dpnmw/agents
1
0
Fork 0
mirror of https://github.com/wshobson/agents.git synced 2026-03-18 09:37:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

chore: update model references to Claude 4.6 and GPT-5.2

Browse Source 
- Claude Opus 4.5 → Opus 4.6, Claude Sonnet 4.5 → Sonnet 4.6 (Haiku stays 4.5)
- Update claude-sonnet-4-5 model IDs to claude-sonnet-4-6 in code examples
- Update SWE-bench stat from 80.9% to 80.8% for Opus 4.6
- Update GPT refs: GPT-5 → GPT-5.2, GPT-4o → gpt-5.2, GPT-4o-mini → GPT-5-mini
- Fix GPT-5.2-mini → GPT-5-mini (correct model name per OpenAI)
- Bump marketplace to v1.5.2 and affected plugin versions
This commit is contained in:
Seth Hobson
2026-02-19 14:03:46 -05:00
parent 5d65aa1063
commit 086557180a
19 changed files with 62 additions and 62 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
.claude-plugin/marketplace.json
View File

@@ -7,7 +7,7 @@
}, },
"metadata": { "metadata": {
"description": "Production-ready workflow orchestration with 73 focused plugins, 112 specialized agents, and 146 skills - optimized for granular installation and minimal token usage", "description": "Production-ready workflow orchestration with 73 focused plugins, 112 specialized agents, and 146 skills - optimized for granular installation and minimal token usage",
"version": "1.5.1" "version": "1.5.2"
}, },
"plugins": [ "plugins": [
{ {
@@ -118,7 +118,7 @@
"name": "code-review-ai", "name": "code-review-ai",
"source": "./plugins/code-review-ai", "source": "./plugins/code-review-ai",
"description": "AI-powered architectural review and code quality analysis", "description": "AI-powered architectural review and code quality analysis",
"version": "1.2.0", "version": "1.2.1",
"author": { "author": {
"name": "Seth Hobson", "name": "Seth Hobson",
"email": "seth@major7apps.com" "email": "seth@major7apps.com"
@@ -181,8 +181,8 @@
}, },
{ {
"name": "llm-application-dev", "name": "llm-application-dev",
"description": "LLM application development with LangGraph, RAG systems, vector search, and AI agent architectures for Claude 4.5 and GPT-5.2", "description": "LLM application development with LangGraph, RAG systems, vector search, and AI agent architectures for Claude 4.6 and GPT-5.2",
"version": "2.0.3", "version": "2.0.4",
"author": { "author": {
"name": "Seth Hobson", "name": "Seth Hobson",
"email": "seth@major7apps.com" "email": "seth@major7apps.com"
@@ -196,7 +196,7 @@
"name": "agent-orchestration", "name": "agent-orchestration",
"source": "./plugins/agent-orchestration", "source": "./plugins/agent-orchestration",
"description": "Multi-agent system optimization, agent improvement workflows, and context management", "description": "Multi-agent system optimization, agent improvement workflows, and context management",
"version": "1.2.0", "version": "1.2.1",
"author": { "author": {
"name": "Seth Hobson", "name": "Seth Hobson",
"email": "seth@major7apps.com" "email": "seth@major7apps.com"
@@ -404,7 +404,7 @@
"name": "performance-testing-review", "name": "performance-testing-review",
"source": "./plugins/performance-testing-review", "source": "./plugins/performance-testing-review",
"description": "Performance analysis, test coverage review, and AI-powered code quality assessment", "description": "Performance analysis, test coverage review, and AI-powered code quality assessment",
"version": "1.2.0", "version": "1.2.1",
"author": { "author": {
"name": "Seth Hobson", "name": "Seth Hobson",
"email": "seth@major7apps.com" "email": "seth@major7apps.com"

14
README.md
View File

@@ -1,6 +1,6 @@
# Claude Code Plugins: Orchestration and Automation # Claude Code Plugins: Orchestration and Automation
> **⚡ Updated for Opus 4.5, Sonnet 4.5 & Haiku 4.5** — Three-tier model strategy for optimal performance > **⚡ Updated for Opus 4.6, Sonnet 4.6 & Haiku 4.5** — Three-tier model strategy for optimal performance
[![Run in Smithery](https://smithery.ai/badge/skills/wshobson)](https://smithery.ai/skills?ns=wshobson&utm_source=github&utm_medium=badge) [![Run in Smithery](https://smithery.ai/badge/skills/wshobson)](https://smithery.ai/skills?ns=wshobson&utm_source=github&utm_medium=badge)
@@ -203,14 +203,14 @@ Strategic model assignment for optimal performance and cost:
| Tier | Model | Agents | Use Case | | Tier | Model | Agents | Use Case |
| ---------- | -------- | ------ | ----------------------------------------------------------------------------------------------- | | ---------- | -------- | ------ | ----------------------------------------------------------------------------------------------- |
| **Tier 1** | Opus 4.5 | 42 | Critical architecture, security, ALL code review, production coding (language pros, frameworks) | | **Tier 1** | Opus 4.6 | 42 | Critical architecture, security, ALL code review, production coding (language pros, frameworks) |
| **Tier 2** | Inherit | 42 | Complex tasks - user chooses model (AI/ML, backend, frontend/mobile, specialized) | | **Tier 2** | Inherit | 42 | Complex tasks - user chooses model (AI/ML, backend, frontend/mobile, specialized) |
| **Tier 3** | Sonnet | 51 | Support with intelligence (docs, testing, debugging, network, API docs, DX, legacy, payments) | | **Tier 3** | Sonnet | 51 | Support with intelligence (docs, testing, debugging, network, API docs, DX, legacy, payments) |
| **Tier 4** | Haiku | 18 | Fast operational tasks (SEO, deployment, simple docs, sales, content, search) | | **Tier 4** | Haiku | 18 | Fast operational tasks (SEO, deployment, simple docs, sales, content, search) |
**Why Opus 4.5 for Critical Agents?** **Why Opus 4.6 for Critical Agents?**
- 80.9% on SWE-bench (industry-leading) - 80.8% on SWE-bench (industry-leading)
- 65% fewer tokens for complex tasks - 65% fewer tokens for complex tasks
- Best for architecture decisions and security audits - Best for architecture decisions and security audits
@@ -218,14 +218,14 @@ Strategic model assignment for optimal performance and cost:
Agents marked `inherit` use your session's default model, letting you balance cost and capability: Agents marked `inherit` use your session's default model, letting you balance cost and capability:
- Set via `claude --model opus` or `claude --model sonnet` when starting a session - Set via `claude --model opus` or `claude --model sonnet` when starting a session
- Falls back to Sonnet 4.5 if no default specified - Falls back to Sonnet 4.6 if no default specified
- Perfect for frontend/mobile developers who want cost control - Perfect for frontend/mobile developers who want cost control
- AI/ML engineers can choose Opus for complex model work - AI/ML engineers can choose Opus for complex model work
**Cost Considerations:** **Cost Considerations:**
- **Opus 4.5**: $5/$25 per million input/output tokens - Premium for critical work - **Opus 4.6**: $5/$25 per million input/output tokens - Premium for critical work
- **Sonnet 4.5**: $3/$15 per million tokens - Balanced performance/cost - **Sonnet 4.6**: $3/$15 per million tokens - Balanced performance/cost
- **Haiku 4.5**: $1/$5 per million tokens - Fast, cost-effective operations - **Haiku 4.5**: $1/$5 per million tokens - Fast, cost-effective operations
- Opus's 65% token reduction on complex tasks often offsets higher rate - Opus's 65% token reduction on complex tasks often offsets higher rate
- Use `inherit` tier to control costs for high-volume use cases - Use `inherit` tier to control costs for high-volume use cases

2
plugins/agent-orchestration/.claude-plugin/plugin.json
View File

@@ -1,6 +1,6 @@
{ {
"name": "agent-orchestration", "name": "agent-orchestration",
"version": "1.2.0", "version": "1.2.1",
"description": "Multi-agent system optimization, agent improvement workflows, and context management", "description": "Multi-agent system optimization, agent improvement workflows, and context management",
"author": { "author": {
"name": "Seth Hobson", "name": "Seth Hobson",

2
plugins/agent-orchestration/commands/multi-agent-optimize.md
View File

@@ -146,7 +146,7 @@ class CostOptimizer:
self.token_budget = 100000 # Monthly budget self.token_budget = 100000 # Monthly budget
self.token_usage = 0 self.token_usage = 0
self.model_costs = { self.model_costs = {
'gpt-5': 0.03, 'gpt-5.2': 0.03,
'claude-4-sonnet': 0.015, 'claude-4-sonnet': 0.015,
'claude-4-haiku': 0.0025 'claude-4-haiku': 0.0025
} }

2
plugins/code-review-ai/.claude-plugin/plugin.json
View File

@@ -1,6 +1,6 @@
{ {
"name": "code-review-ai", "name": "code-review-ai",
"version": "1.2.0", "version": "1.2.1",
"description": "AI-powered architectural review and code quality analysis", "description": "AI-powered architectural review and code quality analysis",
"author": { "author": {
"name": "Seth Hobson", "name": "Seth Hobson",

16
plugins/code-review-ai/commands/ai-review.md
View File

@@ -1,6 +1,6 @@
# AI-Powered Code Review Specialist # AI-Powered Code Review Specialist
You are an expert AI-powered code review specialist combining automated static analysis, intelligent pattern recognition, and modern DevOps practices. Leverage AI tools (GitHub Copilot, Qodo, GPT-5, Claude 4.5 Sonnet) with battle-tested platforms (SonarQube, CodeQL, Semgrep) to identify bugs, vulnerabilities, and performance issues. You are an expert AI-powered code review specialist combining automated static analysis, intelligent pattern recognition, and modern DevOps practices. Leverage AI tools (GitHub Copilot, Qodo, GPT-5.2, Claude 4.6 Sonnet) with battle-tested platforms (SonarQube, CodeQL, Semgrep) to identify bugs, vulnerabilities, and performance issues.
## Context ## Context
@@ -34,7 +34,7 @@ Execute in parallel:
### AI-Assisted Review ### AI-Assisted Review
```python ```python
# Context-aware review prompt for Claude 4.5 Sonnet # Context-aware review prompt for Claude 4.6 Sonnet
review_prompt = f""" review_prompt = f"""
You are reviewing a pull request for a {language} {project_type} application. You are reviewing a pull request for a {language} {project_type} application.
@@ -64,8 +64,8 @@ Format as JSON array.
### Model Selection (2025) ### Model Selection (2025)
- **Fast reviews (<200 lines)**: GPT-4o-mini or Claude 4.5 Haiku - **Fast reviews (<200 lines)**: GPT-5-mini or Claude 4.5 Haiku
- **Deep reasoning**: Claude 4.5 Sonnet or GPT-5 (200K+ tokens) - **Deep reasoning**: Claude 4.6 Sonnet or GPT-5.2 (200K+ tokens)
- **Code generation**: GitHub Copilot or Qodo - **Code generation**: GitHub Copilot or Qodo
- **Multi-language**: Qodo or CodeAnt AI (30+ languages) - **Multi-language**: Qodo or CodeAnt AI (30+ languages)
@@ -92,7 +92,7 @@ interface ReviewRoutingStrategy {
return new QodoEngine({ mode: "test-generation", coverageTarget: 80 }); return new QodoEngine({ mode: "test-generation", coverageTarget: 80 });
} }
return new AIEngine("gpt-4o", { temperature: 0.3, maxTokens: 2000 }); return new AIEngine("gpt-5.2", { temperature: 0.3, maxTokens: 2000 });
} }
} }
``` ```
@@ -312,13 +312,13 @@ jobs:
codeql database create codeql-db --language=javascript,python codeql database create codeql-db --language=javascript,python
semgrep scan --config=auto --sarif --output=semgrep.sarif semgrep scan --config=auto --sarif --output=semgrep.sarif
- name: AI-Enhanced Review (GPT-5) - name: AI-Enhanced Review (GPT-5.2)
env: env:
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }} OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
run: | run: |
python scripts/ai_review.py \ python scripts/ai_review.py \
--pr-number ${{ github.event.number }} \ --pr-number ${{ github.event.number }} \
--model gpt-4o \ --model gpt-5.2 \
--static-analysis-results codeql.sarif,semgrep.sarif --static-analysis-results codeql.sarif,semgrep.sarif
- name: Post Comments - name: Post Comments
@@ -446,7 +446,7 @@ if __name__ == '__main__':
Comprehensive AI code review combining: Comprehensive AI code review combining:
1. Multi-tool static analysis (SonarQube, CodeQL, Semgrep) 1. Multi-tool static analysis (SonarQube, CodeQL, Semgrep)
2. State-of-the-art LLMs (GPT-5, Claude 4.5 Sonnet) 2. State-of-the-art LLMs (GPT-5.2, Claude 4.6 Sonnet)
3. Seamless CI/CD integration (GitHub Actions, GitLab, Azure DevOps) 3. Seamless CI/CD integration (GitHub Actions, GitLab, Azure DevOps)
4. 30+ language support with language-specific linters 4. 30+ language support with language-specific linters
5. Actionable review comments with severity and fix examples 5. Actionable review comments with severity and fix examples

4
plugins/llm-application-dev/.claude-plugin/plugin.json
View File

@@ -1,7 +1,7 @@
{ {
"name": "llm-application-dev", "name": "llm-application-dev",
"description": "LLM application development with LangGraph, RAG systems, vector search, and AI agent architectures for Claude 4.5 and GPT-5.2", "description": "LLM application development with LangGraph, RAG systems, vector search, and AI agent architectures for Claude 4.6 and GPT-5.2",
"version": "2.0.3", "version": "2.0.4",
"author": { "author": {
"name": "Seth Hobson", "name": "Seth Hobson",
"email": "seth@major7apps.com" "email": "seth@major7apps.com"

4
plugins/llm-application-dev/README.md
View File

@@ -5,7 +5,7 @@ Build production-ready LLM applications, advanced RAG systems, and intelligent a
## Version 2.0.0 Highlights ## Version 2.0.0 Highlights
- **LangGraph Integration**: Updated from deprecated LangChain patterns to LangGraph StateGraph workflows - **LangGraph Integration**: Updated from deprecated LangChain patterns to LangGraph StateGraph workflows
- **Modern Model Support**: Claude Opus/Sonnet/Haiku 4.5 and GPT-5.2/GPT-5.2-mini - **Modern Model Support**: Claude Opus 4.6/Sonnet 4.6/Haiku 4.5 and GPT-5.2/GPT-5-mini
- **Voyage AI Embeddings**: Recommended embedding models for Claude applications - **Voyage AI Embeddings**: Recommended embedding models for Claude applications
- **Structured Outputs**: Pydantic-based structured output patterns - **Structured Outputs**: Pydantic-based structured output patterns
@@ -71,7 +71,7 @@ Build production-ready LLM applications, advanced RAG systems, and intelligent a
### 2.0.0 (January 2026) ### 2.0.0 (January 2026)
- **Breaking**: Migrated from LangChain 0.x to LangChain 1.x/LangGraph - **Breaking**: Migrated from LangChain 0.x to LangChain 1.x/LangGraph
- **Breaking**: Updated model references to Claude 4.5 and GPT-5.2 - **Breaking**: Updated model references to Claude 4.6 and GPT-5.2
- Added Voyage AI as primary embedding recommendation for Claude apps - Added Voyage AI as primary embedding recommendation for Claude apps
- Added LangGraph StateGraph patterns replacing deprecated `initialize_agent()` - Added LangGraph StateGraph patterns replacing deprecated `initialize_agent()`
- Added structured outputs with Pydantic - Added structured outputs with Pydantic

8
plugins/llm-application-dev/agents/ai-engineer.md
View File

@@ -14,8 +14,8 @@ Expert AI engineer specializing in LLM application development, RAG systems, and
### LLM Integration & Model Management ### LLM Integration & Model Management
- OpenAI GPT-5.2/GPT-5.2-mini with function calling and structured outputs - OpenAI GPT-5.2/GPT-5-mini with function calling and structured outputs
- Anthropic Claude Opus 4.5, Claude Sonnet 4.5, Claude Haiku 4.5 with tool use and computer use - Anthropic Claude Opus 4.6, Claude Sonnet 4.6, Claude Haiku 4.5 with tool use and computer use
- Open-source models: Llama 3.3, Mixtral 8x22B, Qwen 2.5, DeepSeek-V3 - Open-source models: Llama 3.3, Mixtral 8x22B, Qwen 2.5, DeepSeek-V3
- Local deployment with Ollama, vLLM, TGI (Text Generation Inference) - Local deployment with Ollama, vLLM, TGI (Text Generation Inference)
- Model serving with TorchServe, MLflow, BentoML for production deployment - Model serving with TorchServe, MLflow, BentoML for production deployment
@@ -76,7 +76,7 @@ Expert AI engineer specializing in LLM application development, RAG systems, and
### Multimodal AI Integration ### Multimodal AI Integration
- Vision models: GPT-4V, Claude 4 Vision, LLaVA, CLIP for image understanding - Vision models: GPT-5.2, Claude 4 Vision, LLaVA, CLIP for image understanding
- Audio processing: Whisper for speech-to-text, ElevenLabs for text-to-speech - Audio processing: Whisper for speech-to-text, ElevenLabs for text-to-speech
- Document AI: OCR, table extraction, layout understanding with models like LayoutLM - Document AI: OCR, table extraction, layout understanding with models like LayoutLM
- Video analysis and processing for multimedia applications - Video analysis and processing for multimedia applications
@@ -124,7 +124,7 @@ Expert AI engineer specializing in LLM application development, RAG systems, and
## Knowledge Base ## Knowledge Base
- Latest LLM developments and model capabilities (GPT-5.2, Claude 4.5, Llama 3.3) - Latest LLM developments and model capabilities (GPT-5.2, Claude 4.6, Llama 3.3)
- Modern vector database architectures and optimization techniques - Modern vector database architectures and optimization techniques
- Production AI system design patterns and best practices - Production AI system design patterns and best practices
- AI safety and security considerations for enterprise deployments - AI safety and security considerations for enterprise deployments

4
plugins/llm-application-dev/agents/prompt-engineer.md
View File

@@ -48,7 +48,7 @@ Expert prompt engineer specializing in advanced prompting methodologies and LLM
### Model-Specific Optimization ### Model-Specific Optimization
#### OpenAI Models (GPT-5.2, GPT-5.2-mini) #### OpenAI Models (GPT-5.2, GPT-5-mini)
- Function calling optimization and structured outputs - Function calling optimization and structured outputs
- JSON mode utilization for reliable data extraction - JSON mode utilization for reliable data extraction
@@ -58,7 +58,7 @@ Expert prompt engineer specializing in advanced prompting methodologies and LLM
- Multi-turn conversation management - Multi-turn conversation management
- Image and multimodal prompt engineering - Image and multimodal prompt engineering
#### Anthropic Claude (Claude Opus 4.5, Sonnet 4.5, Haiku 4.5) #### Anthropic Claude (Claude Opus 4.6, Sonnet 4.6, Haiku 4.5)
- Constitutional AI alignment with Claude's training - Constitutional AI alignment with Claude's training
- Tool use optimization for complex workflows - Tool use optimization for complex workflows

6
plugins/llm-application-dev/commands/langchain-agent.md
View File

@@ -37,7 +37,7 @@ class AgentState(TypedDict):
### Model & Embeddings ### Model & Embeddings
- **Primary LLM**: Claude Sonnet 4.5 (`claude-sonnet-4-5`) - **Primary LLM**: Claude Sonnet 4.6 (`claude-sonnet-4-6`)
- **Embeddings**: Voyage AI (`voyage-3-large`) - officially recommended by Anthropic for Claude - **Embeddings**: Voyage AI (`voyage-3-large`) - officially recommended by Anthropic for Claude
- **Specialized**: `voyage-code-3` (code), `voyage-finance-2` (finance), `voyage-law-2` (legal) - **Specialized**: `voyage-code-3` (code), `voyage-finance-2` (finance), `voyage-law-2` (legal)
@@ -158,7 +158,7 @@ from langsmith.evaluation import evaluate
# Run evaluation suite # Run evaluation suite
eval_config = RunEvalConfig( eval_config = RunEvalConfig(
evaluators=["qa", "context_qa", "cot_qa"], evaluators=["qa", "context_qa", "cot_qa"],
eval_llm=ChatAnthropic(model="claude-sonnet-4-5") eval_llm=ChatAnthropic(model="claude-sonnet-4-6")
) )
results = await evaluate( results = await evaluate(
@@ -209,7 +209,7 @@ async def call_with_retry():
## Implementation Checklist ## Implementation Checklist
- [ ] Initialize LLM with Claude Sonnet 4.5 - [ ] Initialize LLM with Claude Sonnet 4.6
- [ ] Setup Voyage AI embeddings (voyage-3-large) - [ ] Setup Voyage AI embeddings (voyage-3-large)
- [ ] Create tools with async support and error handling - [ ] Create tools with async support and error handling
- [ ] Implement memory system (choose type based on use case) - [ ] Implement memory system (choose type based on use case)

4
plugins/llm-application-dev/commands/prompt-optimize.md
View File

@@ -150,7 +150,7 @@ gpt5_optimized = """
```` ````
**Claude 4.5/4** **Claude 4.6/4.5**
```python ```python
claude_optimized = """ claude_optimized = """
<context> <context>
@@ -607,7 +607,7 @@ testing_recommendations:
metrics: ["accuracy", "satisfaction", "cost"] metrics: ["accuracy", "satisfaction", "cost"]
deployment_strategy: deployment_strategy:
model: "GPT-5.2 for quality, Claude 4.5 for safety" model: "GPT-5.2 for quality, Claude 4.6 for safety"
temperature: 0.7 temperature: 0.7
max_tokens: 2000 max_tokens: 2000
monitoring: "Track success, latency, feedback" monitoring: "Track success, latency, feedback"

10
plugins/llm-application-dev/skills/langchain-architecture/SKILL.md
View File

@@ -115,8 +115,8 @@ from langchain_core.tools import tool
import ast import ast
import operator import operator
# Initialize LLM (Claude Sonnet 4.5 recommended) # Initialize LLM (Claude Sonnet 4.6 recommended)
llm = ChatAnthropic(model="claude-sonnet-4-5", temperature=0) llm = ChatAnthropic(model="claude-sonnet-4-6", temperature=0)
# Define tools with Pydantic schemas # Define tools with Pydantic schemas
@tool @tool
@@ -201,7 +201,7 @@ class RAGState(TypedDict):
answer: str answer: str
# Initialize components # Initialize components
llm = ChatAnthropic(model="claude-sonnet-4-5") llm = ChatAnthropic(model="claude-sonnet-4-6")
embeddings = VoyageAIEmbeddings(model="voyage-3-large") embeddings = VoyageAIEmbeddings(model="voyage-3-large")
vectorstore = PineconeVectorStore(index_name="docs", embedding=embeddings) vectorstore = PineconeVectorStore(index_name="docs", embedding=embeddings)
retriever = vectorstore.as_retriever(search_kwargs={"k": 4}) retriever = vectorstore.as_retriever(search_kwargs={"k": 4})
@@ -489,7 +489,7 @@ os.environ["LANGCHAIN_API_KEY"] = "your-api-key"
os.environ["LANGCHAIN_PROJECT"] = "my-project" os.environ["LANGCHAIN_PROJECT"] = "my-project"
# All LangChain/LangGraph operations are automatically traced # All LangChain/LangGraph operations are automatically traced
llm = ChatAnthropic(model="claude-sonnet-4-5") llm = ChatAnthropic(model="claude-sonnet-4-6")
``` ```
### Custom Callback Handler ### Custom Callback Handler
@@ -530,7 +530,7 @@ result = await agent.ainvoke(
```python ```python
from langchain_anthropic import ChatAnthropic from langchain_anthropic import ChatAnthropic
llm = ChatAnthropic(model="claude-sonnet-4-5", streaming=True) llm = ChatAnthropic(model="claude-sonnet-4-6", streaming=True)
# Stream tokens # Stream tokens
async for chunk in llm.astream("Tell me a story"): async for chunk in llm.astream("Tell me a story"):

8
plugins/llm-application-dev/skills/llm-evaluation/SKILL.md
View File

@@ -283,7 +283,7 @@ Provide ratings in JSON format:
}}""" }}"""
message = client.messages.create( message = client.messages.create(
model="claude-sonnet-4-5", model="claude-sonnet-4-6",
max_tokens=500, max_tokens=500,
system=system, system=system,
messages=[{"role": "user", "content": prompt}] messages=[{"role": "user", "content": prompt}]
@@ -329,7 +329,7 @@ Answer with JSON:
}}""" }}"""
message = client.messages.create( message = client.messages.create(
model="claude-sonnet-4-5", model="claude-sonnet-4-6",
max_tokens=500, max_tokens=500,
messages=[{"role": "user", "content": prompt}] messages=[{"role": "user", "content": prompt}]
) )
@@ -375,7 +375,7 @@ Respond in JSON:
}}""" }}"""
message = client.messages.create( message = client.messages.create(
model="claude-sonnet-4-5", model="claude-sonnet-4-6",
max_tokens=500, max_tokens=500,
messages=[{"role": "user", "content": prompt}] messages=[{"role": "user", "content": prompt}]
) )
@@ -605,7 +605,7 @@ experiment_results = await evaluate(
data=dataset.name, data=dataset.name,
evaluators=evaluators, evaluators=evaluators,
experiment_prefix="v1.0.0", experiment_prefix="v1.0.0",
metadata={"model": "claude-sonnet-4-5", "version": "1.0.0"} metadata={"model": "claude-sonnet-4-6", "version": "1.0.0"}
) )
print(f"Mean score: {experiment_results.aggregate_metrics['qa']['mean']}") print(f"Mean score: {experiment_results.aggregate_metrics['qa']['mean']}")

6
plugins/llm-application-dev/skills/prompt-engineering-patterns/SKILL.md
View File

@@ -81,7 +81,7 @@ class SQLQuery(BaseModel):
tables_used: list[str] = Field(description="List of tables referenced") tables_used: list[str] = Field(description="List of tables referenced")
# Initialize model with structured output # Initialize model with structured output
llm = ChatAnthropic(model="claude-sonnet-4-5") llm = ChatAnthropic(model="claude-sonnet-4-6")
structured_llm = llm.with_structured_output(SQLQuery) structured_llm = llm.with_structured_output(SQLQuery)
# Create prompt template # Create prompt template
@@ -124,7 +124,7 @@ async def analyze_sentiment(text: str) -> SentimentAnalysis:
client = Anthropic() client = Anthropic()
message = client.messages.create( message = client.messages.create(
model="claude-sonnet-4-5", model="claude-sonnet-4-6",
max_tokens=500, max_tokens=500,
messages=[{ messages=[{
"role": "user", "role": "user",
@@ -427,7 +427,7 @@ client = Anthropic()
# Use prompt caching for repeated system prompts # Use prompt caching for repeated system prompts
response = client.messages.create( response = client.messages.create(
model="claude-sonnet-4-5", model="claude-sonnet-4-6",
max_tokens=1000, max_tokens=1000,
system=[ system=[
{ {

2
plugins/llm-application-dev/skills/prompt-engineering-patterns/references/chain-of-thought.md
View File

@@ -68,7 +68,7 @@ def self_consistency_cot(query, n=5, temperature=0.7):
responses = [] responses = []
for _ in range(n): for _ in range(n):
response = openai.ChatCompletion.create( response = openai.ChatCompletion.create(
model="gpt-5", model="gpt-5.2",
messages=[{"role": "user", "content": prompt}], messages=[{"role": "user", "content": prompt}],
temperature=temperature temperature=temperature
) )

2
plugins/llm-application-dev/skills/rag-implementation/SKILL.md
View File

@@ -85,7 +85,7 @@ class RAGState(TypedDict):
answer: str answer: str
# Initialize components # Initialize components
llm = ChatAnthropic(model="claude-sonnet-4-5") llm = ChatAnthropic(model="claude-sonnet-4-6")
embeddings = VoyageAIEmbeddings(model="voyage-3-large") embeddings = VoyageAIEmbeddings(model="voyage-3-large")
vectorstore = PineconeVectorStore(index_name="docs", embedding=embeddings) vectorstore = PineconeVectorStore(index_name="docs", embedding=embeddings)
retriever = vectorstore.as_retriever(search_kwargs={"k": 4}) retriever = vectorstore.as_retriever(search_kwargs={"k": 4})

2
plugins/performance-testing-review/.claude-plugin/plugin.json
View File

@@ -1,6 +1,6 @@
{ {
"name": "performance-testing-review", "name": "performance-testing-review",
"version": "1.2.0", "version": "1.2.1",
"description": "Performance analysis, test coverage review, and AI-powered code quality assessment", "description": "Performance analysis, test coverage review, and AI-powered code quality assessment",
"author": { "author": {
"name": "Seth Hobson", "name": "Seth Hobson",

16
plugins/performance-testing-review/commands/ai-review.md
View File

@@ -1,6 +1,6 @@
# AI-Powered Code Review Specialist # AI-Powered Code Review Specialist
You are an expert AI-powered code review specialist combining automated static analysis, intelligent pattern recognition, and modern DevOps practices. Leverage AI tools (GitHub Copilot, Qodo, GPT-5, Claude 4.5 Sonnet) with battle-tested platforms (SonarQube, CodeQL, Semgrep) to identify bugs, vulnerabilities, and performance issues. You are an expert AI-powered code review specialist combining automated static analysis, intelligent pattern recognition, and modern DevOps practices. Leverage AI tools (GitHub Copilot, Qodo, GPT-5.2, Claude 4.6 Sonnet) with battle-tested platforms (SonarQube, CodeQL, Semgrep) to identify bugs, vulnerabilities, and performance issues.
## Context ## Context
@@ -34,7 +34,7 @@ Execute in parallel:
### AI-Assisted Review ### AI-Assisted Review
```python ```python
# Context-aware review prompt for Claude 4.5 Sonnet # Context-aware review prompt for Claude 4.6 Sonnet
review_prompt = f""" review_prompt = f"""
You are reviewing a pull request for a {language} {project_type} application. You are reviewing a pull request for a {language} {project_type} application.
@@ -64,8 +64,8 @@ Format as JSON array.
### Model Selection (2025) ### Model Selection (2025)
- **Fast reviews (<200 lines)**: GPT-4o-mini or Claude 4.5 Haiku - **Fast reviews (<200 lines)**: GPT-5-mini or Claude 4.5 Haiku
- **Deep reasoning**: Claude 4.5 Sonnet or GPT-4.5 (200K+ tokens) - **Deep reasoning**: Claude 4.6 Sonnet or GPT-5.2 (200K+ tokens)
- **Code generation**: GitHub Copilot or Qodo - **Code generation**: GitHub Copilot or Qodo
- **Multi-language**: Qodo or CodeAnt AI (30+ languages) - **Multi-language**: Qodo or CodeAnt AI (30+ languages)
@@ -92,7 +92,7 @@ interface ReviewRoutingStrategy {
return new QodoEngine({ mode: "test-generation", coverageTarget: 80 }); return new QodoEngine({ mode: "test-generation", coverageTarget: 80 });
} }
return new AIEngine("gpt-4o", { temperature: 0.3, maxTokens: 2000 }); return new AIEngine("gpt-5.2", { temperature: 0.3, maxTokens: 2000 });
} }
} }
``` ```
@@ -312,13 +312,13 @@ jobs:
codeql database create codeql-db --language=javascript,python codeql database create codeql-db --language=javascript,python
semgrep scan --config=auto --sarif --output=semgrep.sarif semgrep scan --config=auto --sarif --output=semgrep.sarif
- name: AI-Enhanced Review (GPT-5) - name: AI-Enhanced Review (GPT-5.2)
env: env:
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }} OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
run: | run: |
python scripts/ai_review.py \ python scripts/ai_review.py \
--pr-number ${{ github.event.number }} \ --pr-number ${{ github.event.number }} \
--model gpt-4o \ --model gpt-5.2 \
--static-analysis-results codeql.sarif,semgrep.sarif --static-analysis-results codeql.sarif,semgrep.sarif
- name: Post Comments - name: Post Comments
@@ -446,7 +446,7 @@ if __name__ == '__main__':
Comprehensive AI code review combining: Comprehensive AI code review combining:
1. Multi-tool static analysis (SonarQube, CodeQL, Semgrep) 1. Multi-tool static analysis (SonarQube, CodeQL, Semgrep)
2. State-of-the-art LLMs (GPT-5, Claude 4.5 Sonnet) 2. State-of-the-art LLMs (GPT-5.2, Claude 4.6 Sonnet)
3. Seamless CI/CD integration (GitHub Actions, GitLab, Azure DevOps) 3. Seamless CI/CD integration (GitHub Actions, GitLab, Azure DevOps)
4. 30+ language support with language-specific linters 4. 30+ language support with language-specific linters
5. Actionable review comments with severity and fix examples 5. Actionable review comments with severity and fix examples