Add community skills, agents, system prompts from 22+ sources

Community Skills (32):
- jat: jat-start, jat-verify, jat-complete
- pi-mono: codex-cli, codex-5.3-prompting, interactive-shell
- picoclaw: github, weather, tmux, summarize, skill-creator
- dyad: 18 skills (swarm-to-plan, multi-pr-review, fix-issue, lint, etc.)
- dexter: dcf valuation skill

Agents (23):
- pi-mono subagents: scout, planner, reviewer, worker
- toad: 19 agent configs (Claude, Codex, Gemini, Copilot, OpenCode, etc.)

System Prompts (91):
- Anthropic: 15 Claude prompts (opus-4.6, code, cowork, etc.)
- OpenAI: 49 GPT prompts (gpt-5 series, o3, o4-mini, tools)
- Google: 13 Gemini prompts (2.5-pro, 3-pro, workspace, cli)
- xAI: 5 Grok prompts
- Other: 9 misc prompts (Notion, Raycast, Warp, Kagi, etc.)

Hooks (9):
- JAT hooks for session management, signal tracking, activity logging

Prompts (6):
- pi-mono templates for PR review, issue analysis, changelog audit

Sources analyzed: jat, ralph-desktop, toad, pi-mono, cmux, pi-interactive-shell,
craft-agents-oss, dexter, picoclaw, dyad, system_prompts_leaks, Prometheus,
zed, clawdbot, OS-Copilot, and more

agents/community/pi-mono/planner.md

@@ -0,0 +1,37 @@
+---
+name: planner
+description: Creates implementation plans from context and requirements
+tools: read, grep, find, ls
+model: claude-sonnet-4-5
+---
+
+You are a planning specialist. You receive context (from a scout) and requirements, then produce a clear implementation plan.
+
+You must NOT make any changes. Only read, analyze, and plan.
+
+Input format you'll receive:
+- Context/findings from a scout agent
+- Original query or requirements
+
+Output format:
+
+## Goal
+One sentence summary of what needs to be done.
+
+## Plan
+Numbered steps, each small and actionable:
+1. Step one - specific file/function to modify
+2. Step two - what to add/change
+3. ...
+
+## Files to Modify
+- `path/to/file.ts` - what changes
+- `path/to/other.ts` - what changes
+
+## New Files (if any)
+- `path/to/new.ts` - purpose
+
+## Risks
+Anything to watch out for.
+
+Keep the plan concrete. The worker agent will execute it verbatim.

agents/community/pi-mono/reviewer.md

@@ -0,0 +1,35 @@
+---
+name: reviewer
+description: Code review specialist for quality and security analysis
+tools: read, grep, find, ls, bash
+model: claude-sonnet-4-5
+---
+
+You are a senior code reviewer. Analyze code for quality, security, and maintainability.
+
+Bash is for read-only commands only: `git diff`, `git log`, `git show`. Do NOT modify files or run builds.
+Assume tool permissions are not perfectly enforceable; keep all bash usage strictly read-only.
+
+Strategy:
+1. Run `git diff` to see recent changes (if applicable)
+2. Read the modified files
+3. Check for bugs, security issues, code smells
+
+Output format:
+
+## Files Reviewed
+- `path/to/file.ts` (lines X-Y)
+
+## Critical (must fix)
+- `file.ts:42` - Issue description
+
+## Warnings (should fix)
+- `file.ts:100` - Issue description
+
+## Suggestions (consider)
+- `file.ts:150` - Improvement idea
+
+## Summary
+Overall assessment in 2-3 sentences.
+
+Be specific with file paths and line numbers.

agents/community/pi-mono/scout.md

@@ -0,0 +1,50 @@
+---
+name: scout
+description: Fast codebase recon that returns compressed context for handoff to other agents
+tools: read, grep, find, ls, bash
+model: claude-haiku-4-5
+---
+
+You are a scout. Quickly investigate a codebase and return structured findings that another agent can use without re-reading everything.
+
+Your output will be passed to an agent who has NOT seen the files you explored.
+
+Thoroughness (infer from task, default medium):
+- Quick: Targeted lookups, key files only
+- Medium: Follow imports, read critical sections
+- Thorough: Trace all dependencies, check tests/types
+
+Strategy:
+1. grep/find to locate relevant code
+2. Read key sections (not entire files)
+3. Identify types, interfaces, key functions
+4. Note dependencies between files
+
+Output format:
+
+## Files Retrieved
+List with exact line ranges:
+1. `path/to/file.ts` (lines 10-50) - Description of what's here
+2. `path/to/other.ts` (lines 100-150) - Description
+3. ...
+
+## Key Code
+Critical types, interfaces, or functions:
+
+```typescript
+interface Example {
+  // actual code from the files
+}
+```
+
+```typescript
+function keyFunction() {
+  // actual implementation
+}
+```
+
+## Architecture
+Brief explanation of how the pieces connect.
+
+## Start Here
+Which file to look at first and why.

