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

Replace GPT and Claude models to latest, better and cheaper models (#118)

Browse Source 
* Updated GPT and Claude models to latest, better and cheaper models

* updated more files to use GPT-5 and Sonnet/Haiku 4.5 because theu are the latest, cheaper and better models
This commit is contained in:
Kunal Shah
2025-11-17 09:22:36 +08:00
committed by GitHub
parent 7581142104
commit 1305e48672
8 changed files with 26 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
plugins/agent-orchestration/commands/multi-agent-optimize.md
View File

@@ -132,9 +132,9 @@ 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-4': 0.03, 'gpt-5': 0.03,
'claude-3-sonnet': 0.015, 'claude-4-sonnet': 0.015,
'claude-3-haiku': 0.0025 'claude-4-haiku': 0.0025
} }
def select_optimal_model(self, complexity): def select_optimal_model(self, complexity):

12
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-4, Claude 3.5 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, Claude 4.5 Sonnet) with battle-tested platforms (SonarQube, CodeQL, Semgrep) to identify bugs, vulnerabilities, and performance issues.
## Context ## Context
@@ -30,7 +30,7 @@ Execute in parallel:
### AI-Assisted Review ### AI-Assisted Review
```python ```python
# Context-aware review prompt for Claude 3.5 Sonnet # Context-aware review prompt for Claude 4.5 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.
@@ -59,8 +59,8 @@ Format as JSON array.
``` ```
### Model Selection (2025) ### Model Selection (2025)
- **Fast reviews (<200 lines)**: GPT-4o-mini or Claude 3.5 Sonnet - **Fast reviews (<200 lines)**: GPT-4o-mini or Claude 4.5 Haiku
- **Deep reasoning**: Claude 3.7 Sonnet or GPT-4.5 (200K+ tokens) - **Deep reasoning**: Claude 4.5 Sonnet or GPT-5 (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)
@@ -284,7 +284,7 @@ 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-4) - name: AI-Enhanced Review (GPT-5)
env: env:
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }} OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
run: | run: |
@@ -417,7 +417,7 @@ 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-4, Claude 3.5 Sonnet) 2. State-of-the-art LLMs (GPT-5, Claude 4.5 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

6
plugins/llm-application-dev/agents/ai-engineer.md
View File

@@ -13,7 +13,7 @@ Expert AI engineer specializing in LLM application development, RAG systems, and
### LLM Integration & Model Management ### LLM Integration & Model Management
- OpenAI GPT-4o/4o-mini, o1-preview, o1-mini with function calling and structured outputs - OpenAI GPT-4o/4o-mini, o1-preview, o1-mini with function calling and structured outputs
- Anthropic Claude 3.5 Sonnet, Claude 3 Haiku/Opus with tool use and computer use - Anthropic Claude 4.5 Sonnet/Haiku, Claude 4.1 Opus with tool use and computer use
- Open-source models: Llama 3.1/3.2, Mixtral 8x7B/8x22B, Qwen 2.5, DeepSeek-V2 - Open-source models: Llama 3.1/3.2, Mixtral 8x7B/8x22B, Qwen 2.5, DeepSeek-V2
- 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
@@ -68,7 +68,7 @@ Expert AI engineer specializing in LLM application development, RAG systems, and
- Observability: logging, metrics, tracing with LangSmith, Phoenix, Weights & Biases - Observability: logging, metrics, tracing with LangSmith, Phoenix, Weights & Biases
### Multimodal AI Integration ### Multimodal AI Integration
- Vision models: GPT-4V, Claude 3 Vision, LLaVA, CLIP for image understanding - Vision models: GPT-4V, 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
@@ -111,7 +111,7 @@ Expert AI engineer specializing in LLM application development, RAG systems, and
- Balances cutting-edge techniques with proven, stable solutions - Balances cutting-edge techniques with proven, stable solutions
## Knowledge Base ## Knowledge Base
- Latest LLM developments and model capabilities (GPT-4o, Claude 3.5, Llama 3.2) - Latest LLM developments and model capabilities (GPT-4o, Claude 4.5, Llama 3.2)
- 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

2
plugins/llm-application-dev/agents/prompt-engineer.md
View File

@@ -53,7 +53,7 @@ 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 (3.5 Sonnet, Haiku, Opus) #### Anthropic Claude (4.5 Sonnet, Haiku, Opus)
- 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
- Computer use prompting for automation tasks - Computer use prompting for automation tasks

6
plugins/llm-application-dev/commands/prompt-optimize.md
View File

@@ -113,7 +113,7 @@ Final Response: [Refined]
### 5. Model-Specific Optimization ### 5. Model-Specific Optimization
**GPT-4/GPT-4o** **GPT-5/GPT-4o**
```python ```python
gpt4_optimized = """ gpt4_optimized = """
##CONTEXT## ##CONTEXT##
@@ -136,7 +136,7 @@ gpt4_optimized = """
""" """
``` ```
**Claude 3.5/4** **Claude 4.5/4**
```python ```python
claude_optimized = """ claude_optimized = """
<context> <context>
@@ -566,7 +566,7 @@ testing_recommendations:
metrics: ["accuracy", "satisfaction", "cost"] metrics: ["accuracy", "satisfaction", "cost"]
deployment_strategy: deployment_strategy:
model: "GPT-4 for quality, Claude for safety" model: "GPT-5 for quality, Claude for safety"
temperature: 0.7 temperature: 0.7
max_tokens: 2000 max_tokens: 2000
monitoring: "Track success, latency, feedback" monitoring: "Track success, latency, feedback"

6
plugins/llm-application-dev/skills/llm-evaluation/SKILL.md
View File

@@ -186,7 +186,7 @@ def calculate_factuality(claim, knowledge_base):
### Single Output Evaluation ### Single Output Evaluation
```python ```python
def llm_judge_quality(response, question): def llm_judge_quality(response, question):
"""Use GPT-4 to judge response quality.""" """Use GPT-5 to judge response quality."""
prompt = f"""Rate the following response on a scale of 1-10 for: prompt = f"""Rate the following response on a scale of 1-10 for:
1. Accuracy (factually correct) 1. Accuracy (factually correct)
2. Helpfulness (answers the question) 2. Helpfulness (answers the question)
@@ -205,7 +205,7 @@ Provide ratings in JSON format:
""" """
result = openai.ChatCompletion.create( result = openai.ChatCompletion.create(
model="gpt-4", model="gpt-5",
messages=[{"role": "user", "content": prompt}], messages=[{"role": "user", "content": prompt}],
temperature=0 temperature=0
) )
@@ -236,7 +236,7 @@ Answer with JSON:
""" """
result = openai.ChatCompletion.create( result = openai.ChatCompletion.create(
model="gpt-4", model="gpt-5",
messages=[{"role": "user", "content": prompt}], messages=[{"role": "user", "content": prompt}],
temperature=0 temperature=0
) )

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

@@ -65,7 +65,7 @@ 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-4", model="gpt-5",
messages=[{"role": "user", "content": prompt}], messages=[{"role": "user", "content": prompt}],
temperature=temperature temperature=temperature
) )

12
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-4, Claude 3.5 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, Claude 4.5 Sonnet) with battle-tested platforms (SonarQube, CodeQL, Semgrep) to identify bugs, vulnerabilities, and performance issues.
## Context ## Context
@@ -30,7 +30,7 @@ Execute in parallel:
### AI-Assisted Review ### AI-Assisted Review
```python ```python
# Context-aware review prompt for Claude 3.5 Sonnet # Context-aware review prompt for Claude 4.5 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.
@@ -59,8 +59,8 @@ Format as JSON array.
``` ```
### Model Selection (2025) ### Model Selection (2025)
- **Fast reviews (<200 lines)**: GPT-4o-mini or Claude 3.5 Sonnet - **Fast reviews (<200 lines)**: GPT-4o-mini or Claude 4.5 Haiku
- **Deep reasoning**: Claude 3.7 Sonnet or GPT-4.5 (200K+ tokens) - **Deep reasoning**: Claude 4.5 Sonnet or GPT-4.5 (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)
@@ -284,7 +284,7 @@ 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-4) - name: AI-Enhanced Review (GPT-5)
env: env:
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }} OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
run: | run: |
@@ -417,7 +417,7 @@ 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-4, Claude 3.5 Sonnet) 2. State-of-the-art LLMs (GPT-5, Claude 4.5 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