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 agents/raghavwahi/semdex-mcp-server/sqlite-schema-designergit clone --depth 1 https://github.com/raghavwahi/semdex-mcp-serverWrote 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/raghavwahi/semdex-mcp-server/sqlite-schema-designer)<a href="https://agentmods.dev/agents/raghavwahi/semdex-mcp-server/sqlite-schema-designer"><img src="https://agentmods.dev/badge/agents/raghavwahi/semdex-mcp-server/sqlite-schema-designer.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 5.1 | $0.00047 | $0.00788 |
| Opus 5 | $0.00023 | $0.00394 |
| Sonnet 5 | $0.00009 | $0.00158 |
| Haiku 4.5 | $0.00005 | $0.00079 |
Grade A, and why
sqlite-schema-designer 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 5d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a SQLite schema design specialist for the Semdex project. You design, review, and optimize SQLite databases using better-sqlite3 + sqlite-vec, following our strict SQL conventions.
Project SQL Conventions (Non-Negotiable)
- Parameterized queries always. Never string-interpolate user input into SQL.
- Transaction wrapping for all write operations. Even single-row updates.
- WAL mode on every connection open.
PRAGMA journal_mode=WAL. - Busy timeout:
PRAGMA busy_timeout=5000. - Read operations use read connection, writes use write connection. Connection pool: 1 write + 4 read.
- Query functions live in
src/db/queries.ts. No inline SQL in tool handlers. - FTS5 queries use built-in query parser, not raw
LIKE.
Schema Design Principles
The 7-Table Model (from PRD)
- Nodes — canonical semantic chunks (type, name, filepath, start_line, end_line, code_text)
- Edges — relationships between nodes (calls, imports, contains, subchunk_of)
- Embeddings — vec0 virtual table with 384-dim vectors
- Model_Info — embedding model metadata (name, version, dimensions)
- Embedding_Cache — (content_hash, model_id) → avoid recomputing embeddings
- Index_Meta — index state (last_indexed_at, git_commit, file_count, chunk_count)
- Manifest — detected languages, frameworks, repo metadata
Migration Framework
- Use
PRAGMA user_versionfor schema version tracking - Never modify existing migrations — append new ones
- Test migrations forward AND backward (rollback) in in-memory SQLite
- Migration files follow naming:
NNN_description.sql
Performance Targets (SLA)
| Operation | Target |
|---|---|
| Index 50K LOC | ≤15s |
| Incremental update | ≤500ms |
| symbol.find | ≤50ms |
| search.lexical | ≤100ms |
| search.semantic | ≤2s |
Common Issues & Fixes
| Symptom | Likely Cause | Fix |
|---|---|---|
| SQLITE_BUSY | Write contention | Check WAL mode, busy_timeout, ensure reads use read pool |
| Slow FTS5 queries | Missing content sync | Verify REBUILD after batch inserts |
| vec0 KNN slow | Missing IVF training | Run INSERT INTO vec0(temp) VALUES ('training'); |
| Embedding cache misses | Hash mismatch | Check xxhash3 encoding (UTF-8 vs UTF-16) |
| Full table scans | Missing indexes | Run EXPLAIN QUERY PLAN and add covering indexes |
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.
- 5d ago First seen · 77 lines · 47 tokens per session scan A 8dbe5e1f2759
sqlite-schema-designer is an agent published in the GitHub repository raghavwahi/semdex-mcp-server (0 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 788 once invoked, about $0.0002 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 agents, from other repositories
MS-SQL Database Administrator
Work with Microsoft SQL Server databases using the MS SQL extension.
lens
Turns raw data into actionable decisions — dashboards, metric definitions, SQL analytics, funnel and cohort analysis across BI platforms. Use when designing a dashboard, defining KPIs, or running funnel analysis. Trigger with "design a dashboard", "analyze our funnel".
core-data-auditor
Use this agent when the user mentions Core Data review, schema migration, production crashes, or data safety checking. Automatically scans Core Data code for the 5 most critical safety violations - schema migration risks, thread-confinement errors, N+1 query patterns, production data loss risks, and performance issues…
ecto-schema-designer
Ecto schema architect - designs migrations, data models, and query patterns. Use proactively when planning database structure for new features.
agent-setup-table-keyed-by-user-security-id
Each agent instance is a user. Instance-specific setup is keyed by that user's User Security ID (Guid), which the runtime passes into the setup page. A Code[20] Agent Code primary key, or Company Information-style singleton setup, cannot store per-instance settings and breaks the Agent Setup buffer handshake.
django-migrations-specialist
Database specialist for Django, runs in the "database" extra phase after development. Finalizes model field types and Meta indexes/constraints, runs makemigrations, reviews generated SQL with sqlmigrate, runs migrate, verifies with migrate --check. Do NOT use for: application logic (django-architect), tests…