agents/community/pi-mono/worker.md

@@ -0,0 +1,24 @@
+---
+name: worker
+description: General-purpose subagent with full capabilities, isolated context
+model: claude-sonnet-4-5
+---
+
+You are a worker agent with full capabilities. You operate in an isolated context window to handle delegated tasks without polluting the main conversation.
+
+Work autonomously to complete the assigned task. Use all available tools as needed.
+
+Output format when finished:
+
+## Completed
+What was done.
+
+## Files Changed
+- `path/to/file.ts` - what changed
+
+## Notes (if any)
+Anything the main agent should know.
+
+If handing off to another agent (e.g. reviewer), include:
+- Exact file paths changed
+- Key functions/types touched (short list)

agents/community/toad/ampcode.com.toml

@@ -0,0 +1,51 @@
+# Schema defined in agent_schema.py
+# https://github.com/tao12345666333/amp-acp
+
+identity = "ampcode.com"
+name = "Amp (AmpCode)"
+short_name = "amp"
+url = "https://ampcode.com"
+protocol = "acp"
+author_name = "AmpCode"
+author_url = "https://ampcode.com"
+publisher_name = "Will McGugan"
+publisher_url = "https://willmcgugan.github.io/"
+type = "coding"
+description = "Open-source ACP adapter that exposes the Amp CLI to editors such as Zed via the Agent Client Protocol."
+tags = []
+run_command."*" = "npx -y amp-acp"
+
+help = '''
+# Amp (AmpCode)
+
+Amp is a frontier coding agent for your terminal and editor, built by Sourcegraph.
+
+- **Multi-Model** Sonnet, GPT-5, fast models—Amp uses them all, for what each model is best at.
+- **Opinionated** You're always using the good parts of Amp. If we don't use and love a feature, we kill it.
+- **On the Frontier** Amp goes where the models take it. No backcompat, no legacy features.
+- **Threads** You can save and share your interactions with Amp. You wouldn't code without version control, would you?
+
+## Prerequisites
+
+- Node.js 18+ so `npx` can run the adapter
+- Ensure the `AMP_EXECUTABLE` environment variable points at your Amp binary (or place `amp` on `PATH`)
+
+
+---
+
+## ACP adapter for AmpCode
+
+**Repository**: https://github.com/tao12345666333/amp-acp
+'''
+
+[actions."*".install]
+command = "curl -fsSL https://ampcode.com/install.sh | bash && npm install -g amp-acp"
+description = "Install AMP Code"
+
+[actions."*".install_adapter]
+command = "npm install -g amp-acp"
+description = "Install the Amp ACP adapter"
+
+[actions."*".login]
+command = "amp login"
+description = "Login to Amp (run once)"

agents/community/toad/augmentcode.com.toml

@@ -0,0 +1,40 @@
+# Schema defined in agent_schema.py
+# https://github.com/augmentcode/auggie
+
+identity = "augmentcode.com"
+name = "Auggie (Augment Code)"
+short_name = "auggie"
+url = "https://www.augmentcode.com/product/CLI"
+protocol = "acp"
+author_name = "Augment Code"
+author_url = "https://www.augmentcode.com/"
+publisher_name = "Will McGugan"
+publisher_url = "https://willmcgugan.github.io/"
+type = "coding"
+description = "An AI agent that brings Augment Code's power to the terminal with ACP support for Zed, Neovim, and Emacs."
+tags = []
+run_command."*" = "auggie --acp"
+
+help = '''
+# Auggie (Augment Code)
+
+*The agentic CLI that goes where your code does*
+
+## Features
+
+- **Agent Client Protocol (ACP) Support**: Use Auggie in Zed, Neovim, Emacs, and other ACP-compatible editors
+- **Autonomous Code Analysis**: Intelligently explore codebases and build working memory
+- **Multi-Editor Integration**: Seamlessly integrates with your favorite development environment
+
+---
+
+**Documentation**: https://docs.augmentcode.com/cli/setup-auggie/install-auggie-cli
+'''
+
+[actions."*".install]
+command = "npm install -g @augmentcode/auggie"
+description = "Install Auggie CLI (requires Node 22+)"
+
+[actions."*".login]
+command = "auggie login"
+description = "Login it Auggie (run once)"

agents/community/toad/claude.com.toml

@@ -0,0 +1,41 @@
+# Schema defined in agent_schema.py
+# https://www.claude.com/product/claude-code
+
+identity = "claude.com"
+name = "Claude Code"
+short_name = "claude"
+url = "https://www.claude.com/product/claude-code"
+protocol = "acp"
+author_name = "Anthropic"
+author_url = "https://www.anthropic.com/"
+publisher_name = "Will McGugan"
+publisher_url = "https://willmcgugan.github.io/"
+type = "coding"
+description = "Unleash Claude’s raw power directly in your terminal."
+tags = []
+run_command."*" = "claude-code-acp"
+
+help = '''
+# Claude Code
+
+Built for developers
+Unleash Claude’s raw power directly in your terminal.
+Search million-line codebases instantly.
+Turn hours-long workflows into a single command.
+Your tools.
+Your workflow.
+Your codebase, evolving at thought speed.
+
+--- 
+[ACP adapter for Claude Code](https://github.com/zed-industries/claude-code-acp) by Zed Industries.
+
+'''
+
+
+[actions."*".install]
+command = "curl -fsSL https://claude.ai/install.sh | bash &&  npm install -g @zed-industries/claude-code-acp"
+description = "Install Claude Code + ACP adapter"
+
+[actions."*".install_acp]
+command = "npm install -g @zed-industries/claude-code-acp"
+description = "Install ACP adapter"

agents/community/toad/copilot.github.com.toml

@@ -0,0 +1,29 @@
+# Schema defined in agent_schema.py
+# https://github.com/github/copilot-cli?locale=en-US
+
+identity = "copilot.github.com"
+name = "Copilot"
+short_name = "copilot"
+url = "https://github.com/github/copilot-cli"
+protocol = "acp"
+author_name = "GitHub"
+author_url = "https://githib.com"
+publisher_name = "Will McGugan"
+publisher_url = "https://willmcgugan.github.io/"
+type = "coding"
+description = "The power of GitHub Copilot, now in your terminal."
+tags = []
+run_command."*" = "copilot --acp"
+
+help = '''
+# GitHub Copilot
+
+GitHub Copilot CLI brings AI-powered coding assistanc"e directly to your command line, enabling you to build, debug, and understand code through natural language conversations. Powered by the same agentic harness as GitHub's Copilot coding agent, it provides intelligent assistance while staying deeply integrated with your GitHub workflow.
+
+Install vial the select below, or see the README for [alternative install methods](https://github.com/github/copilot-cli?tab=readme-ov-file#installation)
+
+'''
+
+[actions."*".install]
+command = "npm install -g @github/copilot@prerelease"
+description = "Install Copilot"

agents/community/toad/docker.com.toml

@@ -0,0 +1,59 @@
+# Schema defined in agent_schema.py
+# https://github.com/docker/cagent
+
+identity = "docker.com"
+name = "Docker cagent"
+short_name = "cagent"
+url = "https://docs.docker.com/ai/cagent/"
+protocol = "acp"
+author_name = "Docker"
+author_url = "https://www.docker.com/"
+publisher_name = "Will McGugan"
+publisher_url = "https://willmcgugan.github.io/"
+type = "coding"
+description = "Agent Builder and Runtime by Docker Engineering. Build, orchestrate, and share AI agents with MCP and ACP support."
+tags = []
+run_command."*" = "cagent acp"
+recommended = false
+
+help = '''
+# Docker cagent
+
+**Agent Builder and Runtime by Docker Engineering**
+
+Docker cagent lets you build, orchestrate, and share AI agents that work together as a team.
+
+## Key Features
+
+- **Hierarchical Agent System**: Intelligent task delegation between multiple agents
+- **Model Context Protocol (MCP)**: Rich tool ecosystem via MCP integration
+- **Multiple Interfaces**: CLI, TUI, API server, and MCP server modes
+- **Share & Distribute**: Package and share agents to Docker Hub as OCI artifacts
+
+## Agent Client Protocol Support
+
+cagent supports ACP, enabling integration with ACP-compatible editors and development environments.
+
+## Installation
+
+The easiest way to get cagent is to install Docker Desktop version 4.49 or later, which includes cagent.
+
+## Distribution
+
+Agent configurations can be packaged and shared using the `cagent push` command, treating agents as reproducible OCI artifacts.
+
+---
+
+**Documentation**: https://docs.docker.com/ai/cagent/  
+**GitHub**: https://github.com/docker/cagent  
+**Blog Post**: https://www.docker.com/blog/cagent-build-and-distribute-ai-agents-and-workflows/
+'''
+
+welcome = '''
+Say "hello" to CAgent!
+
+'''
+
+[actions."*".install]
+command = "echo 'Install Docker Desktop 4.49+ which includes cagent: https://www.docker.com/products/docker-desktop/'"
+description = "Install Docker Desktop with cagent"

agents/community/toad/geminicli.com.toml

@@ -0,0 +1,28 @@
+# Schema defined in agent_schema.py
+# https://github.com/google-gemini/gemini-cli
+identity = "geminicli.com"
+name = "Gemini CLI"
+short_name = "gemini"
+url = "https://geminicli.com/"
+protocol = "acp"
+author_name = "Google"
+author_url = "https://www.gooogle.com"
+publisher_name = "Will McGugan"
+publisher_url = "https://willmcgugan.github.io/"
+type = "coding"
+description = "Query and edit large codebases, generate apps from images or PDFs, and automate complex workflows—all from your terminal."
+tags = []
+run_command."*" = "gemini --experimental-acp"
+
+help = '''
+# Gemini CLI
+
+**Build  debug & deploy with AI**
+
+Query and edit large codebases, generate apps from images or PDFs, and automate complex workflows—all from your terminal.
+
+'''
+
+[actions."*".install]
+command = "npm install -g @google/gemini-cli"
+description = "Install Gemini CLI"

agents/community/toad/goose.ai.toml

@@ -0,0 +1,51 @@
+# Schema defined in agent_schema.py
+# https://github.com/block/goose
+
+identity = "goose.ai"
+name = "Goose"
+short_name = "goose"
+url = "https://block.github.io/goose/"
+protocol = "acp"
+author_name = "Block"
+author_url = "https://block.xyz/"
+publisher_name = "Will McGugan"
+publisher_url = "https://willmcgugan.github.io/"
+type = "coding"
+description = "An open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM."
+tags = []
+run_command."*" = "goose acp"
+
+help = '''
+# Goose 🪿
+
+**An open source, extensible AI agent**
+
+Goose is an open framework for AI agents that goes beyond code suggestions to install dependencies, execute commands, edit files, and run tests.
+
+## Key Features
+
+- **Extensible Framework**: Plugin-based architecture for custom tools and behaviors
+- **Multi-LLM Support**: Works with various LLM providers
+- **Agent Client Protocol (ACP)**: Native ACP support for editor integration
+- **Multiple Interfaces**: CLI, and ACP server modes
+
+## Configuration
+
+You can override ACP configurations using environment variables:
+- `GOOSE_PROVIDER`: Set your preferred LLM provider
+- `GOOSE_MODEL`: Specify the model to use
+
+---
+
+**Documentation**: https://block.github.io/goose/docs/guides/acp-clients/  
+**GitHub**: https://github.com/block/goose  
+**Quickstart**: https://block.github.io/goose/docs/quickstart/
+'''
+
+[actions."*".install]
+command = "curl -fsSL https://github.com/block/goose/releases/download/stable/download_cli.sh | bash"
+description = "Install Goose"
+
+[action."*".update]
+command = "Update Goose"
+description = "Update Goose"

agents/community/toad/inference.huggingface.co.toml

@@ -0,0 +1,44 @@
+# Schema defined in agent_schema.py
+
+active = true
+identity = "inference.huggingface.co"
+name = "Hugging Face Inference Providers"
+short_name = "hf"
+url = "https://huggingface.co"
+protocol = "acp"
+author_name = "Hugging Face"
+author_url = "https://huffingface.co"
+publisher_name = "Hugging Face"
+publisher_url = "https://huffingface.co"
+type = "chat"
+description = """
+Use the latest open weight models and skills with HF Inference Providers. Create an account at Hugging Face and register with [b]toad-hf-inference-explorers[/] for [bold $success]$20[/] of free credit!"""
+tags = []
+run_command."*" = "hf-inference-acp -x"
+
+help = '''
+# Hugging Face Inference Providers
+
+Chat with the latest open weight models using Hugging Face inference providers.
+
+--- 
+
+Create an account at huggingface.co/join and register with [Toad Explorers](https://huggingface.co/toad-hf-inference-explorers) for **$20** of free credit!
+'''
+
+
+welcome = '''
+# Hugging Face 🤗
+
+Use `ctrl+o` to enter Setup mode and type `go` to change settings.
+
+Use `/skills` to manage and install skills.
+
+Join the community at [Toad Hf Inference Explorers](https://huggingface.co/toad-hf-inference-explorers)
+'''
+
+recommended = true
+
+[actions."*".install]
+command = "uv tool install -U hf-inference-acp --with-executables-from huggingface_hub --force"
+description = "Install Hugging Face Inference Providers"

agents/community/toad/kimi.com.toml

@@ -0,0 +1,35 @@
+# Schema defined in agent_schema.py
+# https://github.com/MoonshotAI/kimi-cli
+
+identity = "kimi.com"
+name = "Kimi CLI"
+short_name = "kimi"
+url = "https://www.kimi.com/"
+protocol = "acp"
+author_name = "Moonshot AI"
+author_url = "https://www.kimi.com/"
+publisher_name = "Will McGugan"
+publisher_url = "https://willmcgugan.github.io/"
+type = "coding"
+description = "Kimi CLI is a new CLI agent that can help you with your software development tasks and terminal operations."
+tags = []
+run_command."*" = "kimi acp"
+
+help = '''
+# Kimi CLI
+
+Kimi CLI is a new CLI agent that can help you with your software development tasks and terminal operations.
+
+See the following [instructions](https://github.com/MoonshotAI/kimi-cli?tab=readme-ov-file#usage) for how to configure Kimi before running.
+
+'''
+
+
+[actions."*".install]
+command = "uv tool install kimi-cli --no-cache"
+description = "Install Kimi CLI"
+
+
+[actions."*".update]
+command = "uv tool upgrade kimi-cli --no-cache"
+description = "Upgrade Kimi CLI"

agents/community/toad/openai.com.toml

@@ -0,0 +1,53 @@
+# Schema defined in agent_schema.py
+# https://github.com/openai/codex
+
+identity = "openai.com"
+name = "Codex CLI"
+short_name = "codex"
+url = "https://developers.openai.com/codex/cli/"
+protocol = "acp"
+author_name = "OpenAI"
+author_url = "https://www.openai.com/"
+publisher_name = "Will McGugan"
+publisher_url = "https://willmcgugan.github.io/"
+type = "coding"
+description = "Lightweight coding agent by OpenAI that runs in your terminal with native ACP support."
+tags = []
+run_command."*" = "npx @zed-industries/codex-acp"
+
+help = '''
+# Codex CLI
+
+**Lightweight coding agent that runs in your terminal**
+
+Codex CLI is OpenAI's terminal-based coding agent with built-in support for the Agent Client Protocol.
+
+## Features
+
+- **Agent Client Protocol (ACP)**: Native ACP support for seamless editor integration
+- **Zed Integration**: Built-in support in Zed IDE (v0.208+)
+- **Terminal-First**: Designed for developers who live in the command line
+
+## ACP Integration
+
+Codex works out-of-the-box with ACP-compatible editors:
+- Zed: Open agent panel (cmd-?/ctrl-?) and start a new Codex thread
+- Other ACP clients: Use the `codex-acp` command
+
+## Installation
+
+Install globally via npm or Homebrew:
+- npm: `npm i -g @openai/codex`
+- Homebrew: `brew install --cask codex`
+
+For ACP adapter (used by editors): Install from https://github.com/zed-industries/codex-acp/releases
+
+---
+
+**GitHub**: https://github.com/openai/codex  
+**ACP Adapter**: https://github.com/zed-industries/codex-acp
+'''
+
+[actions."*".install]
+command = "npm install -g @openai/codex"
+description = "Install Codex CLI"

agents/community/toad/opencode.ai.toml

@@ -0,0 +1,39 @@
+# Schema defined in agent_schema.py
+# https://github.com/sst/opencode
+
+identity = "opencode.ai"
+name = "OpenCode"
+short_name = "opencode"
+url = "https://opencode.ai/"
+protocol = "acp"
+author_name = "SST"
+author_url = "https://sst.dev/"
+publisher_name = "Will McGugan"
+publisher_url = "https://willmcgugan.github.io/"
+type = "coding"
+description = "The AI coding agent built for the terminal with client/server architecture and ACP support via adapter."
+tags = []
+run_command."*" = "opencode acp"
+
+help = '''
+# OpenCode
+
+OpenCode is an open source agent that helps you write and run code directly from the terminal with a flexible client/server architecture.
+
+## Key Features
+
+- **Client/Server Architecture**: Run OpenCode on your computer while controlling it remotely
+- **Terminal-Native**: Built for developers who work in the command line
+- **Multi-LLM Support**: Works with various AI providers
+- **GitHub Integration**: Deep integration with GitHub workflows
+
+---
+
+**Website**: https://opencode.ai/  
+**GitHub**: https://github.com/sst/opencode  
+
+'''
+
+[actions."*".install]
+command = "npm i -g opencode-ai"
+description = "Install OpenCode"

agents/community/toad/openhands.dev.toml

@@ -0,0 +1,45 @@
+# Schema defined in agent_schema.py
+# https://www.claude.com/product/claude-code
+
+identity = "openhands.dev"
+name = "OpenHands"
+short_name = "openhands"
+url = "https://openhands.dev/"
+protocol = "acp"
+author_name = "OpenHands"
+author_url = "https://openhands.dev/"
+publisher_name = "Will McGugan"
+publisher_url = "https://willmcgugan.github.io/"
+type = "coding"
+description = "The open platform for cloud coding agents. Scale from one to thousands of agents — open source, model-agnostic, and enterprise-ready. New users get [$text-success bold]$10[/] in free OpenHands Cloud credits!"
+tags = []
+run_command."*" = "openhands acp"
+recommended = true
+
+help = '''
+# OpenHands
+
+The open platform for cloud coding agents
+
+Scale from one to thousands of agents -- open source, model agnostic, and enterprise-ready.
+
+[openhands-dev](https://openhands.dev/)
+'''
+
+welcome = '''
+## The future of software development must be written by engineers
+
+Software development is changing. That change needs to happen in the open, driven by a community of professional developers. That's why OpenHands' software agent is MIT-licensed and trusted by a growing community.
+
+Visit [openhands-dev](https://openhands.dev/) for more information.
+'''
+
+[actions."*".install]
+command = "uv tool install openhands -U --python 3.12 && openhands login"
+bootstrap_uv = true
+description = "Install OpenHands"
+
+[actions."*".update]
+command = "uv tool install openhands -U --python 3.12"
+bootstrap_uv = true
+description = "Update OpenHands"

agents/community/toad/stakpak.dev.toml

@@ -0,0 +1,61 @@
+# Schema defined in agent_schema.py
+# https://github.com/stakpak/agent
+
+identity = "stakpak.dev"
+name = "Stakpak Agent"
+short_name = "stakpak"
+url = "https://stakpak.dev/"
+protocol = "acp"
+author_name = "Stakpak"
+author_url = "https://stakpak.dev/"
+publisher_name = "Will McGugan"
+publisher_url = "https://willmcgugan.github.io/"
+type = "coding"
+description = "Terminal-native DevOps Agent in Rust with enterprise-grade security, ACP support, and IaC generation capabilities."
+tags = []
+run_command."*" = "stakpak acp"
+
+help = '''
+# Stakpak Agent
+
+**The most secure agent built for operations & DevOps**
+
+Stakpak is a terminal-native DevOps Agent built in Rust with enterprise-grade security features and Agent Client Protocol support.
+
+## Key Features
+
+- **Enterprise-Grade Security**: 
+  - Mutual TLS (mTLS) encryption
+  - Dynamic secret redaction
+  - Privacy-first architecture
+- **DevOps Capabilities**: Run commands, edit files, search docs, and generate high-quality IaC
+- **Agent Client Protocol (ACP)**: Native support for editor integration
+- **Rust Performance**: Built in Rust for speed and reliability
+
+## ACP Integration
+
+Stakpak implements the Agent Client Protocol, enabling integration with ACP-compatible editors and development environments like Zed, Neovim, and others.
+
+## Security
+
+Stakpak emphasizes security with:
+- End-to-end encryption via mTLS
+- Automatic detection and redaction of sensitive information
+- Privacy-first design principles
+
+## Use Cases
+
+- Infrastructure as Code (IaC) generation
+- DevOps automation
+- Secure operations in production environments
+- Terminal-based development workflows
+
+---
+
+**GitHub**: https://github.com/stakpak/agent  
+**Website**: https://stakpak.dev/
+'''
+
+[actions."*".install]
+command = "cargo install stakpak"
+description = "Install Stakpak Agent via Cargo"

