Hook scripts reference

Claude Mem registers hooks via plugin/hooks/hooks.json. At runtime, Claude Code fires lifecycle events and Claude Mem responds by running the appropriate script. This page documents every script, what it does, and the data contracts it expects.

Hooks.json — the complete configuration

The actual file shipped with the plugin:

{
  "description": "Claude-mem memory system hooks",
  "hooks": {
    "Setup": [{
      "matcher": "*",
      "hooks": [{
        "type": "command",
        "command": "_R=\"${CLAUDE_PLUGIN_ROOT}\"; [ -z \"$_R\" ] && _R=\"$HOME/.claude/plugins/marketplaces/thedotmack/plugin\"; \"$_R/scripts/setup.sh\"",
        "timeout": 300
      }]
    }],
    "SessionStart": [{
      "matcher": "startup|clear|compact",
      "hooks": [
        {
          "type": "command",
          "command": "_R=\"${CLAUDE_PLUGIN_ROOT}\"; [ -z \"$_R\" ] && _R=\"$HOME/.claude/plugins/marketplaces/thedotmack/plugin\"; node \"$_R/scripts/smart-install.js\"",
          "timeout": 300
        },
        {
          "type": "command",
          "command": "_R=\"${CLAUDE_PLUGIN_ROOT}\"; [ -z \"$_R\" ] && _R=\"$HOME/.claude/plugins/marketplaces/thedotmack/plugin\"; node \"$_R/scripts/bun-runner.js\" \"$_R/scripts/worker-service.cjs\" start",
          "timeout": 60
        },
        {
          "type": "command",
          "command": "_R=\"${CLAUDE_PLUGIN_ROOT}\"; [ -z \"$_R\" ] && _R=\"$HOME/.claude/plugins/marketplaces/thedotmack/plugin\"; node \"$_R/scripts/bun-runner.js\" \"$_R/scripts/worker-service.cjs\" hook claude-code context",
          "timeout": 60
        }
      ]
    }],
    "UserPromptSubmit": [{
      "hooks": [{
        "type": "command",
        "command": "_R=\"${CLAUDE_PLUGIN_ROOT}\"; [ -z \"$_R\" ] && _R=\"$HOME/.claude/plugins/marketplaces/thedotmack/plugin\"; node \"$_R/scripts/bun-runner.js\" \"$_R/scripts/worker-service.cjs\" hook claude-code session-init",
        "timeout": 60
      }]
    }],
    "PostToolUse": [{
      "matcher": "*",
      "hooks": [{
        "type": "command",
        "command": "_R=\"${CLAUDE_PLUGIN_ROOT}\"; [ -z \"$_R\" ] && _R=\"$HOME/.claude/plugins/marketplaces/thedotmack/plugin\"; node \"$_R/scripts/bun-runner.js\" \"$_R/scripts/worker-service.cjs\" hook claude-code observation",
        "timeout": 120
      }]
    }],
    "Stop": [{
      "hooks": [{
        "type": "command",
        "command": "_R=\"${CLAUDE_PLUGIN_ROOT}\"; [ -z \"$_R\" ] && _R=\"$HOME/.claude/plugins/marketplaces/thedotmack/plugin\"; node \"$_R/scripts/bun-runner.js\" \"$_R/scripts/worker-service.cjs\" hook claude-code summarize",
        "timeout": 120
      }]
    }],
    "SessionEnd": [{
      "hooks": [{
        "type": "command",
        "command": "node -e \"let d='';process.stdin.on('data',c=>d+=c);process.stdin.on('end',()=>{try{const{sessionId:s}=JSON.parse(d);if(!s){process.exit(0)}const r=require('http').request({hostname:'127.0.0.1',port:37777,path:'/api/sessions/complete',method:'POST',headers:{'Content-Type':'application/json'}},()=>process.exit(0));r.on('error',()=>process.exit(0));r.end(JSON.stringify({contentSessionId:s}));setTimeout(()=>process.exit(0),3000)}catch{process.exit(0)}})\"",
        "timeout": 5
      }]
    }]
  }
}

${CLAUDE_PLUGIN_ROOT} is set by Claude Code to the installed plugin’s root directory. The fallback $HOME/.claude/plugins/marketplaces/thedotmack/plugin handles environments where the variable is not set.

The 5 lifecycle stages

Stage	Script	Lifecycle event	Purpose
0 (pre-hook)	`smart-install.js`	Before SessionStart context	Cached dependency check
1	`worker-service.cjs start`	SessionStart	Start Bun worker service
2	`worker-service.cjs hook … context`	SessionStart	Inject prior session context
3	`worker-service.cjs hook … session-init`	UserPromptSubmit	Create session, save prompt
4	`worker-service.cjs hook … observation`	PostToolUse	Queue tool observation
5	`worker-service.cjs hook … summarize`	Stop	Trigger session summary
6	`cleanup-hook.js` (inline)	SessionEnd	Mark session complete

Script 1: smart-install.js

File: scripts/smart-install.js (pre-hook, not a lifecycle hook) Lifecycle event: Runs via command chaining before context injection in SessionStart Matcher: startup|clear|compact Timeout: 300 seconds

What it does

Checks whether Node.js dependencies are up to date and installs them only when necessary. Without this, every session startup would run npm install (2–5 seconds). Decision logic:

Does node_modules exist?
Does .install-version match the current package.json version?
Is better-sqlite3 present? (Legacy check — bun:sqlite requires no installation)

If all checks pass: skip install (~10ms). Otherwise: run npm install and write the new version to .install-version.

const currentVersion = getPackageVersion();
const installedVersion = readFileSync('.install-version', 'utf-8');

if (currentVersion !== installedVersion) {
  await runNpmInstall();
  writeFileSync('.install-version', currentVersion);
}

What it reads: package.json, .install-version marker file What it writes: .install-version marker file Exit codes:

0 — Check complete (installed or skipped)
1 — Installation error (shown to user on stderr)

Added in: v5.0.3

Script 2: worker-service.cjs start

File: plugin/scripts/worker-service.cjs Command argument: start Lifecycle event: SessionStart (second hook in sequence) Matcher: startup|clear|compact Timeout: 60 seconds

What it does

Ensures the Bun-managed worker process is running. Uses a three-layer health check:

Does ~/.claude-mem/.worker.pid exist?
Is the process with that PID alive? (kill(pid, 0))
Does GET http://127.0.0.1:37777/health return OK?

If all three pass, the worker is already running and the hook returns immediately. Otherwise, it spawns a new Bun process. What it reads: ~/.claude-mem/.worker.pid, ~/.claude-mem/.worker.port What it writes: ~/.claude-mem/.worker.pid, ~/.claude-mem/.worker.port Exit codes:

0 — Worker confirmed running
0 — Worker started successfully (or startup errors are swallowed to prevent session breakage)

Script 3: context-hook.js (worker-service hook … context)

File: plugin/scripts/context-hook.js / worker-service.cjs hook claude-code context Lifecycle event: SessionStart (third hook in sequence) Source: src/hooks/context-hook.ts Matcher: startup|clear|compact Timeout: 60 seconds

What it does

Fetches context from previous sessions and injects it silently into Claude’s initial system prompt. Processing steps:

Wait for worker to be healthy (health check with retry, max 10s)
Extract project name from cwd: path.basename(cwd)
Call GET http://127.0.0.1:37777/api/context/inject?project={project}
Return the formatted markdown as hookSpecificOutput.additionalContext

Stdin

{
  "session_id": "claude-session-abc123",
  "cwd": "/path/to/project",
  "hook_event_name": "SessionStart",
  "source": "startup"
}

Stdout

{
  "hookSpecificOutput": {
    "hookEventName": "SessionStart",
    "additionalContext": "# [claude-mem] recent context\n\n**Legend:** 🎯 session-request ...\n\n### Oct 26, 2025\n\n**General**\n| ID | Time | T | Title | Tokens |\n..."
  }
}

Context format (progressive disclosure index):

# [claude-mem] recent context

**Legend:** 🎯 session-request | 🔴 gotcha | 🟡 problem-solution ...

### Oct 26, 2025

**General**
| ID | Time | T | Title | Tokens |
|----|------|---|-------|--------|
| #2586 | 12:58 AM | 🔵 | Context hook file empty | ~51 |

*Use MCP search tools to access full details*

What it reads: Worker HTTP API (/api/context/inject) → SQLite session_summaries and observations tables What it writes: Nothing (read-only) Configuration: CLAUDE_MEM_CONTEXT_OBSERVATIONS env var controls the number of observations shown (default: 50) Exit codes:

0 — Context injected (or gracefully empty if worker unavailable)

As of Claude Code 2.1.0, context is injected silently via additionalContext. It is not shown to the user as a message.

