Guide for integrating Agentica SDK with Claude Code CLI proxy
Modular Code Organization
Token-efficient code analysis via 5-layer stack (AST, Call Graph, CFG, DFG, PDG). 95% token savings.
Find unused functions and dead code in the codebase
Complete Claude Code hooks reference - input/output schemas, registration, testing patterns
Claude Code CLI commands, flags, headless mode, and automation patterns
Create and configure Claude Code sub-agents with custom prompts, tools, and models
Analyze Claude Code sessions via Braintrust
Meta-skill for creating and managing Claude Code skills
Braintrust tracing for Claude Code - hook architecture, sub-agent correlation, debugging
Create and use Claude Code slash commands - quick prompts, bash execution, file references
Update model references in skill files when new Claude models are released
This skill provides guidance on using OpenAI's Codex CLI for detail-oriented code analysis. Use when the user explicitly invokes "/codex", asks to "use codex", "run codex", "have codex review", or...
Show users how Continuous Claude works - the opinionated setup with hooks, memory, and coordination
Run automated tests to validate plugin integrity
Comprehensive code review workflow - parallel specialized reviews β synthesis
Code refactoring workflow - analyze β plan β implement β review β validate
Agentica server + Claude proxy setup - architecture, startup sequence, debugging
Subject's own words - tweets, blogs, forums, chat logs
Automated browser-based document search and retrieval from free public sources