Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/DDS-Solutions/AI-TadPole-OSnpx agentmods add skills/dds-solutions/ai-tadpole-os/vector-memory-lancedbWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/dds-solutions/ai-tadpole-os/vector-memory-lancedb)<a href="https://agentmods.dev/skills/dds-solutions/ai-tadpole-os/vector-memory-lancedb"><img src="https://agentmods.dev/badge/skills/dds-solutions/ai-tadpole-os/vector-memory-lancedb/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/dds-solutions/ai-tadpole-os/vector-memory-lancedb"><img src="https://agentmods.dev/badge/skills/dds-solutions/ai-tadpole-os/vector-memory-lancedb.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00030 | $0.00790 |
| Opus 5.5 | $0.00012 | $0.00316 |
| Sonnet 5.5 | $0.00006 | $0.00158 |
| Haiku 4.5 | $0.00003 | $0.00079 |
Grade A, and why
vector-memory-lancedb scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
[!IMPORTANT] AI Context & Knowledge Heritage
- Subsystem: Agent Skills Registry / vector-memory-lancedb
- Architecture:
@docs ARCHITECTURE:Documentation- Failure Path: Embedding dimension mismatch, vector index corruption, high drift queries.
- Observability: Traceability via
execution/parity_guard.py([SKILL])
LanceDB Vector Memory & Semantic Retrieval Protocol
Purpose: Manage embedded vector storage, enforce deduplication thresholds, and power fast semantic RAG memory in Tadpole OS. Workflow Binding: Used during
/refactorand/debug.
🎯 Progressive Disclosure & L3 Reference Index
Read REQUIRED core standards below; consult deep L3 Reference Guides on demand:
| L3 Reference Guide / Tool | Purpose | Trigger / When to Load |
|---|---|---|
references/lancedb_vector_rag_recipes.md |
PyArrow schema definitions, cosine search parameters, indexing options (IVF-PQ) | Setting up vector tables or tuning semantic query recall |
scripts/vector_memory_validator.py |
Deterministic vector similarity validator and deduplication boundary checker | Verifying embedding calculations or self-test validation |
🏛️ Core Architectural Invariants
- Strict Dimensionality Matching: All vectors ingested into a table must match the table's declared fixed dimension (e.g., 768 for Gemma/Nomic).
- Deduplication Threshold (
LANCEDB_DEDUPE_THRESHOLD): Retain default0.92. If an incoming document vector has cosine similarity $\ge 0.92$ to an existing record, update the existing entry rather than creating duplicates. - Drift Detection (
LANCEDB_DRIFT_THRESHOLD): If the nearest vector distance exceeds0.35, flag the retrieval as low-confidence and trigger fallback search.
🛡️ Socratic Gate: Vector Ingestion & Query Tuning
Before executing vector operations:
- Model & Dimension Consistency: Is the embedding model consistent across writes and reads?
- Batch Processing: Are bulk document ingestions batched rather than committed per-record?
- Payload Sanitization: Are text chunks stripped of raw secrets or sensitive tokens before embedding?
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 68 lines · 30 tokens per session scan A 56fd3fd53a49
vector-memory-lancedb is a skill published in the GitHub repository DDS-Solutions/AI-TadPole-OS (8 stars, last pushed 2d ago), licensed MIT. It adds 30 tokens to every session and 790 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-18.
Other skills, from other repositories
langchain
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG…
graphify-windows
Turn any folder of files into a navigable knowledge graph with community detection, an honest audit trail, and three outputs: interactive HTML, GraphRAG-ready JSON, and a plain-language GRAPHREPORT.md.
langchain
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG…
llm-wiki
Karpathy's LLM Wiki — build and maintain a persistent, interlinked markdown knowledge base. Ingest sources, query compiled knowledge, and lint for consistency.
langchain
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG…
langchain
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG…