Borrowing it
Nothing to install: this file belongs to Xsaven/vector-memory-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Xsaven/vector-memory-mcp/master/.claude/agents/database-master.mdgit clone --depth 1 https://github.com/Xsaven/vector-memory-mcpWrote 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/agents/xsaven/vector-memory-mcp/database-master)<a href="https://agentmods.dev/agents/xsaven/vector-memory-mcp/database-master"><img src="https://agentmods.dev/badge/agents/xsaven/vector-memory-mcp/database-master/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/agents/xsaven/vector-memory-mcp/database-master"><img src="https://agentmods.dev/badge/agents/xsaven/vector-memory-mcp/database-master.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 | $0.00021 | $0.07434 |
| Opus 5.5 | $0.00008 | $0.02974 |
| Sonnet 5.5 | $0.00004 | $0.01487 |
| Haiku 4.5 | $0.00002 | $0.00743 |
Grade A, and why
database-master 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 2mo 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 — 535 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Industry Context:
- Vector memory integration: Hybrid (vector embeddings + structured metadata)
- Technologies: ChromaDB, FAISS, SQLite-vec, LanceDB
- Embeddings: sentence-transformers (all-MiniLM-L6-v2, 384-dimensional)
- Performance target: <200ms search for 10K memories
- Architecture: Dual-table design (memory_metadata + memory_vectors with vec0 virtual table)
Project Context:
- Database: SQLite 3.43.2 + sqlite-vec >= 0.1.6
- Schema: memory_metadata (content, category, tags, timestamps) + memory_vectors (vec0 virtual table)
- Indexes: category, created_at, content_hash, access_count
- WAL mode enabled for concurrent access
- SHA-256 content hashing for deduplication
- Smart cleanup algorithm (recency + access patterns)
Metadata: confidence=0.85, industry_alignment=0.85, priority=high
Wal mode optimization
SQLite Write-Ahead Logging (WAL) mode enables concurrent readers and writers without blocking.
- PRAGMA journal_mode=WAL
- PRAGMA synchronous=NORMAL
- PRAGMA busy_timeout=5000
- Readers: parallel unlimited, Writers: single sequential
- WAL checkpoint: automatic at 1000 pages or manual PRAGMA wal_checkpoint(TRUNCATE)
Sqlite vec patterns
sqlite-vec provides vec0 virtual table for efficient vector similarity search using cosine distance.
- CREATE VIRTUAL TABLE memory_vectors USING vec0(id INTEGER PRIMARY KEY, embedding FLOAT[384])
- vec_distance_cosine(embedding, query_vector) - Returns cosine distance [0,2] (lower = more similar)
- SELECT id FROM memory_vectors WHERE vec_distance_cosine(embedding, ?1) < 0.5 ORDER BY vec_distance_cosine(embedding, ?1) LIMIT 10
- Indexing: vec0 uses flat vector index (no HNSW yet), linear scan optimized in C
- Performance: ~50ms for 10K vectors on M1, scales linearly
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.
- 2mo ago First seen · 535 lines · 21 tokens per session scan A 63ef9026aa2b
database-master is an agent published in the GitHub repository Xsaven/vector-memory-mcp (0 stars, last pushed 8mo ago), licensed MIT. It adds 21 tokens to every session and 7,434 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 2026-09-01.
database-master compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| database-masterXsaven/vector-memory-mcp | Agent | 0 | 8mo ago | MIT | A | 21 | Claude Code |
| MS-SQL Database Administratorgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 18 | Claude Code |
| core-data-auditorCharlesWiltgen/Axiom | Agent | 1.3k | yesterday | MIT | A | 28 | Claude Code |
| lensjeremylongshore/tons-of-skills-marketplace | Agent | 2.9k | yesterday | MIT | A | 53 | Claude Code |
| ecto-schema-designeroliver-kriska/claude-elixir-phoenix | Agent | 574 | yesterday | MIT | A | 30 | Claude Code |
| django-migrations-specialistAratKruglik/claude-sdlc | Agent | 55 | 11d ago | MIT | A | 85 | Claude Code |
| yd-oracle-expertLeeYudok/agents-scaffold | Agent | 38 | yesterday | MIT | A | 100 | Claude Code |