Skip to main content
subagent CX Codex

mind-wasp-drone — Claude Code subagent: cognitive-layer review

mind-wasp-drone — a subagent for auditing and tuning everything LLM in your codebase: agent routing, prompt cascades, RAG, memory tiers, tracing, and streaming responses. Call it when you work on AI code, retrieval, or memory.

AGPL-3.0-or-later ★ 96 updated 2026-10-18

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add legioncodeinc/vibe-coding-tools
/plugin install data-and-ai-tools@wasp-nest
Open on GitHub

What mind-wasp-drone does

mind-wasp-drone owns the cognitive layer: coach-agent lineups, five-tier prompt cascades, three-tier memory (ephemeral cache, Postgres, retrieval substrate), per-call tracing of LLM invocations, retrieval and routing evaluation, multimodal pipelines, and orchestration. It checks each subsystem as a stack-neutral architecture first, then against your project's actual choice.

This project uses Neon Postgres plus pgvector by default, via vector-store-wasp-drone and retrieval-wasp-drone. If you already run Qdrant, Cohere, Valkey, or OpenRouter, that alternative stack remains fully documented and valid. The subagent stays out of chat UI, table indexing, security audits, and feature specs — other agents handle those.

Invoke for RAG audits, memory refactors, GraphRAG enablement, prompt cascade tweaks, streaming LLM responses over SvelteKit +server.ts on Vercel, or whenever you touch the cognitive layer in a PR.

What it helps with

  • Audit a RAG system and verify two-stage recall-then-rerank retrieval
  • Design a coach-agent architecture with per-call routing traces and metrics
  • Build a three-tier memory system across LLM invocations
  • Enable GraphRAG or swap retrieval substrates without data loss
  • Stream an LLM response to a client over SvelteKit on Vercel

Example prompts for the agent

  • Audit the RAG pipeline with a query and check recall-rerank stages
  • Review the prompt cascade and agent routing traces
  • Enable GraphRAG while preserving the current Postgres retrieval

How to install mind-wasp-drone

1Plugin marketplace

/plugin marketplace add legioncodeinc/vibe-coding-tools
/plugin install data-and-ai-tools@wasp-nest

2Manually: put the files in place

.claude/agents/mind-wasp-drone.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about mind-wasp-drone

How do I install mind-wasp-drone in Claude Code?

Run /plugin marketplace add legioncodeinc/vibe-coding-tools, then /plugin install data-and-ai-tools@wasp-nest and add .claude/agents/mind-wasp-drone.md to your config. For Codex, use .codex/agents/mind-wasp-drone.toml.

What does mind-wasp-drone review?

The cognitive layer: agent routing, prompts, RAG, memory tiers, LLM-call tracing, and response streaming. It examines architecture as a concept first, then checks your project's specific stack.

Which retrieval substrate does it use by default?

Neon Postgres with pgvector, implemented via vector-store-wasp-drone and retrieval-wasp-drone. Qdrant, Cohere, Valkey, and OpenRouter are fully supported alternatives for projects already running them.

Similar subagents

All subagents for Agent setup: memory, context, orchestration →

From the same set172

The whole set →
ci-release-stinger ci-release-stinger is a Claude Code skill that designs and reviews CI and release workflows for SvelteKit apps on Vercel and npm packages. It activates for requests about Actions jobs, migrations, caching, or publishing. CX Codex +1 ★ 96repo stars meeting-scribe meeting-scribe turns Littlebird records into shareable follow-up messages. Anchors decisions to exact quotes and timestamps, surfaces unresolved questions, and splits recaps for different recipients. CX Codex +1 ★ 96repo stars competitor-watch competitor-watch tracks market competitors and new entrants by fusing internal interaction logs with web search results. CX Codex +1 ★ 96repo stars typescript-node-wasp-drone typescript-node-wasp-drone reviews TypeScript and Node.js projects built as SvelteKit apps on Vercel or npm libraries and CLIs. Use it for typing, validation, tests, and project tooling. CX Codex ★ 96repo stars money-leak-auditor money-leak-auditor audits SaaS and vendor spending through Littlebird screen capture. Flags forgotten tools, failed card charges, and billing leaks. CX Codex +1 ★ 96repo stars renewal-sentinel The renewal-sentinel skill finds upcoming charges, renewals, and cancellation cutoffs in Littlebird records. Use it when planning decisions over the next 90 days. CX Codex +1 ★ 96repo stars deal-pipeline-reconstructor The deal-pipeline-reconstructor skill assembles your deals from messages, calls and notes into a structured board. Sellers without a CRM can see what stage each opportunity is at, what evidence supports it, and which ones have gone quiet. CX Codex +1 ★ 96repo stars lead-harvester lead-harvester reconstructs contact lists from comment-to-DM campaigns, scores buyer intent, and drafts initial replies. CX Codex +1 ★ 96repo stars

Project sponsors

Companies that keep this analytics open