name: codex-review description: > Runs OpenAI Codex CLI (read-only) to perform tasks using OpenAI/GPT models as a second opinion. Use when the user asks for a "codex review", "second opinion", "cross-model review", or wants an independent analysis from a different AI model family. The main agent provides the task description and working directory in the prompt. user: "run codex review on the uncommitted changes" user: "get a second opinion on this code from codex" user: "ask codex to analyze the architecture of this module"
| name | orchestrating-swarms |
|---|---|
| description | Master multi-agent orchestration using Claude Code's TeammateTool and Task system. Use when coordinating multiple agents, running parallel code reviews, creating pipeline workflows with dependencies, building self-organizing task queues, or any task benefiting from divide-and-conquer patterns. |
Master multi-agent orchestration using Claude Code's TeammateTool and Task system.
Amazon Bedrock AgentCore is in preview release and is subject to change.
Note: This guide is based on the official AWS documentation but uses a non-interactive deployment method and provides visibility into the IAM roles and ECR repositories created, making the process more transparent. The original guide uses interactive prompts which this guide avoids.
This guide has been tested on Linux x86_64/amd64 systems. While Bedrock AgentCore runs on ARM64, the deployment process uses CodeBuild for cross-platform compilation.
Below is a high‑level, end‑to‑end guide to the four pieces you asked about – how they fit together in Azure Databricks, what they’re used for, and the key steps needed to get them working in production.
- SSO lets users authenticate once (e.g., via Azure AD, Okta, ADFS) and then automatically get access to the Databricks workspace, notebooks, jobs, and REST APIs without re‑entering credentials.
- In Azure Databricks the SSO flow is built on SAML 2.0 (or OpenID Connect for Azure AD).
- Marlene - Senior Developer Advocate, Python on Azure team at Microsoft
- Active in Python community (ACM volunteer, Python Software Foundation board)
- Gwen - Developer Advocate, Same team as Marlene
| """ | |
| 1. Make sure you have `uv` install. (e.g. `brew install uv`) | |
| 2. Setup Python venv `uv venv && source .venv/bin/activate` | |
| 3. Setup the model API key (e.g. `export ANTHROPIC_API_KEY=<your_api_key>`) | |
| 4. Run it! `uv run python tiny_agent.py` | |
| """ | |
| import asyncio | |
| from pydantic_ai import Agent |
| # Define the WSL mount command and its arguments | |
| $wslCommand = "wsl.exe" | |
| $wslArguments = "--mount \\.\PhysicalDrive2 --partition 1 --type ext4 --name data_wsl_shared" | |
| # Create the scheduled task action that will run the WSL command | |
| $action = New-ScheduledTaskAction -Execute $wslCommand -Argument $wslArguments | |
| # Create a trigger that runs the task at system startup | |
| $trigger = New-ScheduledTaskTrigger -AtStartup |
| export PATH=$HOME/bin:$HOME/.local/bin:/usr/local/bin:$PATH | |
| export ZSH="$HOME/.oh-my-zsh" | |
| ZSH_THEME="robbyrussell" | |
| DISABLE_MAGIC_FUNCTIONS="true" | |
| plugins=(git) | |
| source $ZSH/oh-my-zsh.sh # First source oh-my-zsh | |
| # Then set your custom prompt | |
| PROMPT='%{$fg[cyan]%}%m%{$reset_color%} ${ret_status}%{$fg_bold[green]%}➜ %{$fg_bold[blue]%}%c%{$reset_color%} $(git_prompt_info)' |
| #!/bin/bash | |
| set -e | |
| echo "Setting up Neovim with a modern configuration..." | |
| # Detect the operating system | |
| if [ -f /etc/os-release ]; then | |
| . /etc/os-release | |
| OS=$NAME |
| function Load-RoutingTableFromJson { | |
| param ( | |
| [string]$JsonFilePath | |
| ) | |
| if (-not (Test-Path $JsonFilePath)) { | |
| Write-Error "JSON file not found: $JsonFilePath" | |
| return $null | |
| } |