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 skills add ofershap/mcp-server-sqlite --skill sqlite-querygit clone --depth 1 https://github.com/ofershap/mcp-server-sqliteWrote 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/ofershap/mcp-server-sqlite/sqlite-query)<a href="https://agentmods.dev/skills/ofershap/mcp-server-sqlite/sqlite-query"><img src="https://agentmods.dev/badge/skills/ofershap/mcp-server-sqlite/sqlite-query/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/ofershap/mcp-server-sqlite/sqlite-query"><img src="https://agentmods.dev/badge/skills/ofershap/mcp-server-sqlite/sqlite-query.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 | $0.00024 | $0.00392 |
| Opus 5.5 | $0.00010 | $0.00157 |
| Sonnet 5.5 | $0.00005 | $0.00078 |
| Haiku 4.5 | $0.00002 | $0.00039 |
Grade A, and why
sqlite-query 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 1mo 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.
What it actually says
SQLite Query via MCP
Use this skill when you need to query SQLite databases, inspect schemas, or optimize queries. Read-only by default for safety.
Available Tools
| Tool | What it does |
|---|---|
query |
Execute SQL (SELECT, PRAGMA, EXPLAIN, WITH). Returns results as a table. |
schema |
Full schema: all tables with columns, types, and row counts |
table_info |
Detailed info for a single table: columns, constraints, row count |
explain |
Run EXPLAIN QUERY PLAN for query optimization |
list_databases |
List .db, .sqlite, .sqlite3 files in a directory |
Workflow
list_databasesto find .db files in the projectschemato understand the full database structuretable_infofor detailed column info on specific tablesqueryto run SELECT queries and inspect dataexplainto optimize slow queries
Key Patterns
- Read-only by default — only SELECT, PRAGMA, EXPLAIN, and WITH are allowed
- Pass
readonly: falsein tool args to enable INSERT, UPDATE, DELETE schemareturns everything at once — use it first to understand the databasequeryreturns tabular results — ideal for exploration and debugging- Database path is passed per-tool call, not globally configured
Safety
- Read-only mode is on by default — no accidental mutations
- Confirm with the user before enabling write mode (
readonly: false) - Large result sets are truncated — use LIMIT in queries for efficiency
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.
- 1mo ago First seen · 41 lines · 24 tokens per session scan A d48d502329da
sqlite-query is a skill published in the GitHub repository ofershap/mcp-server-sqlite (4 stars, last pushed 7mo ago), licensed MIT. It adds 24 tokens to every session and 392 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 2026-08-31.
Other skills, from other repositories
firebase-cloud-firestore
Use when setting up Firestore, designing schemas, doing CRUD, creating listeners, paginating queries, configuring indexes, enabling offline persistence, or writing security rules.
firebase-database
Use when syncing real-time data, structuring JSON trees, reading/writing, creating listeners, enabling offline persistence, managing presence, sharding, or writing security rules.
firebase-data-connect
Use when setting up Data Connect, writing GraphQL queries/mutations, configuring generated SDKs, handling offline, or applying security rules.
sql-optimization-patterns
Optimize SQL queries with indexing strategies, EXPLAIN analysis, and database performance tuning patterns. Use when the user needs to diagnose slow queries, design efficient schemas, or improve database-backed application performance.
kmd-lint
Health check for a markdown knowledge base (Obsidian-compatible, the LLM-wiki pattern) — personal or shared. Use whenever asked to lint, audit, check, review, or clean up a KB, on any scheduled hygiene/maintenance run, or when KB quality is in doubt (stale pages, contradictions, broken links, unprocessed sources…
RAG Workflow Planner
Designs a complete Retrieval-Augmented Generation (RAG) pipeline for a given use case, including chunking strategy, embedding model selection, and retrieval approach.