Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/sandraschi/database-operations-mcp/database-expertnpx skills add sandraschi/database-operations-mcp --skill database-expertgit clone --depth 1 https://github.com/sandraschi/database-operations-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/skills/sandraschi/database-operations-mcp/database-expert)<a href="https://agentmods.dev/skills/sandraschi/database-operations-mcp/database-expert"><img src="https://agentmods.dev/badge/skills/sandraschi/database-operations-mcp/database-expert.svg" alt="Measured on agentmods" 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 | $0.00020 | $0.00496 |
| Opus 5 | $0.00010 | $0.00248 |
| Sonnet 5 | $0.00004 | $0.00099 |
| Haiku 4.5 | $0.00002 | $0.00050 |
Grade A, and why
database-expert 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 3d 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Database expert skill
When helping with databases, use the Database Operations MCP server's tools in this order.
1. Connections
- List supported types:
db_connection(operation="list_supported")— SQLite, PostgreSQL, MySQL, DuckDB, MongoDB, Redis, LanceDB, ChromaDB. - List registered:
db_connection(operation="list"); get/set active:get_active,set_activewith connection_name. - Register:
db_connection(operation="register", connection_name=..., database_type=..., connection_config={...}). For SQLite use{"database": "/path/to/file.db"}; for PostgreSQL use host, port, user, password, database. - Test:
db_connection(operation="test", connection_name=...).
Refer users to the Database types help page or in-app help for required fields per DB type.
2. Schema
- List databases:
db_schema(operation="list_databases", connection_name=...). - List tables:
db_schema(operation="list_tables", connection_name=..., database_name=...). - Describe table:
db_schema(operation="describe_table", connection_name=..., table_name=...)for columns and types.
3. Queries and data
- Read-only SQL:
db_operations(operation="execute_query", connection_name=..., query="SELECT ...", limit=...). Prefer parameterized queries when user input is involved. - Quick sample:
db_operations(operation="quick_data_sample", connection_name=..., table_name=..., limit=...). - Writes: Use
execute_writeorbatch_insertonly when the user clearly intends to change data.
4. Health and management
- Health check:
db_management(operation="database_health_check", connection_name=...). - Metrics:
db_management(operation="get_database_metrics", connection_name=...).
Best practices
- Confirm the active connection or ask which connection to use when multiple exist.
- Suggest limits (e.g. LIMIT 100) for ad-hoc SELECTs.
- Point users to the Add connection wizard or Database types help when they are unsure how to connect.
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.
- 3d ago First seen · 40 lines · 20 tokens per session scan A a024355679b5
database-expert is a skill published in the GitHub repository sandraschi/database-operations-mcp (3 stars, last pushed 17d ago), licensed MIT. It adds 20 tokens to every session and 496 once invoked, about $0.0001 per session on Opus 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 2026-08-31.
Other skills, from other repositories
cdc
Change Data Capture - architecture, entrypoints, bytecode emission, sync engine integration, tests.
async-io-model
Explanations of common asynchronous patterns used in tursodb. Involves IOResult, state machines, re-entrancy pitfalls, CompletionGroup. Always use these patterns in core when doing anything IO.
differential-fuzzer
Information about the differential fuzzer tool, how to run it and use it catch bugs in Turso. Always load this skill when running this tool.
storage-format
SQLite file format, B-trees, pages, cells, overflow, freelist that is used in tursodb.
mvcc
Overview of Experimental MVCC feature - snapshot isolation, versioning, limitations.
transaction-correctness
How WAL mechanics, checkpointing, concurrency rules, recovery work in tursodb.