From 545c69c03ba1c40b601cc45a6f56f83996093149 Mon Sep 17 00:00:00 2001 From: Seth Hobson Date: Thu, 31 Jul 2025 16:42:27 -0400 Subject: [PATCH] Update README.md with simplified model naming convention - Fixed merge conflict in legal-advisor description - Updated all model names from full identifiers to simplified names (opus/sonnet/haiku) - Corrected Sonnet agent count from 26 to 27 (added php-pro) - Updated section headers to reflect simplified naming - Updated model configuration documentation to clarify v1.0.64 naming convention - Updated subagent format example to show simplified model specification --- README.md | 32 +++++++++++++++----------------- 1 file changed, 15 insertions(+), 17 deletions(-) diff --git a/README.md b/README.md index dbad81f..fe3ab51 100644 --- a/README.md +++ b/README.md @@ -66,17 +66,14 @@ This repository contains 46 specialized subagents that extend Claude Code's capa - **[content-marketer](content-marketer.md)** - Write blog posts, social media content, and email newsletters - **[sales-automator](sales-automator.md)** - Draft cold emails, follow-ups, and proposal templates - **[customer-support](customer-support.md)** - Handle support tickets, FAQ responses, and customer emails -<<<<<<< HEAD - **[legal-advisor](legal-advisor.md)** - Draft privacy policies, terms of service, disclaimers, and legal notices -======= -- **[legal-advisor](legal-advisor.md)** - Draft privacy policies, terms of service, and compliance documents ## Model Assignments All 46 subagents are configured with specific Claude models based on task complexity: -### 🚀 Claude Haiku 3.5 (Fast & Cost-Effective) - 8 agents -**Model:** `claude-3-5-haiku-20241022` +### 🚀 Haiku (Fast & Cost-Effective) - 8 agents +**Model:** `haiku` - `data-scientist` - SQL queries and data analysis - `api-documenter` - OpenAPI/Swagger documentation - `business-analyst` - Metrics and KPI tracking @@ -86,8 +83,8 @@ All 46 subagents are configured with specific Claude models based on task comple - `search-specialist` - Web research and information gathering - `legal-advisor` - Privacy policies and compliance documents -### ⚡ Claude Sonnet 4 (Balanced Performance) - 26 agents -**Model:** `claude-sonnet-4-20250514` +### ⚡ Sonnet (Balanced Performance) - 27 agents +**Model:** `sonnet` **Development & Languages:** - `python-pro` - Python development with advanced features @@ -96,6 +93,7 @@ All 46 subagents are configured with specific Claude models based on task comple - `rust-pro` - Rust memory safety and systems programming - `c-pro` - C programming and embedded systems - `cpp-pro` - Modern C++ with STL and templates +- `php-pro` - Modern PHP with advanced features - `frontend-developer` - React components and UI - `backend-architect` - API design and microservices - `mobile-developer` - React Native/Flutter apps @@ -121,8 +119,8 @@ All 46 subagents are configured with specific Claude models based on task comple - `legacy-modernizer` - Framework migrations - `payment-integration` - Payment processing -### 🧠 Claude Opus 4 (Maximum Capability) - 11 agents -**Model:** `claude-opus-4-20250514` +### 🧠 Opus (Maximum Capability) - 11 agents +**Model:** `opus` - `ai-engineer` - LLM applications and RAG systems - `security-auditor` - Vulnerability analysis - `performance-engineer` - Application optimization @@ -246,7 +244,7 @@ Each subagent follows this structure: --- name: subagent-name description: When this subagent should be invoked -model: claude-3-5-haiku-20241022 # Optional - specify which model to use +model: haiku # Optional - specify which model to use (haiku/sonnet/opus) tools: tool1, tool2 # Optional - defaults to all tools --- @@ -257,14 +255,14 @@ System prompt defining the subagent's role and capabilities As of Claude Code v1.0.64, subagents can specify which Claude model they should use. This allows for cost-effective task delegation based on complexity: -- **Low Complexity (Haiku 3.5)**: Simple tasks like basic data analysis, documentation generation, and standard responses -- **Medium Complexity (Sonnet 4)**: Development tasks, code review, testing, and standard engineering work -- **High Complexity (Opus 4)**: Critical tasks like security auditing, architecture review, incident response, and AI/ML engineering +- **Low Complexity (Haiku)**: Simple tasks like basic data analysis, documentation generation, and standard responses +- **Medium Complexity (Sonnet)**: Development tasks, code review, testing, and standard engineering work +- **High Complexity (Opus)**: Critical tasks like security auditing, architecture review, incident response, and AI/ML engineering -Available models: -- `claude-3-5-haiku-20241022` - Fast and cost-effective for simple tasks -- `claude-sonnet-4-20250514` - Balanced performance for most development work -- `claude-opus-4-20250514` - Most capable for complex analysis and critical tasks +Available models (using simplified naming as of Claude Code v1.0.64): +- `haiku` - Fast and cost-effective for simple tasks +- `sonnet` - Balanced performance for most development work +- `opus` - Most capable for complex analysis and critical tasks If no model is specified, the subagent will use the system's default model.