nlqdb

nlqdb/nlqdb

Plugin Claude Code

nlqdb's own plugins — analytical agent memory over MCP, from the repo that serves it.

nlqdb/nlqdb

Command Claude Code

You are the daily operating agent for nlqdb. One run = one measured improvement — or an explicit null run (step 2) when no lever clears the bar. An artifact ships per step 3 when the queue is ready, but an artifact is never the run's justification (founder-resolved 2026-07-11). Work autonomously end-to-end; the…

nlqdb/nlqdb

Command Claude Code

You are the EK agent for nlqdb. One run = one EK-slice progressed on docs/features/expert-knowledge-platform/worksheets/INDEX.md — or an explicit null run. Work autonomously end-to-end; the founder is not watching and must not be pinged. This loop exists because SK-EKP-005 made the marketplace a parallel track while…

nlqdb/nlqdb

Command Claude Code

Enter a very lean operating mode for the main conversation. You are the founder's orchestrator and observability layer, not a worker. Every token spent in this thread is a token stolen from the founder's next question — spend as few as possible and keep the context window clean for their follow-ups.

nlqdb/nlqdb

Command Claude Code

You are the reach agent for nlqdb. One run = one R-slice progressed on docs/features/agent-memory-pivot/worksheets/reach/INDEX.md — or an explicit null run. Work autonomously end-to-end; the founder is not watching and must not be pinged. This loop exists so acquisition work is never starved by /daily's worst-number…

nlqdb/nlqdb

Command Claude Code

Your review criteria: security (including sql injection), readability, scalability, consistency, reusability, developer experience and most importantly user experience (minimum actions for maximum value and minimum user-regretted-seconds like interruptions / spam etc), observability (non-spammy), robustness…

nlqdb/nlqdb

Command Claude Code

You audit the daily loop and point it in the right direction. There are no time-boxed goals: the job is week-over-week direction and honesty of the numbers, not deadlines. Work autonomously; the founder is not watching. Human-only needs go to docs/blocked-by-human.md, nothing else pings the founder. Obey CLAUDE.md…

nlqdb/nlqdb

Instructions file CodexOpenCode

AGENTS.md instructions for nlqdb/nlqdb, covering agents guide — nlqdb, 1. what nlqdb is, north-star — what every pr moves, 2. six behavioral principles (non-negotiable) and p1. never contradict documented decisions silently.

nlqdb/nlqdb

Instructions file

Claude Code instructions for nlqdb/nlqdb, a project described as: Simplest Natural Langauge Querying DB That scales. Fast.

nlqdb/nlqdb

Plugin Claude Code

Persistent, queryable memory for your agent: a real Postgres it asks in plain English over MCP, so it can GROUP BY / JOIN / aggregate over what it remembered instead of recalling the nearest few rows. Bundles the hosted MCP server plus two skills that teach the agent when to use it.

nlqdb/nlqdb

MCP server Claude CodeCodexCursor

MCP server "nlqdb", hosted remotely at mcp.nlqdb.com, as configured in nlqdb/nlqdb.

nlqdb/nlqdb

Skill Claude CodeCodex

Turn this repo's markdown docs into a queryable nlqdb memory database — decision IDs and statuses, open questions with ages, queues, ledgers, and the cross-references between them. Use when asked which features have stale open questions, which decisions reference a given ID, what is blocked and since when, or to…

nlqdb/nlqdb

Cursor rule

Use nlqdb as this agent's analytical memory — persist and query memory in plain English over MCP.

nlqdb/nlqdb

Skill Claude CodeCodex

Give this agent persistent, queryable memory over the nlqdb MCP server. Use whenever the agent needs to remember something across sessions, recall what it stored, or aggregate over its memory (GROUP BY / JOIN / counts / trends) — backed by a real Postgres it queries in plain English, not a vector store.

nlqdb/nlqdb

MCP server Claude CodeCodexCursor

Analytical memory for AI agents: a real Postgres queried in plain English over MCP. One command. Remote server at mcp.nlqdb.com.