monomind 1.18.15 → 1.19.0

package/.claude/agents/core/researcher.md

@@ -35,26 +35,29 @@ You are a research specialist focused on thorough investigation, pattern analysi
 
 ## Research Methodology
 
-### 1. Information Gathering
-- Use multiple search strategies (glob, grep, semantic search)
+### 1. Information Gathering (monograph-first)
+- **Always start with monograph** — call `monograph_query` or `monograph_suggest` before grep/find
+- Only fall back to grep/find if monograph returns 0 results or the DB is not built
 - Read relevant files completely for context
 - Check multiple locations for related information
-- Consider different naming conventions and patterns
 
 ### 2. Pattern Analysis
-```bash
-# Example search patterns
-- Implementation patterns: grep -r "class.*Controller" --include="*.ts"
-- Configuration patterns: glob "**/*.config.*"
-- Test patterns: grep -r "describe\|test\|it" --include="*.test.*"
-- Import patterns: grep -r "^import.*from" --include="*.ts"
+```
+# Preferred: monograph for symbol/definition lookups
+monograph_query({ query: "Controller" })           # find controller classes
+monograph_query({ query: "config" })                # find configuration patterns
+monograph_suggest({ task: "test patterns" })         # find test-related files
+
+# Fallback only (if monograph returns 0 results):
+grep -r "class.*Controller" --include="*.ts"
+grep -r "^import.*from" --include="*.ts"
 ```
 
 ### 3. Dependency Analysis
-- Track import statements and module dependencies
-- Identify external package dependencies
-- Map internal module relationships
-- Document API contracts and interfaces
+- **Use `monograph_neighbors` and `monograph_impact`** for dependency mapping
+- Call `monograph_god_nodes` for high-centrality files
+- Call `monograph_community` for module cluster boundaries
+- Fall back to grep on import statements only if monograph is unavailable
 
 ### 4. Documentation Mining
 - Extract inline comments and JSDoc
@@ -98,21 +101,23 @@ research_findings:
 
 ## Search Strategies
 
-### 1. Broad to Narrow
-```bash
-# Start broad
-glob "**/*.ts"
-# Narrow by pattern
+### 1. Monograph-First (preferred)
+```
+# Start with monograph for any symbol or code lookup
+monograph_query({ query: "symbol-name" })           # BM25 keyword search
+monograph_suggest({ task: "description of task" })   # ranked file suggestions
+monograph_neighbors({ name: "ClassName" })           # direct connections
+monograph_impact({ name: "functionName" })           # blast radius
+
+# Only if monograph returns 0 results or DB not built:
 grep -r "specific-pattern" --include="*.ts"
-# Focus on specific files
-read specific-file.ts
 ```
 
 ### 2. Cross-Reference
-- Search for class/function definitions
-- Find all usages and references
-- Track data flow through the system
-- Identify integration points
+- Use `monograph_neighbors` for usages and references
+- Use `monograph_shortest_path` to trace connections between modules
+- Use `monograph_context` for 360° view of a file
+- Fall back to grep only if monograph is unavailable
 
 ### 3. Historical Analysis
 - Review git history for context

package/.claude/agents/github/code-review-swarm.md

@@ -2,7 +2,7 @@
 name: code-review-swarm
 description: |
   Deploy specialized AI agents to perform comprehensive, intelligent code reviews that go beyond traditional static analysis
-tools: mcp__monomind__swarm_init, mcp__monomind__agent_spawn, mcp__monomind__task_orchestrate, Bash, Read, Write, TodoWrite
+tools: mcp__monomind__swarm_init, mcp__monomind__agent_spawn, Bash, Read, Write, TodoWrite
 ---
 
 # Code Review Swarm - Automated Code Review with AI Agents

package/.claude/agents/github/github-modes.md

@@ -2,7 +2,7 @@
 name: github-modes
 description: |
   Comprehensive GitHub integration modes for workflow orchestration, PR management, and repository coordination with batch optimization
-tools: mcp__monomind__swarm_init, mcp__monomind__agent_spawn, mcp__monomind__task_orchestrate, Bash, TodoWrite, Read, Write
+tools: mcp__monomind__swarm_init, mcp__monomind__agent_spawn, Bash, TodoWrite, Read, Write
 ---
 
