By SuedePritch
A comprehensive toolkit for creating, validating, and distributing Claude Code plugins
Create a new sub-agent file with proper frontmatter and structure.
Create a new slash command file with proper frontmatter and structure.
Add or update hooks.json with a new hook configuration for automated behavior.
Create a new Skill folder with SKILL.md and supporting directories.
Scaffold a new Claude Code plugin with standard structure and starter files
Modifies files
Hook triggers on file write and edit operations
Runs pre-commands
Contains inline bash commands via ! syntax
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.
Bash prerequisite issue
Uses bash pre-commands but Bash not in allowed tools
Bash prerequisite issue
Uses bash pre-commands but Bash not in allowed tools
An autonomous task-driven loop that works through your TASKLIST.md independently. Claude keeps working until all tasks are complete.
# Add the marketplace
/plugin marketplace add SuedePritch/Independent
# Install the plugin
/plugin install independent@jamespritchard-plugins
In your project, create .claude/TASKLIST.md:
- [ ] Refactor the authentication module
- [ ] Add unit tests for user service
- [ ] Update API documentation
- [ ] Fix the bug in checkout flow
/independent
Claude will:
Tasks are tracked with checkboxes:
- [ ] = pending- [x] = completeClaude marks tasks complete automatically, or you can check them off manually.
The plugin uses Claude Code hooks to enforce task completion:
| Hook | Purpose |
|---|---|
| SessionStart | Clears session log for fresh starts |
| PreToolUse | Monitors task progress, enforces agent ownership |
| PostToolUse | Tracks agent invocations |
| Stop | Blocks exit if tasks remain incomplete |
| SubagentStart | Injects pending task context into subagents |
When you try to exit with incomplete tasks, the Stop hook blocks it and shows remaining work.
Updates are automatic. When a new version is pushed, run:
/plugin install independent@jamespritchard-plugins
independent/
├── .claude-plugin/
│ └── plugin.json # Plugin metadata
├── commands/
│ └── independent.md # The /independent command
├── hooks/
│ ├── hooks.json # Hook configuration
│ ├── session-start.sh # Session initialization
│ ├── pretooluse-hook.sh
│ ├── post-tool-use.sh
│ ├── stop-hook.sh # Exit gate
│ └── subagentstart-hook.sh
└── scripts/
└── setup-independent.sh
MIT
npx claudepluginhub suedepritch/independent --plugin plugin-developmentAutonomous task-driven loop that works through TASKLIST.md independently
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
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.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Complete developer toolkit for Claude Code
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer