ai-tools-platform-wasp-drone — Claude Code subagent: what it does
ai-tools-platform-wasp-drone picks the AI gateway, cloud provider, model tier and GPU cloud for a given task. Triggers on requests like "which AI provider should I use" or "set up Portkey".
AGPL-3.0-or-later ★ 96 updated 2026-10-18
/plugin marketplace add legioncodeinc/vibe-coding-tools
/plugin install data-and-ai-tools@wasp-nestWhat ai-tools-platform-wasp-drone does
This subagent handles the full path from a developer's intent to a running LLM: choosing between gateways like Portkey and OpenRouter, cloud providers such as AWS Bedrock, Vertex AI and Azure OpenAI, frontier models (Claude, GPT, Gemini) paired with a cheap fallback tier (Haiku, Mini, Flash), local setups on Ollama or LM Studio, and GPU cloud vendors including Runpod, Modal, Together, Fireworks and Groq.
Before answering, it reads the ai-tools-platform-stinger/SKILL.md master index for the stack's default picks, then opens the guide matching the request: gateway setup, provider selection, model selection, cost optimization, local LLM workflow, GPU cloud, or MCP and IDE plugin setup. Its baseline leans on Portkey for production, Sonnet for the frontier tier and Modal for serverless GPU work, adjusted for budget, privacy needs or a client's existing cloud.
Key storage and rotation stay with security-wasp-drone, and RAG or memory architecture goes to mind-wasp-drone; this agent hands those off instead of covering them itself.
What it helps with
- pick an AI gateway between Portkey and OpenRouter
- choose a cloud provider among AWS Bedrock, Vertex AI and Azure OpenAI
- set a cheap fallback model for a production workload
- set up a local LLM run through Ollama or LM Studio
- compare GPU cloud vendors for open-weight model inference
Example prompts for the agent
- Which AI provider should I use for a new Claude-based service?
- Set up Portkey as the gateway for production
- Compare Runpod and Modal for serving an open-weight model
How to install ai-tools-platform-wasp-drone
1Plugin marketplace
/plugin marketplace add legioncodeinc/vibe-coding-tools/plugin install data-and-ai-tools@wasp-nest2Manually: put the files in place
.claude/agents/ai-tools-platform-wasp-drone.mdFor all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention
Manually: put the files in place
.codex/agents/ai-tools-platform-wasp-drone.tomlCodex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/
Manually: put the files in place
.cursor/agents/ai-tools-platform-wasp-drone.mdCursor also reads .claude/agents/
Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean
Questions about ai-tools-platform-wasp-drone
How do I install ai-tools-platform-wasp-drone in Claude Code?
Run /plugin marketplace add legioncodeinc/vibe-coding-tools, then /plugin install data-and-ai-tools@wasp-nest.
What does ai-tools-platform-wasp-drone do?
It selects an AI gateway, cloud provider, frontier and cheap-tier models, local LLM setup, GPU cloud vendor and the MCP servers a project needs.
How does ai-tools-platform-wasp-drone differ from mind-wasp-drone and security-wasp-drone?
It skips RAG pipeline and memory architecture, which belongs to mind-wasp-drone, and leaves API key storage to security-wasp-drone.