 # GitHub Integration Modes

package/.claude/agents/github/issue-tracker.md

@@ -2,7 +2,7 @@
 name: issue-tracker
 description: |
   Intelligent issue management and project coordination with automated tracking, progress monitoring, and team coordination
-tools: mcp__monomind__swarm_init, mcp__monomind__agent_spawn, mcp__monomind__task_orchestrate, mcp__monomind__memory_store, Bash, TodoWrite, Read, Write
+tools: mcp__monomind__swarm_init, mcp__monomind__agent_spawn, mcp__monomind__memory_store, Bash, TodoWrite, Read, Write
 ---
 
 # GitHub Issue Tracker

package/.claude/agents/github/multi-repo-swarm.md

@@ -1,7 +1,7 @@
 ---
 name: multi-repo-swarm
 description: Cross-repository swarm orchestration for organization-wide automation and intelligent collaboration
-tools: Bash, Read, Write, Edit, Glob, Grep, LS, TodoWrite, mcp__monomind__swarm_init, mcp__monomind__agent_spawn, mcp__monomind__task_orchestrate, mcp__monomind__swarm_status, mcp__monomind__memory_usage, mcp__monomind__github_repo_analyze, mcp__monomind__github_pr_manage, mcp__monomind__github_sync_coord, mcp__monomind__github_metrics
+tools: Bash, Read, Write, Edit, Glob, Grep, LS, TodoWrite, mcp__monomind__swarm_init, mcp__monomind__agent_spawn, mcp__monomind__swarm_status, mcp__monomind__memory_usage, mcp__monomind__github_repo_analyze, mcp__monomind__github_pr_manage, mcp__monomind__github_sync_coord, mcp__monomind__github_metrics
 ---
 
 # Multi-Repo Swarm - Cross-Repository Swarm Orchestration

package/.claude/agents/github/pr-manager.md

@@ -2,7 +2,7 @@
 name: pr-manager
 description: |
   Comprehensive pull request management with swarm coordination for automated reviews, testing, and merge workflows
-tools: Bash, Read, Write, Edit, Glob, Grep, LS, TodoWrite, mcp__monomind__swarm_init, mcp__monomind__agent_spawn, mcp__monomind__task_orchestrate, mcp__monomind__swarm_status, mcp__monomind__memory_store, mcp__monomind__github_pr_manage, mcp__monomind__github_code_review, mcp__monomind__github_metrics
+tools: Bash, Read, Write, Edit, Glob, Grep, LS, TodoWrite, mcp__monomind__swarm_init, mcp__monomind__agent_spawn, mcp__monomind__swarm_status, mcp__monomind__memory_store, mcp__monomind__github_pr_manage, mcp__monomind__github_code_review, mcp__monomind__github_metrics
 ---
 
 # GitHub PR Manager

package/.claude/agents/github/project-board-sync.md

@@ -2,7 +2,7 @@
 name: project-board-sync
 description: |
   Synchronize AI swarms with GitHub Projects for visual task management, progress tracking, and team coordination
-tools: Bash, Read, Write, Edit, Glob, Grep, LS, TodoWrite, mcp__monomind__swarm_init, mcp__monomind__agent_spawn, mcp__monomind__task_orchestrate, mcp__monomind__swarm_status, mcp__monomind__memory_usage, mcp__monomind__github_repo_analyze, mcp__monomind__github_pr_manage, mcp__monomind__github_issue_track, mcp__monomind__github_metrics, mcp__monomind__workflow_create, mcp__monomind__workflow_execute
+tools: Bash, Read, Write, Edit, Glob, Grep, LS, TodoWrite, mcp__monomind__swarm_init, mcp__monomind__agent_spawn, mcp__monomind__swarm_status, mcp__monomind__memory_usage, mcp__monomind__github_repo_analyze, mcp__monomind__github_pr_manage, mcp__monomind__github_issue_track, mcp__monomind__github_metrics, mcp__monomind__workflow_create, mcp__monomind__workflow_execute
 ---
 
 # Project Board Sync - GitHub Projects Integration

package/.claude/agents/github/release-manager.md

@@ -2,7 +2,7 @@
 name: release-manager
 description: |
   Automated release coordination and deployment with Monomind swarm orchestration for seamless version management, testing, and deployment across multiple packages
-tools: Bash, Read, Write, Edit, TodoWrite, TodoRead, Task, WebFetch, mcp__github__create_pull_request, mcp__github__merge_pull_request, mcp__github__create_branch, mcp__github__push_files, mcp__github__create_issue, mcp__monomind__swarm_init, mcp__monomind__agent_spawn, mcp__monomind__task_orchestrate, mcp__monomind__memory_store
+tools: Bash, Read, Write, Edit, TodoWrite, TodoRead, Task, WebFetch, mcp__github__create_pull_request, mcp__github__merge_pull_request, mcp__github__create_branch, mcp__github__push_files, mcp__github__create_issue, mcp__monomind__swarm_init, mcp__monomind__agent_spawn, mcp__monomind__memory_store
 ---
 
 # GitHub Release Manager

package/.claude/agents/github/repo-architect.md

@@ -2,7 +2,7 @@
 name: repo-architect
 description: |
   Repository structure optimization and multi-repo management with Monomind swarm coordination for scalable project architecture and development workflows
-tools: Bash, Read, Write, Edit, LS, Glob, TodoWrite, TodoRead, Task, WebFetch, mcp__github__create_repository, mcp__github__fork_repository, mcp__github__search_repositories, mcp__github__push_files, mcp__github__create_or_update_file, mcp__monomind__swarm_init, mcp__monomind__agent_spawn, mcp__monomind__task_orchestrate, mcp__monomind__memory_store
+tools: Bash, Read, Write, Edit, LS, Glob, TodoWrite, TodoRead, Task, WebFetch, mcp__github__create_repository, mcp__github__fork_repository, mcp__github__search_repositories, mcp__github__push_files, mcp__github__create_or_update_file, mcp__monomind__swarm_init, mcp__monomind__agent_spawn, mcp__monomind__memory_store
 ---
 
 # GitHub Repository Architect

package/.claude/agents/github/swarm-issue.md

@@ -2,7 +2,7 @@
 name: swarm-issue
 description: |
   GitHub issue-based swarm coordination agent that transforms issues into intelligent multi-agent tasks with automatic decomposition and progress tracking
-tools: mcp__github__get_issue, mcp__github__create_issue, mcp__github__update_issue, mcp__github__list_issues, mcp__github__create_issue_comment, mcp__monomind__swarm_init, mcp__monomind__agent_spawn, mcp__monomind__task_orchestrate, mcp__monomind__memory_usage, TodoWrite, TodoRead, Bash, Grep, Read, Write
+tools: mcp__github__get_issue, mcp__github__create_issue, mcp__github__update_issue, mcp__github__list_issues, mcp__github__create_issue_comment, mcp__monomind__swarm_init, mcp__monomind__agent_spawn, mcp__monomind__memory_usage, TodoWrite, TodoRead, Bash, Grep, Read, Write
 ---
 
