Agent skill · writing content · thedotmack
how-it-works
Explain how claude-mem captures observations, when memory injection kicks in, and where data lives. Use when the user asks "how does claude-mem work?" or "what is this thing doing?".
Why this skill is useful
Codifies the specific memory injection process and data storage details for claude-mem, which the AI could infer but doesn't have explicit knowledge of.
What it needs
About 1k tokens when loaded. Last updated 2026-08-05. 89,894 stars on the source repository.
What this skill does
How claude-mem works What it does Every Read, Edit, and Bash that Claude makes turns into a compressed observation. Observations get summarized at session end. Relevant ones get auto-injected into future prompts so the next session starts with context from the last one — no re-explaining the codebase, no re-discovering decisions. When it kicks in Memory injection starts on your second session in a project. The first session in a fresh project seeds memory; subsequent sessions receive auto-injected context for relevant past work. Run /learn-codebase if you want to front-load the entire repo into memory in a single pass (~5 minutes, optional). Where data lives Everything stays in ~/.claude-mem on this machine. Nothing leaves your machine except calls to whichever AI provider you configured for compression (Claude / OpenRouter / Gemini). The SQLite database, vector index, logs, and settings all live under that directory and are removed cleanly on npx claude-mem uninstall.
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills thedotmack/how-it-works