Skill Permissions

All skills & plugins / Claude Code official plugins

plugin-dev

Comprehensive toolkit for developing Claude Code plugins. Includes 7 expert skills covering hooks, MCP integration, commands, agents, and best practices. AI-assisted plugin creation and validation.

Type
Plugin with 7 skills by Anthropic
Catalog
Claude Code official plugins
Source
anthropics/claude-plugins-official/plugins/plugin-dev (60 files scanned)
Install and details
Agent Skills Index entry
License
Apache-2.0 (LICENSE file)
Signals
Pre-approved shellBundled scripts

Pre-approved tools

Shell (any command). Tools listed in allowed-tools (or an agent's tools) can be used without a permission prompt while the skill is active, depending on your agent and settings.

KindTools
read/searchReadGrepGlobTodoWriteAskUserQuestion
shell, any commandBash
write/edit filesWrite
sub-agentsSkillTask

Declared in agents/plugin-validator.md, agents/skill-reviewer.md, agents/agent-creator.md, commands/create-plugin.md.

Hooks

No hooks.

MCP servers and apps

None.

Bundled code

10 code files (Shell):

Network calls

No HTTP or socket call pattern found in the code.

Starts other programs

No subprocess, exec or eval pattern found.

Credentials referenced

No key, token or secret environment variable found in code or MCP config.

Static scan of commit 41f619d on 2026-10-27. Signals are patterns found in the files, not a verdict: a network call can be the whole point of a skill. Read the linked lines before you decide. How the scan works.