 # Swarm Issue - Issue-Based Swarm Coordination

package/.claude/agents/github/swarm-pr.md

@@ -2,7 +2,7 @@
 name: swarm-pr
 description: |
   Pull request swarm management agent that coordinates multi-agent code review, validation, and integration workflows with automated PR lifecycle management
-tools: mcp__github__get_pull_request, mcp__github__create_pull_request, mcp__github__update_pull_request, mcp__github__list_pull_requests, mcp__github__create_pr_comment, mcp__github__get_pr_diff, mcp__github__merge_pull_request, mcp__monomind__swarm_init, mcp__monomind__agent_spawn, mcp__monomind__task_orchestrate, mcp__monomind__memory_usage, mcp__monomind__coordination_sync, TodoWrite, TodoRead, Bash, Grep, Read, Write, Edit
+tools: mcp__github__get_pull_request, mcp__github__create_pull_request, mcp__github__update_pull_request, mcp__github__list_pull_requests, mcp__github__create_pr_comment, mcp__github__get_pr_diff, mcp__github__merge_pull_request, mcp__monomind__swarm_init, mcp__monomind__agent_spawn, mcp__monomind__memory_usage, mcp__monomind__coordination_sync, TodoWrite, TodoRead, Bash, Grep, Read, Write, Edit
 ---
 
 # Swarm PR - Managing Swarms through Pull Requests

package/.claude/agents/github/sync-coordinator.md

@@ -2,7 +2,7 @@
 name: sync-coordinator
 description: |
   Multi-repository synchronization coordinator that manages version alignment, dependency synchronization, and cross-package integration with intelligent swarm orchestration
-tools: mcp__github__push_files, mcp__github__create_or_update_file, mcp__github__get_file_contents, mcp__github__create_pull_request, mcp__github__search_repositories, mcp__github__list_repositories, mcp__monomind__swarm_init, mcp__monomind__agent_spawn, mcp__monomind__task_orchestrate, mcp__monomind__memory_store, mcp__monomind__coordination_sync, mcp__monomind__load_balance, TodoWrite, TodoRead, Bash, Read, Write, Edit, MultiEdit
+tools: mcp__github__push_files, mcp__github__create_or_update_file, mcp__github__get_file_contents, mcp__github__create_pull_request, mcp__github__search_repositories, mcp__github__list_repositories, mcp__monomind__swarm_init, mcp__monomind__agent_spawn, mcp__monomind__memory_store, mcp__monomind__coordination_sync, mcp__monomind__load_balance, TodoWrite, TodoRead, Bash, Read, Write, Edit, MultiEdit
 ---
 
 # GitHub Sync Coordinator

package/.claude/agents/github/workflow-automation.md

@@ -2,7 +2,7 @@
 name: workflow-automation
 description: |
   GitHub Actions workflow automation agent that creates intelligent, self-organizing CI/CD pipelines with adaptive multi-agent coordination and automated optimization
-tools: mcp__github__create_workflow, mcp__github__update_workflow, mcp__github__list_workflows, mcp__github__get_workflow_runs, mcp__github__create_workflow_dispatch, mcp__monomind__swarm_init, mcp__monomind__agent_spawn, mcp__monomind__task_orchestrate, mcp__monomind__memory_usage, mcp__monomind__performance_report, mcp__monomind__bottleneck_analyze, mcp__monomind__workflow_create, mcp__monomind__automation_setup, TodoWrite, TodoRead, Bash, Read, Write, Edit, Grep
+tools: mcp__github__create_workflow, mcp__github__update_workflow, mcp__github__list_workflows, mcp__github__get_workflow_runs, mcp__github__create_workflow_dispatch, mcp__monomind__swarm_init, mcp__monomind__agent_spawn, mcp__monomind__memory_usage, mcp__monomind__performance_report, mcp__monomind__bottleneck_analyze, mcp__monomind__workflow_create, mcp__monomind__automation_setup, TodoWrite, TodoRead, Bash, Read, Write, Edit, Grep
 ---
 
 # Workflow Automation - GitHub Actions Integration

package/.claude/agents/goal/goal-planner.md

@@ -87,7 +87,7 @@ Advanced action definitions with tool groups:
 Action: analyze_codebase
   Preconditions: {repository_accessible: true}
   Effects: {code_analyzed: true, metrics_available: true}
-  Tools: [grep, ast_parser, complexity_analyzer]
+  Tools: [monograph_query, monograph_suggest, grep (fallback), ast_parser, complexity_analyzer]
   Execution: hybrid (LLM for insights, code for metrics)
   Cost: 2
   Fallback: manual_review if tools unavailable

package/.claude/agents/specialized/specialized-workflow-architect.md

@@ -440,27 +440,24 @@ Use this when joining a new project or auditing an existing system:
 
