Agent skills for deep code review and grounded investigation.

Code review skills for PHP, TypeScript, and Python: comment audit, writing comments, type-safety review, correctness review, a three-stage PR review orchestrator, and PR comments

• 6 skills
• any language

1. 1/plugin marketplace add noppu-labs/ai-toolkit
   Copy
2. 2/plugin install review@ai-toolkit
   Copy

Deterministic structural briefs and two-pass code investigations: brief, module, and spec review skills

• 3 skills
• any language

1. 1/plugin marketplace add noppu-labs/ai-toolkit
   Copy
2. 2/plugin install investigate@ai-toolkit
   Copy

Backend skills, a specialist agent and path-scoped rules for Laravel 13 apps: controllers, models, DTOs, policies, testing and security.

• 16 skills
• 1 agent
• 4 rules

1. 1/plugin marketplace add noppu-labs/ai-toolkit
   Copy
2. 2/plugin install laravel@ai-toolkit
   Copy

Frontend skills, a specialist agent and path-scoped rules for Inertia v3 + React 19 + TypeScript: shadcn, Tailwind, state management and Vite performance.

• 6 skills
• 1 agent
• 2 rules

1. 1/plugin marketplace add noppu-labs/ai-toolkit
   Copy
2. 2/plugin install inertia-react@ai-toolkit
   Copy

An AI reviewer answers OpenCode's permission prompts. Routine actions go through, risky ones are blocked with a reason, and the rest come to you.

• OpenCode V1 + V2
• TUI overlay
• runs headless
• audit log

Pick a 5m, 1h or hybrid prompt-cache TTL per session, and keep idle caches warm with keepalive pings. Tuned for Claude and GPT-5.6+.

• OpenCode V2
• Claude + GPT-5.6+
• keepalive pings
• sidebar readout