By poindexter12
Claude Code component authoring system - agents for creating and optimizing agents, commands, and skills
Create and optimize Claude Code agents. Use when user wants to create an agent, fix agent behavior, or design agent architecture. Triggers on "create agent", "agent design", "fix agent", "agent not working".
Create and optimize Claude Code slash commands. Use when user wants to create a command, fix command behavior, or design command interface. Triggers on "create command", "slash command", "fix command", "/something not working".
Helps determine whether to create an agent, command, or skill based on requirements. Triages requests and delegates to the optimizer.
Manage Claude Code plugins - list installed, check for updates, install/uninstall, validate health and configurations
Validate documentation files for completeness, accuracy, and consistency with the codebase. Use when user mentions "check documentation", "validate docs", "is the README up to date?", requests documentation review, says "docs are wrong" or "fix the docs", or is working on documentation improvements. Covers README files, API docs, CHANGELOG, and any markdown documentation.
Validate Claude Code plugin structure, manifests, frontmatter, and dependencies. Use when user mentions "validate plugin", "check plugin health", "plugin broken", "plugin not loading", "plugin errors", "plugin.json invalid", "agent not working", "check plugin structure", or reports plugin-related issues.
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 claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Modular Claude Code plugins organized into workflows and technologies.
Waypoint is a collection of Claude agents, commands, and skills organized into two categories:
Each category is a plugin with its own .claude-plugin/plugin.json manifest.
Install Waypoint as a Claude Code plugin:
# Clone the repository
git clone [email protected]:poindexter12/waypoint.git
# The plugin system will automatically discover and load the plugins
# Just ensure the repository is accessible to Claude Code
Waypoint uses the Claude Code plugin system. Each subdirectory (workflows/, technologies/, claire/) contains a .claude-plugin/plugin.json manifest that defines the available agents, commands, and skills.
Operational tooling that enhances development workflows.
Agents: consultant - Git worktree strategy and organization
Commands: /working-tree:new, /working-tree:status, /working-tree:list, /working-tree:destroy, /working-tree:adopt
Skills: working-tree - Worktree patterns and templates
Domain knowledge for infrastructure tools.
Agents:
terraform - Terraform/IaC patterns and best practicesansible - Ansible playbooks and automationdocker-compose - Docker and container orchestrationproxmox - Proxmox virtualization platformSkills:
terraform - HCL patterns, state management, Proxmox provideransible - Playbooks, inventory, modulesdocker - Dockerfile, Compose, networkingproxmox - VMs, LXC, storage, clusteringTools for creating and optimizing Claude Code components.
Commands: /claire:fetch-docs
Agents: coordinator, author-agent, author-command
Skills: doc-validator
waypoint/
├── .claude-plugin/plugin.json # Root plugin index
├── workflows/ # Operational tooling
│ ├── .claude-plugin/plugin.json
│ ├── agents/consultant.md
│ ├── commands/*.md
│ └── skills/working-tree/
├── technologies/ # Domain knowledge
│ ├── .claude-plugin/plugin.json
│ ├── agents/*.md # terraform, ansible, docker, proxmox
│ └── skills/*/ # Per-technology skills
└── claire/ # Meta-tooling
├── .claude-plugin/plugin.json
├── agents/
├── commands/
└── skills/
The Makefile provides tools for managing plugin manifests and versions.
| Target | Description |
|---|---|
help | Show all available commands (default) |
manifest | Update plugin.json files from directory contents |
version V=x.y.z | Bump version in all plugin.json files |
changelog-preview | Show commits since last version tag |
clean | Remove build artifacts |
# Update all plugin.json manifests from directory contents
make manifest
# Bump all versions to 1.2.0
make version V=1.2.0
# Preview unreleased changes for changelog
make changelog-preview
Add a new workflow agent/command:
workflows/agents/workflows/commands/workflows/skills/Add a new technology:
technologies/agents/my-tech.mdtechnologies/skills/my-tech/SKILL.mdtechnologies/skills/my-tech/references/Then run make manifest to update plugin.json files.
Each plugin category follows this pattern:
plugin-category/
├── .claude-plugin/
│ └── plugin.json # Plugin manifest (auto-updated by make manifest)
├── agents/
│ └── *.md # Agent definitions
├── commands/
│ └── *.md # Command definitions (workflows only)
└── skills/
└── skill-name/ # Skill directories
├── SKILL.md # Required: skill definition
├── REFERENCE.md # Optional: detailed documentation
└── references/ # Optional: additional docs
Slash Command Files (commands/*.md) use YAML frontmatter with these allowed fields:
npx claudepluginhub poindexter12/waypointOperational tooling for development workflows - git worktree management, GitHub issues backlog
Domain knowledge for infrastructure technologies - Terraform, OpenTofu, Packer, Ansible, Docker, Proxmox
Git workflow commands and the Will Haacket agent - a modern take on GitHub Flow aliases
Multi-agent orchestration system with MCP tools and Claude Code plugin agents. 51 specialized agents for development workflows, code quality, deployment, research, and more.
Comprehensive plugin development toolkit for creating Claude Code plugins with AI-powered guidance for skills, agents, commands, and hooks
High-intelligence Claude Code copilot with deep code reasoning, evidence-driven planning, orchestration-first execution, model routing, context budgeting, CI/CD integration, enterprise security, plugin development, prompt engineering, performance profiling, agent teams, channels (event-driven autonomy with CI webhook, mobile approval relay, Discord bridge, and fakechat dev profile), interactive tutorials, LSP integration, security-hardened hook script library, MCP Prompts coverage, common workflow packs, runtime selection guide, computer-use patterns, checkpointing, scheduled-task blueprints, repo bootstrap scanner, hook policy engine (8 installable packs), layered memory deployment, role-based subagent packs (implementer, debugger, migration-lead, dependency-auditor, release-coordinator), 5 agent-team topology kits, autonomy operating mode (4 profiles + 3 gates), and a queryable 15-tool MCP documentation server with autonomy advisor.
Infrastructure management discipline: Ansible automation, container orchestration, Proxmox virtualization, Unraid NAS, and network architecture
Complete developer toolkit for Claude Code
Custom commands, skills, agents, rules, hooks, and output styles for Claude Code - session continuity and modern CLI tooling for real-world development workflows