agents/community/toad/vibe.mistral.ai.toml

@@ -0,0 +1,27 @@
+# Schema defined in agent_schema.py
+# https://www.claude.com/product/claude-code
+
+identity = "vibe.mistral.ai"
+name = "Mistral Vibe"
+short_name = "vibe"
+url = "https://mistral.ai/news/devstral-2-vibe-cli"
+protocol = "acp"
+author_name = "Mistral"
+author_url = "https://mistral.ai/"
+publisher_name = "Will McGugan"
+publisher_url = "https://willmcgugan.github.io/"
+type = "coding"
+description = "State-of-the-art, open-source agentic coding models and CLI agent."
+tags = []
+run_command."*" = "vibe-acp"
+
+help = '''
+# Devstral2 Mistral Vibe CLI
+
+Today, we're releasing Devstral 2—our next-generation coding model family available in two sizes: Devstral 2 (123B) and Devstral Small 2 (24B). Devstral 2 ships under a modified MIT license, while Devstral Small 2 uses Apache 2.0. Both are open-source and permissively licensed to accelerate distributed intelligence.
+'''
+
+
+[actions."*".install]
+command = "curl -LsSf https://mistral.ai/vibe/install.sh | bash"
+description = "Install Mistral Vibe"

agents/community/toad/vtcode.dev.toml

@@ -0,0 +1,62 @@
+# Schema defined in agent_schema.py
+# https://github.com/vinhnx/vtcode
+
+identity = "vtcode.dev"
+name = "VT Code"
+short_name = "vtcode"
+url = "https://github.com/vinhnx/vtcode"
+protocol = "acp"
+author_name = "Vinh Nguyen"
+author_url = "https://github.com/vinhnx"
+publisher_name = "Will McGugan"
+publisher_url = "https://willmcgugan.github.io/"
+type = "coding"
+description = "Rust-based terminal coding agent with semantic code intelligence via Tree-sitter, ast-grep, and native Zed IDE integration via ACP."
+tags = []
+run_command."*" = "vtcode acp"
+
+help = '''
+# VT Code
+
+**Semantic Coding Agent**
+
+VT Code is a Rust-based terminal coding agent with semantic code intelligence and native support for the Agent Client Protocol.
+
+## Key Features
+
+- **Semantic Code Intelligence**: 
+  - Tree-sitter integration for syntax-aware analysis
+  - ast-grep integration for semantic search
+  - Advanced token budget tracking
+- **Multi-LLM Support**: Works with multiple LLM providers with automatic failover
+- **Rich Terminal UI**: Real-time streaming in a beautiful TUI
+- **Editor Integration**: Native support for Zed IDE via ACP
+- **Security**: Defense-in-depth security model
+
+## Smart Tools
+
+- Built-in code analysis and refactoring
+- File operations with semantic understanding
+- Terminal command execution
+- Lifecycle hooks for custom shell commands
+
+## Agent Client Protocol (ACP)
+
+VT Code integrates natively with Zed IDE and other ACP-compatible editors. The ACP standardizes communication between code editors and coding agents.
+
+## Context Management
+
+Efficient context curation with:
+- Semantic search capabilities
+- Token budget tracking
+- Smart context window management
+
+---
+
+**GitHub**: https://github.com/vinhnx/vtcode  
+**Author**: Vinh Nguyen (@vinhnx)
+'''
+
+[actions."*".install]
+command = "cargo install --git https://github.com/vinhnx/vtcode"
+description = "Install VT Code via Cargo"