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 neverinfamous/memory-journal-mcp --skill sqlitegit clone --depth 1 https://github.com/neverinfamous/memory-journal-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/neverinfamous/memory-journal-mcp/sqlite)<a href="https://agentmods.dev/skills/neverinfamous/memory-journal-mcp/sqlite"><img src="https://agentmods.dev/badge/skills/neverinfamous/memory-journal-mcp/sqlite/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/neverinfamous/memory-journal-mcp/sqlite"><img src="https://agentmods.dev/badge/skills/neverinfamous/memory-journal-mcp/sqlite.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 | $0.00101 | $0.00953 |
| Opus 5 | $0.00051 | $0.00477 |
| Sonnet 5 | $0.00020 | $0.00191 |
| Haiku 4.5 | $0.00010 | $0.00095 |
Grade A, and why
sqlite 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 10d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SQLite Production Standards
SQLite provides lightweight, serverless SQL, but its default configurations are extremely permissive and optimized for backwards compatibility rather than production rigor.
Any AI agent interacting with or scaffolding SQLite databases MUST adhere to the following strict guidelines to prevent catastrophic concurrency failures, silent data corruption, or locking issues.
Agent Routing Rule: When encountering vague requests like "set up a database", you MUST refuse to guess and ask the user for the specific engine before assuming SQLite.
Concurrency & Performance (Critical Mandates)
SQLite only permits one writer at a time. To prevent random SQLITE_BUSY errors and enable high-performance read-while-writing:
- Enable WAL Mode: Generally, you should execute
PRAGMA journal_mode=WAL;immediately upon connection for high concurrency, unless the database is on a networked filesystem where WAL is unsafe. Ensure the-waland-shmsidecar files are managed alongside the main.dbfile. - Configure Timeouts: Set
PRAGMA busy_timeout=5000;so writers wait up to 5 seconds before failing. - Early Lock Acquisition: Use
BEGIN IMMEDIATE;to grab the write lock early and prevent deadlocks in read-then-write batch patterns, but note this locks the database for all other writers. - Synchronization:
PRAGMA synchronous=NORMAL;provides the best balance of safety and speed while in WAL mode.
Data Integrity & Type Safety
SQLite's default type system uses "Type Affinity" (it will happily accept the string "hello" in an INTEGER column) and ignores foreign keys.
- Foreign Keys: You MUST execute
PRAGMA foreign_keys=ON;on every single new database connection. It is not persisted. Without this,ON DELETE CASCADEfails silently. - Strict Typing: For all new tables, strongly prefer appending
STRICTto theCREATE TABLEstatement (e.g.,CREATE TABLE users (...) STRICT;) to enforce real data types. This is supported in SQLite 3.37.0+. - Date/Time Handling: There is no native DATE/TIME type. Standardize on
TEXT(ISO8601) orINTEGER(Unix timestamp). - Booleans: Do not use
BOOLEAN. UseINTEGER(0/1).TRUEandFALSEare just aliases.
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.
- 10d ago First seen · 50 lines · 101 tokens per session scan A c504006445c7
sqlite is a skill published in the GitHub repository neverinfamous/memory-journal-mcp (20 stars, last pushed 1mo ago), licensed MIT. It adds 101 tokens to every session and 953 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
migration-helper
Guide safe database and code migrations with zero-downtime strategies.
surrealdb-canonical-layer
Verify a SurrealDB-backed canonical layer directly, over the surrealdb MCP server, instead of writing a disposable Node script per check. Use whenever the user asks to confirm a batch of writes landed correctly ("did the FreedomFest speakers get tagged right", "do these people have an org relationship", "check that…
ontology
Manage ontology schemas, concepts, relationships, and alignments for Semantica knowledge graphs.
airtable
Read and write Airtable bases via the official REST API and the user's personal access token — list/filter records, create, update, delete. Use when asked to "add a row to Airtable", "find records in my base", "update this Airtable record".
activerecord
This skill should be used when the user asks to "write a migration", "add a column", "add column to table", "create an index", "add a foreign key", "set up associations", "fix N+1 queries", "optimize queries", "add validations", "create callbacks", "use eager loading", or mentions ActiveRecord, belongsto, hasmany…
skill-creator
Generate a new skill from a plain-language description — decides invocation control, arguments, and context cost, then scaffolds, validates, and tests it.