Script 4: new-hook.js (worker-service hook … session-init)

File: plugin/scripts/new-hook.js / worker-service.cjs hook claude-code session-init Lifecycle event: UserPromptSubmit Source: src/hooks/new-hook.ts Matcher: None (runs for every prompt) Timeout: 60 seconds

What it does

Creates or retrieves the session record for this conversation and saves the user’s prompt for full-text search. Processing steps:

Extract project name from cwd
Strip privacy tags (<private>...</private>, <claude-mem-context>...</claude-mem-context>) from the prompt
If prompt is entirely private after stripping, skip saving
INSERT OR IGNORE INTO sdk_sessions — idempotent; returns existing row if session already exists (continuation prompts)
Increment prompt_counter on the session row
INSERT INTO user_prompts with the cleaned prompt text and prompt number
POST http://127.0.0.1:37777/sessions/{sessionDbId}/init (fire-and-forget, 2s timeout)

Idempotency: Using the same session_id always maps to the same database row. This handles continuation prompts correctly.

Stdin

{
  "session_id": "claude-session-abc123",
  "cwd": "/path/to/project",
  "prompt": "Add login feature to the API"
}

Stdout

{ "continue": true, "suppressOutput": true }

What it reads: SQLite sdk_sessions table What it writes: SQLite sdk_sessions, user_prompts tables; HTTP POST to worker Exit codes:

0 — Session initialized (or skipped for private prompts)

Never generate your own session IDs. Always use the session_id provided by Claude Code via stdin — this is the source of truth for linking all observations and summaries together.

Script 5: save-hook.js (worker-service hook … observation)

File: plugin/scripts/save-hook.js / worker-service.cjs hook claude-code observation Lifecycle event: PostToolUse Source: src/hooks/save-hook.ts Matcher: * (all tools) Timeout: 120 seconds

What it does

Captures tool execution data and sends it to the worker for asynchronous AI compression. The hook itself returns in ~8ms; the AI compression runs in the background over 1–30 seconds. Processing steps:

Check the skip list — discard low-value tools immediately:

const SKIP_TOOLS = new Set([
  'ListMcpResourcesTool', // MCP infrastructure noise
  'SlashCommand',          // Command invocation
  'Skill',                 // Skill invocation
  'TodoWrite',             // Task management meta-tool
  'AskUserQuestion'        // User interaction
]);

Ensure worker is running (health check)
Strip privacy tags from tool_input and tool_response

HTTP POST to worker (fire-and-forget, 2s timeout):

POST http://127.0.0.1:37777/api/sessions/observations
Body: { claudeSessionId, tool_name, tool_input, tool_response, cwd }

Stdin

{
  "session_id": "claude-session-abc123",
  "cwd": "/path/to/project",
  "tool_name": "Read",
  "tool_input": { "file_path": "/src/index.ts" },
  "tool_response": "file contents..."
}

Stdout

{ "continue": true, "suppressOutput": true }

What it reads: Stdin from Claude Code What it writes: HTTP POST to worker (worker writes to SQLite and Chroma) Async worker processing:

createSDKSession(claudeSessionId, '', '') → returns sessionDbId
Checks privacy (skips observation if user prompt was entirely private)
Strips memory tags from tool_input and tool_response (defense-in-depth)
Queues observation for SDK agent
SDK agent calls Claude to compress into structured XML
Stores compressed observation in database, syncs to Chroma vector DB

Exit codes:

0 — Observation queued (or skipped for low-value/private tools)

Script 6: summary-hook.js (worker-service hook … summarize)

File: plugin/scripts/summary-hook.js / worker-service.cjs hook claude-code summarize Lifecycle event: Stop Source: src/hooks/summary-hook.ts Matcher: None (runs on every stop) Timeout: 120 seconds

What it does

Triggers asynchronous session summary generation when the user stops asking questions. The hook returns immediately; the actual summarization runs in the worker. Processing steps:

