~ / rigs / joelpt / claude-plugin-plugin-dev

joelpt/claude-plugin-plugin-dev

Claude Code plugin development skills (hook, command, skill, agent, MCP, settings, structure). Slim wrappers over anthropics/claude-plugins-public.

↗ GitHub ★ 0 MIT updated 4mo ago project Claude Code Claude plugin
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~299 tokens
Featherweight · median rig: 2.2k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit joelpt/claude-plugin-plugin-dev/agents ./rig-claude-plugin-plugin-dev/agents
$ npx degit joelpt/claude-plugin-plugin-dev/commands ./rig-claude-plugin-plugin-dev/commands
$ npx degit joelpt/claude-plugin-plugin-dev/skills ./rig-claude-plugin-plugin-dev/skills

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ npx degit joelpt/claude-plugin-plugin-dev/skills/agent-development .claude/skills/agent-development
$ npx degit joelpt/claude-plugin-plugin-dev/skills/command-development .claude/skills/command-development
$ npx degit joelpt/claude-plugin-plugin-dev/skills/hook-development .claude/skills/hook-development
$ npx degit joelpt/claude-plugin-plugin-dev/skills/mcp-integration .claude/skills/mcp-integration
$ npx degit joelpt/claude-plugin-plugin-dev/skills/plugin-settings .claude/skills/plugin-settings
$ npx degit joelpt/claude-plugin-plugin-dev/skills/plugin-structure .claude/skills/plugin-structure
$ npx degit joelpt/claude-plugin-plugin-dev/skills/skill-development .claude/skills/skill-development
$ curl -fsSL --create-dirs -o .claude/agents/agent-creator.md https://raw.githubusercontent.com/joelpt/claude-plugin-plugin-dev/main/agents/agent-creator.md
$ curl -fsSL --create-dirs -o .claude/agents/plugin-validator.md https://raw.githubusercontent.com/joelpt/claude-plugin-plugin-dev/main/agents/plugin-validator.md
$ curl -fsSL --create-dirs -o .claude/agents/skill-reviewer.md https://raw.githubusercontent.com/joelpt/claude-plugin-plugin-dev/main/agents/skill-reviewer.md

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,413 rigs:

{
  "permissions": {
    "deny": [
      "Read(~/.ssh/**)",
      "Read(**/.env)",
      "Bash(rm -rf *)",
      "Read(./.env)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /*)",
      "Read(~/.aws/**)",
      "Bash(rm -rf:*)",
      "Read(.env)",
      "Bash(git push --force*)",
      "Read(**/*.key)",
      "Read(./.env.*)",
      "Read(**/.env.*)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(gh pr merge *)",
      "Bash(chown *)",
      "Bash(docker *)"
    ]
  }
}

Skills (7)

Subagents (3)

agent-creatorUse this agent when the user asks to create, generate, or build a new Claude Code plugin agent. Trigger when user wants to create autonomous agents for plugins.
plugin-validatorUse this agent when the user asks to validate a plugin, check plugin structure, verify plugin.json, or check plugin files. Also trigger proactively after plugin creation or modification.
skill-reviewerUse this agent when the user has created or modified a plugin skill and wants quality review, or asks to review, check, or improve a skill. Trigger proactively after skill creation.

Slash commands (1)

/create-plugin

Similar rigs

copied ✓