advanced-features-2025
Advanced Claude Code plugin features for hooks, MCP integration, team distribution, and progressive disclosure. PROACTIVELY activate for: (1) progressive disclosure design, (2) hook automation, (3) PreToolUse and PostToolUse hooks, (4) MCP server integration, (5) .mcp.json configuration, (6) team plugin distribution, (7) repository-level plugin layouts, (8) context efficiency, (9) private marketplaces, (10) ${CLAUDE_PLUGIN_ROOT}. Provides: hooks reference, MCP patterns, team distribution, and context-efficiency guidance.
How do I install this agent skill?
npx skills add https://github.com/josiahsiegel/claude-plugin-marketplace --skill advanced-features-2025Is this agent skill safe to install?
- Gen Agent Trust Hubpass
This skill is a documentation and reference guide for advanced Claude Code plugin features. It provides patterns for lifecycle hooks, MCP integrations, and team configuration. While it includes shell scripts for automation, it also provides defensive examples to block dangerous command patterns.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
- Runlayerwarn
5/5 files flagged
What does this agent skill do?
Advanced Plugin Features (2025)
Quick Reference
| Feature | Location | Purpose |
|---|---|---|
| Agent Skills | skills/*/SKILL.md | Dynamic knowledge loading |
| Hooks | hooks/hooks.json | Event automation |
| MCP Servers | .mcp.json | External integrations |
| Team Config | .claude/settings.json | Repository plugins |
| Hook Event | When Fired | Use Case |
|---|---|---|
| PreToolUse | Before tool | Validation |
| PostToolUse | After tool | Testing, linting |
| SessionStart | Session begins | Logging, setup |
| SessionEnd | Session ends | Cleanup |
| UserPromptSubmit | Prompt submitted | Preprocessing |
| PreCompact | Before compact | State save |
| Notification | Notification shown | Custom alerts |
| Stop | User stops | Cleanup |
| SubagentStop | Subagent ends | Logging |
| Variable | Purpose |
|---|---|
${CLAUDE_PLUGIN_ROOT} | Plugin installation path |
${TOOL_INPUT_*} | Tool input parameters |
Agent Skills
Concept
Skills are dynamically loaded based on task context, enabling:
- Unbounded capacity: Knowledge split across files
- Context efficiency: Only load what's needed
- Progressive disclosure: Three-tier loading
Three-Tier Loading
- Frontmatter: Loaded at startup (triggers)
- SKILL.md body: Loaded on activation
- references/: Loaded when detail needed
Structure
skills/
└── skill-name/
├── SKILL.md # Core content
├── references/ # Detailed docs
│ └── deep-dive.md
├── examples/ # Working code
│ └── example.md
└── scripts/ # Utilities
└── tool.sh
SKILL.md Format
---
name: skill-name
description: |
When to activate this skill. Include:
(1) Use case 1
(2) Use case 2
Provides: what it offers
---
# Skill Title
## Quick Reference
[Tables, key points]
## Core Content
[Essential information - keep lean]
## Additional Resources
See `references/` for detailed guidance.
Hooks
Configuration
Inline in plugin.json:
{
"hooks": {
"PostToolUse": [{
"matcher": "Write|Edit",
"hooks": [{
"type": "command",
"command": "${CLAUDE_PLUGIN_ROOT}/scripts/lint.sh"
}]
}]
}
}
Separate hooks.json:
{
"PostToolUse": [{
"matcher": "Write",
"hooks": [{
"type": "command",
"command": "${CLAUDE_PLUGIN_ROOT}/scripts/format.sh",
"timeout": 5000
}]
}]
}
Matchers
Write- File writesEdit- File editsBash- Shell commandsWrite|Edit- Multiple tools.*- Any tool (use sparingly)
Common Patterns
Auto-test after changes:
{
"PostToolUse": [{
"matcher": "Write|Edit",
"hooks": [{
"type": "command",
"command": "${CLAUDE_PLUGIN_ROOT}/scripts/run-tests.sh"
}]
}]
}
Validate before Bash:
{
"PreToolUse": [{
"matcher": "Bash",
"hooks": [{
"type": "command",
"command": "${CLAUDE_PLUGIN_ROOT}/scripts/validate-cmd.sh"
}]
}]
}
MCP Server Integration
Configuration
{
"mcpServers": {
"server-name": {
"command": "node",
"args": ["${CLAUDE_PLUGIN_ROOT}/mcp/server.js"],
"env": {
"API_KEY": "${API_KEY}"
}
}
}
}
External Services
{
"mcpServers": {
"stripe": {
"command": "npx",
"args": ["-y", "@stripe/mcp-server"],
"env": {
"STRIPE_API_KEY": "${STRIPE_API_KEY}"
}
}
}
}
Repository Configuration
Team Distribution
Create .claude/settings.json at repo root:
{
"extraKnownMarketplaces": [
"company/internal-plugins"
],
"plugins": {
"enabled": [
"deployment-helper@company",
"code-standards@company"
]
}
}
Workflow
- Maintainer creates
.claude/settings.json - Team members clone repo
- Trust folder when prompted
- Plugins install automatically
Best Practices
Progressive Disclosure
- Keep SKILL.md under 500 lines
- Move details to
references/ - Use
examples/for working code - Reference files with relative paths
Hooks
- Use specific matchers (avoid
.*) - Set reasonable timeouts
- Use
${CLAUDE_PLUGIN_ROOT}for paths - Test scripts independently
MCP
- Document required env vars
- Provide setup instructions
- Use environment variables for secrets
- Test connection before distribution
Additional Resources
For detailed patterns, see:
references/hooks-advanced.md- Complete hook patternsreferences/mcp-patterns.md- MCP integration examplesreferences/team-distribution.md- Repository configurationexamples/hook-scripts.md- Working hook scripts
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/josiahsiegel/claude-plugin-marketplace/advanced-features-2025">View advanced-features-2025 on skillZs</a>