deeplake-dataset-wasp-drone — Claude Code subagent setup
deeplake-dataset-wasp-drone is a Claude Code subagent for Deep Lake schemas, indexes, schema healing, and BYOC storage. It handles Hivemind data tasks.
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 deeplake-dataset-wasp-drone does
This subagent handles Deep Lake data architecture across Hivemind projects. It enforces schema single-sourcing inside src/deeplake-schema.ts across seven core tables: memory, sessions, skills, rules, goals, kpis, and codebase. The agent constructs DDL using USING deeplake, formats FLOAT4[768] nomic-embed-text-v1.5 embeddings, and isolates JSONB payloads.
Schema updates follow strictly additive healing via healMissingColumns(). Blanket ALTER TABLE calls and IF NOT EXISTS syntax are prevented because Deep Lake emits HTTP 500 errors on collision. Indexing uses a dedicated routing tree: ensureLookupIndex for hot filters, <#> cosine operators for raw vectors, and deeplake_hybrid_record for hybrid queries. BM25 indexes are explicitly barred from the memory table due to an internal OID issue.
Execution requires the companion skill deeplake-dataset-stinger resolved beforehand. API requests through DeeplakeApi are constrained by a concurrency semaphore of 5 and monitor HTTP 402 responses for depleted balances.
What it helps with
- Generate USING deeplake DDL tables from ColumnDef definitions
- Heal missing schema columns without breaking existing table structures
- Select between BM25, cosine vector, and hybrid record indexes
- Configure DeeplakeApi rate limits, retries, and storage schemes
Example prompts for the agent
- Review this ColumnDef definition and verify default values for NOT NULL columns
- Which storage backend should we use: s3://, mem://, or al:// with a creds_key?
- Design an additive schema heal plan for missing columns in deeplake-schema.ts
How to install deeplake-dataset-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/deeplake-dataset-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/deeplake-dataset-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/deeplake-dataset-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 deeplake-dataset-wasp-drone
How to install deeplake-dataset-wasp-drone in Claude Code?
Run /plugin marketplace add legioncodeinc/vibe-coding-tools, execute /plugin install data-and-ai-tools@wasp-nest, then load .claude/agents/deeplake-dataset-wasp-drone.md.
What is the primary scope of this subagent?
It manages Hivemind Deep Lake schemas, DDL creation, indexing trees, query concurrency guards, dataset branching, and BYOC backend selection.
Does this subagent handle credential audits or RAG tuning?
No. It flags security audits, PRD drafting, and embedding retrieval tuning so dedicated companion drones can take over.