how-it-works
claude-mem automatically converts file reads, edits, and bash commands into compressed observations that summarize at session end. Starting with the second session in a project, relevant observations auto-inject into future prompts, providing continuity without re-explaining context. All data persists locally in ~/.claude-mem, with only compression requests sent to configured AI providers.
git clone --depth 1 https://github.com/thedotmack/claude-mem /tmp/how-it-works && cp -r /tmp/how-it-works/plugin/skills/how-it-works ~/.claude/skills/how-it-worksSKILL.md
# 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`.
Watch a pull request or review cycle until it is ready to merge. Use when asked to babysit, monitor, or keep checking PR comments, reviews, and CI until all actionable issues are resolved.
Audit a design against Dieter Rams' ten "Good design is..." principles, then hand off a /make-plan prompt for one of three outcomes — new design, refine design, or redesign. Use when the user says "audit this design", "design review", "check this UI against Rams", "is this UI good", "critique this design", "design audit", or asks for a critique that should lead to a plan.
Execute a phased implementation plan using subagents. Use when asked to execute, run, or carry out a plan — especially one created by make-plan.
Build and query AI-powered knowledge bases from claude-mem observations. Use when users want to create focused "brains" from their observation history, ask questions about past work patterns, or compile expertise on specific topics.
Prime a codebase by reading every source file in full. Use when starting work on a new or unfamiliar project, or when the user asks to "learn the codebase", "read the codebase", "prime", or "get up to speed".
Create a detailed, phased implementation plan with documentation discovery. Use when asked to plan a feature, task, or multi-step implementation — especially before executing with do.
Search claude-mem's persistent cross-session memory database. Use when user asks "did we already solve this?", "how did we do X last time?", or needs work from previous sessions.