--- title: "Memory hook bundle, auto-persist sessions, snapshot before compact, recall on trigger | Recipe — StudioMeyer Academy" description: "Four mcp_tool hooks for the StudioMeyer Memory MCP that turn it from 'a tool I call manually' into 'a memory layer that always knows what I did'. Stop, PreCompact, UserPromptSubmit, SubagentStop, all idempotent, all fast." canonical: "https://studiomeyer.academy/en/recipes/16.2-memory-hook-bundle" language: en markdown_versions: ["https://studiomeyer.academy/en/recipes/16.2-memory-hook-bundle.md"] publisher: "StudioMeyer Academy, https://studiomeyer.academy (llms.txt: https://studiomeyer.academy/llms.txt)" --- [← Alle Recipes](https://studiomeyer.academy/recipes) Phase 16 · Claude Code Hooks·6 steps # Memory hook bundle, auto-persist sessions, snapshot before compact, recall on trigger Four mcp\_tool hooks for the StudioMeyer Memory MCP that turn it from 'a tool I call manually' into 'a memory layer that always knows what I did'. Stop, PreCompact, UserPromptSubmit, SubagentStop, all idempotent, all fast. 6 steps0% Du liest ohne Account. Mit [Login](https://studiomeyer.academy/login?next=/recipes/16.2-memory-hook-bundle) speichern wir Step-Fortschritt + Notes. # Memory hook bundle, auto-persist sessions, snapshot before compact, recall on trigger The Memory MCP (`studiomeyer-memory`, hosted at `memory.studiomeyer.io`) has 56 tools. Without hooks, you call them manually: `nex_session_start` at the beginning, `nex_summarize` and `nex_session_end` at the end, `nex_search` when you need recall. That's a lot of clicking, and it's easy to forget the end-of-session calls. This bundle wires four hooks that do all of it automatically. Effect: every Claude Code session is persisted to long-term memory without touching a tool by hand. ### Step 1: Stop hook → auto-summarize and end session Add this to `~/.claude/settings.json` under `hooks.Stop`: ```json { "Stop": [ { "hooks": [ { "type": "mcp_tool", "server": "studiomeyer-memory", "tool": "nex_summarize", "input": { "session_id": "${session_id}" }, "timeout": 30, "statusMessage": "Memory: summarizing session..." }, { "type": "mcp_tool", "server": "studiomeyer-memory", "tool": "nex_session_end", "input": { "session_id": "${session_id}" }, "timeout": 15, "statusMessage": "Memory: closing session..." } ] } ] } ``` Two hooks fire on Stop: first summarize (writes a session snapshot into the `nex_sessions` table), then close. Both are idempotent, calling them twice on the same session is a NOOP. ### Step 2: PreCompact hook → snapshot before context loss Context compaction throws away part of the in-window history. Before that happens, snapshot: ```json { "PreCompact": [ { "hooks": [ { "type": "mcp_tool", "server": "studiomeyer-memory", "tool": "nex_summarize", "input": { "session_id": "${session_id}" }, "timeout": 30, "statusMessage": "Memory: snapshot before compaction..." } ] } ] } ``` Why duplicate `nex_summarize` between Stop and PreCompact? Because Stop only fires when the session ends. If the session is long and gets compacted mid-flow, you lose the pre-compact context unless you snapshot it first. Both calls are idempotent so the duplicate is safe. ### Step 3: UserPromptSubmit hook → recall on trigger phrases When you ask "have we discussed this before" or "what do we know about X", the assistant should consult Memory before guessing. Wire it explicitly: ```json { "UserPromptSubmit": [ { "hooks": [ { "type": "mcp_tool", "server": "studiomeyer-memory", "tool": "nex_search", "input": { "query": "${user_prompt}", "limit": 5 }, "timeout": 10, "statusMessage": "Memory: pre-checking..." } ] } ] } ``` This fires on every user prompt and pre-fetches up to 5 relevant memories. The result is injected into the assistant's context as `additionalContext`. The assistant doesn't have to remember to call `nex_search` first, the hook does it transparently. If you only want this on specific trigger phrases (to save a tool call per prompt), add a server-side `if`\-filter, but `if`\-filters only work on Tool-Events, not on `UserPromptSubmit`. Easier path: use the existing user-level `memory-first-check.sh` bash hook which already does keyword filtering, and skip this `mcp_tool` variant. ### Step 4: SubagentStop hook → ingest research reports When you spawn a subagent (e.g. via the Task tool) and it returns a long research report, you want the key findings persisted. The SubagentStop hook fires when the subagent finishes: ```json { "SubagentStop": [ { "hooks": [ { "type": "mcp_tool", "server": "studiomeyer-memory", "tool": "nex_learn", "input": { "category": "research", "insight": "${last_assistant_message}", "confidence": 0.6, "source": "subagent-stop-hook" }, "timeout": 15, "statusMessage": "Memory: ingesting subagent report..." } ] } ] } ``` The `last_assistant_message` substitution variable contains the subagent's final output. `nex_learn` runs the gatekeeper which deduplicates against existing learnings, so re-calling on the same content is a NOOP. ### Step 5: GDPR + idempotency notes All four hooks satisfy the five-rule check from recipe 16.1: - **Idempotent.** `nex_summarize` and `nex_session_end` are NOOP on duplicate. `nex_search` is read-only. `nex_learn` deduplicates via the gatekeeper. - **Fast.** All four are typically under 2 seconds against a warm database. Cold start (first call after deploy) can hit 5-8 seconds, well under the 30s timeout. - **Deterministic.** Same session\_id, same summary. Same query, similar (not identical, due to recency-decay) recall ranking. - **Side-effect-free without user trigger.** `nex_search` is read-only. `nex_summarize` writes to `nex_sessions`, but the user implicitly triggered it by ending the session. `nex_learn` writes to `nex_learnings`, but the user implicitly triggered it by spawning the subagent. - **GDPR.** All data flows from your Claude Code session to your own Memory tenant on `memory.studiomeyer.io`. No third-party sharing. Tenant data is isolated per `tenant_id`. You can delete your tenant any time via the dashboard. ### Step 6: Verify the bundle works ```bash # Edit settings.json with all four hooks above, then: claude # Type a few prompts, then Ctrl-D ``` Check the Memory dashboard at `https://memory.studiomeyer.io/dashboard`, you should see the new session listed under "Sessions" with the auto-generated summary. The `nx_learnings` count should not have changed (no subagent was spawned). Then re-run with a subagent: ```bash claude # Ask: "use the research subagent to find 3 articles about MCP hooks" # After the subagent finishes and you Ctrl-D ``` The dashboard should now show 1 new learning under category=research. ## Done Memory is fully agentic. Every session you run gets persisted automatically. Every research subagent's findings land in your knowledge base without manual `nex_learn` calls. ## Sources - [Claude Code Hooks Reference](https://code.claude.com/docs/en/hooks) - [StudioMeyer Memory MCP Documentation](https://memory.studiomeyer.io) [← The mcp\_tool hook, direct MCP](https://studiomeyer.academy/recipes/16.1-mcp-tool-hook-intro) [CRM hook bundle, auto-lookup c →](https://studiomeyer.academy/recipes/16.3-crm-hook-bundle) Phase 16 mcp\_tool hooks, Memory/CRM/GEO/Crew/Academy hook bundles [Alle Phasen →](https://studiomeyer.academy/recipes) Concepts [Hooks](https://studiomeyer.academy/concepts/hooks) [Memory basics](https://studiomeyer.academy/concepts/memory_basics) ## Sitemap Public pages of this site as Markdown: [sitemap](https://studiomeyer.academy/sitemap.md). Curated entry point: [llms.txt](https://studiomeyer.academy/llms.txt), full text: [llms-full.txt](https://studiomeyer.academy/llms-full.txt).