Read the transcript JSONL file to extract:
- Last user message (type: "user")
- Last assistant message (type: "assistant", filtering out <system-reminder> tags)
Ensure worker is running

POST to worker (fire-and-forget, 2s timeout):

POST http://127.0.0.1:37777/api/sessions/summarize
Body: { claudeSessionId, last_user_message, last_assistant_message }

Signal the worker to stop the processing spinner:

POST http://127.0.0.1:37777/api/processing
Body: { isProcessing: false }

Stdin

{
  "session_id": "claude-session-abc123",
  "cwd": "/path/to/project",
  "transcript_path": "/path/to/transcript.jsonl"
}

Stdout

{ "continue": true, "suppressOutput": true }

What it reads: Transcript JSONL file from disk What it writes: HTTP POST to worker (worker writes to SQLite session_summaries table) Async worker processing:

Looks up sessionDbId from claudeSessionId
Queues summarization for SDK agent
SDK agent calls Claude with structured prompt
Parses XML response with fields: request, investigated, learned, completed, next_steps
Stores in session_summaries table, syncs to Chroma

Exit codes:

0 — Summary queued

Script 7: cleanup-hook.js (inline SessionEnd)

File: Inline node -e "..." in hooks.json Lifecycle event: SessionEnd Source: src/hooks/cleanup-hook.ts Matcher: None (runs on all session ends) Timeout: 5 seconds

What it does

Marks the session as completed so the worker can update its state and broadcast to SSE clients (viewer UI). The hook is intentionally minimal — it is inlined directly in hooks.json to avoid a process startup penalty for a short-lived operation. Processing steps:

Parse sessionId from stdin JSON

POST to worker (fire-and-forget, 3s timeout):

POST http://127.0.0.1:37777/api/sessions/complete
Body: { contentSessionId: sessionId }

Exit 0 regardless of outcome (HTTP errors are swallowed)

Stdin

{
  "session_id": "claude-session-abc123",
  "cwd": "/path/to/project",
  "transcript_path": "/path/to/transcript.jsonl",
  "reason": "exit"
}

Stdout

None (HTTP fire-and-forget). What it reads: Stdin from Claude Code What it writes: HTTP POST to worker (worker updates SQLite, broadcasts SSE event) Async worker processing:

Looks up sessionDbId
UPDATE sdk_sessions SET status = 'completed', completed_at = NOW()
Broadcasts session completion event to SSE clients (updates viewer UI)

Exit codes:

0 — Always (failure to mark complete is non-fatal)

Session state machine

All seven scripts operate on the same session state:

[*] → Initialized (SessionStart generates session_id)
    → Active (UserPromptSubmit fires, first prompt)
    → Active (UserPromptSubmit fires, continuation — promptNumber++)
    → ObservationQueued (PostToolUse fires — async, non-blocking)
    → Summarizing (Stop fires — summary generated async)
    → Active (user resumes, new prompt)
    → Completed (SessionEnd fires)
    → [*]

Key invariants:

session_id never changes within a conversation
sessionDbId is the integer primary key — all operations use it
promptNumber increments with each UserPromptSubmit
State transitions are non-blocking — hooks fire and return

Database schema

The session-centric schema that all hook scripts write to:

-- One row per Claude Code session (conversation)
CREATE TABLE sdk_sessions (
  id                INTEGER PRIMARY KEY AUTOINCREMENT,
  claude_session_id TEXT    UNIQUE NOT NULL,  -- From Claude Code hook input
  project           TEXT    NOT NULL,          -- path.basename(cwd)
  first_user_prompt TEXT,                      -- Nullable (v4.2.8+)
  prompt_counter    INTEGER DEFAULT 0,
  status            TEXT    DEFAULT 'initialized',
  created_at        DATETIME,
  completed_at      DATETIME
);

-- One row per user prompt within a session
CREATE TABLE user_prompts (
  id            INTEGER PRIMARY KEY,
  session_id    INTEGER REFERENCES sdk_sessions(id),
  prompt_number INTEGER,
  prompt        TEXT,
  created_at    DATETIME
);

-- One row per tool observation (after AI compression)
CREATE TABLE observations (
  id          INTEGER PRIMARY KEY AUTOINCREMENT,
  session_id  INTEGER REFERENCES sdk_sessions(id),
  tool_name   TEXT,
  compressed_observation TEXT,
  created_at  DATETIME
);

