeping SOPs accurate, relevant, and synchronized with implementation changes.
Use when writing SOPs that require precise requirement levels using RFC 2119 constraint keywords (MUST, SHOULD, MAY). Covers proper usage of requirement keywords for deterministic agent behavior.
Use when structuring Standard Operating Procedures with proper sections, organization, and markdown formatting. Covers SOP anatomy and section organization.
Admin access level
Server config contains admin-level keywords
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.
A curated marketplace of Claude Code plugins that embody the principles of ethical and professional software development.
Han (藩 - domain/clan) is a marketplace of Claude Code plugins built on the foundation of the seven Bushido virtues. Each plugin helps you write better code through skills, agents, validation hooks, and external integrations.
The marketplace is organized around Japanese martial arts philosophy:
The Bushido Code guides every plugin in this marketplace:
Use the han CLI tool to automatically detect and install appropriate plugins:
Important: Han must be installed globally for hooks to work. Hooks run validation commands (tests, linting, etc.) when you stop working, and they require
hanto be available in your PATH. Usingnpxwill install plugins but hooks will not function.
# Install globally (REQUIRED for hooks)
npm install -g @thebushidocollective/han
# Then install plugins
han plugin install --auto
For other installation methods (Homebrew, curl, manual download), visit han.guru.
The installer will:
.claude/settings.json automatically/plugin CommandUse Claude Code's built-in plugin command to add the marketplace:
/plugin marketplace add thebushidocollective/han
Then install individual plugins:
/plugin install bushido@han
/plugin install jutsu-typescript@han
Note: For hooks to work, you must also install
hanglobally and ensure it's in your PATH. See Automatic Installation above.
Add the Han marketplace to your Claude Code settings (.claude/settings.json):
{
"extraKnownMarketplaces": {
"han": {
"source": {
"source": "github",
"repo": "thebushidocollective/han"
}
}
},
"enabledPlugins": {
"bushido@han": true
}
}
Then browse available plugins using Claude Code's plugin interface.
Note: For hooks to work, you must also install
hanglobally and ensure it's in your PATH. See Automatic Installation above.
The foundational plugin containing the seven virtues, enforcement hooks, and core quality skills.
Always install this first - it provides the philosophical foundation and universal quality principles (SOLID, TDD, Boy Scout Rule, etc.).
Language and tool plugins that provide validation hooks for your development workflow.
Categories:
Each jutsu plugin includes validation hooks that run on Stop and SubagentStop events, ensuring code quality before you continue.
Browse all jutsu plugins: Check the /jutsu directory in this repository.
Specialized agents focused on development disciplines and practices.
Disciplines include:
Browse all dō plugins: Check the /do directory in this repository.
MCP servers that provide external knowledge and integrations.
Examples:
Browse all hashi plugins: Check the /hashi directory in this repository.
Reminder: Han must be installed globally for hooks to work. See han.guru for installation instructions.
# Interactive mode - browse and select plugins
han plugin install
# Auto-detect mode - AI analyzes codebase
han plugin install --auto
npx claudepluginhub thedotmack/han --plugin hashi-agent-sopMemory compression system for Claude Code - persist context across sessions
Persistent memory system for Claude Code - seamlessly preserve context across sessions
Validation and quality enforcement for Claude Agent SDK projects with TypeScript type checking and structure validation.
Validation and quality enforcement for GitHub Actions workflows with act local testing.
MCP server for managing technical blueprint documentation. Use search_blueprints before creating, read_blueprint before modifying, write_blueprint after implementation changes. Includes skills and hooks for quality enforcement.
Harness-native ECC operator layer - 67 agents, 278 skills, 94 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
v9.54.1 — Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive C4 architecture documentation workflow with bottom-up code analysis, component synthesis, container mapping, and context diagram generation
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.