-- One row per session summary (can have many per session)
CREATE TABLE session_summaries (
  id          INTEGER PRIMARY KEY,
  session_id  INTEGER REFERENCES sdk_sessions(id),
  request     TEXT,
  investigated TEXT,
  learned     TEXT,
  completed   TEXT,
  next_steps  TEXT,
  created_at  DATETIME
);

-- FTS5 virtual table for full-text search
CREATE VIRTUAL TABLE observations_fts USING fts5(
  title, subtitle, narrative, facts, concepts,
  content=observations
);

Privacy and tag stripping

Both new-hook.js and save-hook.js strip special tags before data is saved:

// User-level privacy (manual)
<private>sensitive content</private>  // removed before storing

// System-level recursion prevention (auto-injected by context hook)
<claude-mem-context>...</claude-mem-context>  // removed before storing

Stripping happens at the hook layer (edge processing) before data is sent to the worker. The worker strips tags again as defense-in-depth. Functions: stripMemoryTagsFromPrompt() and stripMemoryTagsFromJson() — source: src/utils/tag-stripping.ts.

Common pitfalls

Problem	Root cause	Solution
Session ID mismatch	Different `session_id` used across hooks	Always use ID from hook stdin — never generate your own
Duplicate sessions	Creating new session instead of reusing	Use `INSERT OR IGNORE` with `claude_session_id` as unique key
Blocking IDE	Hook waits for full AI response	Use fire-and-forget with 2s HTTP timeout
Memory tags in DB	Tag stripping skipped	Strip at hook layer before HTTP send
Worker not found	Health check returns too fast	Retry loop with exponential backoff (max 10s)
Context not injecting	npm install logs in stdout	Fixed in v4.3.1 — use `--loglevel=silent` flag

System Design

Hooks & Lifecycle

Evolution

Hook scripts reference

Hook scripts reference

Hooks.json — the complete configuration

The 5 lifecycle stages

Script 1: smart-install.js

What it does

Script 2: worker-service.cjs start

What it does

Script 3: context-hook.js (worker-service hook … context)

What it does

Stdin

Stdout

Script 4: new-hook.js (worker-service hook … session-init)

What it does

Stdin

Stdout

Script 5: save-hook.js (worker-service hook … observation)

What it does

Stdin

Stdout

Script 6: summary-hook.js (worker-service hook … summarize)

What it does

Stdin

Stdout

Script 7: cleanup-hook.js (inline SessionEnd)

What it does

Stdin

Stdout

Session state machine

Database schema

Privacy and tag stripping

Common pitfalls

Build docs developers (and LLMs) love

System Design

Hooks & Lifecycle

Evolution

Documentation Index

​Hook scripts reference

​Hooks.json — the complete configuration

​The 5 lifecycle stages

​Script 1: smart-install.js

​What it does

​Script 2: worker-service.cjs start

​What it does

​Script 3: context-hook.js (worker-service hook … context)

​What it does

​Stdin

​Stdout

​Script 4: new-hook.js (worker-service hook … session-init)

​What it does

​Stdin

​Stdout

​Script 5: save-hook.js (worker-service hook … observation)

​What it does

​Stdin

​Stdout

​Script 6: summary-hook.js (worker-service hook … summarize)

​What it does

​Stdin

​Stdout

​Script 7: cleanup-hook.js (inline SessionEnd)

​What it does

​Stdin

​Stdout

​Session state machine

​Database schema

​Privacy and tag stripping

​Common pitfalls

Build docs developers (and LLMs) love

Hook scripts reference

Hooks.json — the complete configuration

The 5 lifecycle stages

Script 1: smart-install.js

What it does

Script 2: worker-service.cjs start

What it does

Script 3: context-hook.js (worker-service hook … context)

What it does

Stdin

Stdout

Script 4: new-hook.js (worker-service hook … session-init)

What it does

Stdin

Stdout

Script 5: save-hook.js (worker-service hook … observation)

What it does

Stdin

Stdout

Script 6: summary-hook.js (worker-service hook … summarize)

What it does

Stdin

Stdout

Script 7: cleanup-hook.js (inline SessionEnd)

What it does

Stdin

Stdout

Session state machine

Database schema

Privacy and tag stripping

Common pitfalls