 ### Step 0: Discovery Pass (always first)
 
-Before designing anything, discover what already exists:
+Before designing anything, discover what already exists. **Use monograph first** — fall back to grep only if monograph returns 0 results or the DB is not built.
+
+```
+# PREFERRED: monograph-based discovery
+monograph_query({ query: "route handler" })          # find all route entry points
+monograph_query({ query: "worker job consumer" })    # find background processors
+monograph_query({ query: "state transition status" })# find state machines
+monograph_route_map({})                              # list all HTTP routes with handlers
+monograph_suggest({ task: "workflow entry points, workers, state machines, cron jobs" })
+```
 
 ```bash
-# Find all workflow entry points (adapt patterns to your framework)
+# FALLBACK (only if monograph returns 0 results):
 grep -rn "router\.\(post\|put\|delete\|get\|patch\)" src/routes/ --include="*.ts" --include="*.js"
 grep -rn "@app\.\(route\|get\|post\|put\|delete\)" src/ --include="*.py"
-grep -rn "HandleFunc\|Handle(" cmd/ pkg/ --include="*.go"
-
-# Find all background workers / job processors
 find src/ -type f -name "*worker*" -o -name "*job*" -o -name "*consumer*" -o -name "*processor*"
-
-# Find all state transitions in the codebase
 grep -rn "status.*=\|\.status\s*=\|state.*=\|\.state\s*=" src/ --include="*.ts" --include="*.py" --include="*.go" | grep -v "test\|spec\|mock"
-
-# Find all database migrations
 find . -path "*/migrations/*" -type f | head -30
-
-# Find all infrastructure resources
-find . -name "*.tf" -o -name "docker-compose*.yml" -o -name "*.yaml" | xargs grep -l "resource\|service:" 2>/dev/null
-
-# Find all scheduled / cron jobs
 grep -rn "cron\|schedule\|setInterval\|@Scheduled" src/ --include="*.ts" --include="*.py" --include="*.go" --include="*.java"
 ```
 

package/.claude/agents/testing/production-validator.md

@@ -245,17 +245,18 @@ describe('Performance Validation', () => {
 
 ### 1. Code Quality Validation
 
+**Preferred: monograph-based code quality scan:**
+```
+monograph_query({ query: "mock fake stub" })         # find mock implementations in prod code
+monograph_query({ query: "TODO FIXME" })             # find unfinished work in critical paths
+monograph_query({ query: "console log warn error" }) # find console statements
+```
+
+**Fallback (if monograph returns 0 results or DB not built):**
 ```bash
-# No mock implementations in production code
 grep -r "mock\|fake\|stub" src/ --exclude-dir=__tests__ --exclude="*.test.*" --exclude="*.spec.*"
-
-# No TODO/FIXME in critical paths
 grep -r "TODO\|FIXME" src/ --exclude-dir=__tests__
-
-# No hardcoded test data
 grep -r "test@\|example\|localhost" src/ --exclude-dir=__tests__
-
-# No console.log statements
 grep -r "console\." src/ --exclude-dir=__tests__
 ```
 

package/.claude/agents/testing/testing-evidence-collector.md

@@ -47,7 +47,9 @@ You are **EvidenceQA**, a skeptical QA specialist who requires visual proof for
 # 2. Check what's actually built
 ls -la resources/views/ || ls -la *.html
 
-# 3. Reality check for claimed features  
+# 3. Reality check for claimed features (monograph-first, grep fallback)
+# Preferred: monograph_query({ query: "luxury premium glass morphism" })
+# Fallback:
 grep -r "luxury\|premium\|glass\|morphism" . --include="*.html" --include="*.css" --include="*.blade.php" || echo "NO PREMIUM FEATURES FOUND"
 
 # 4. Review comprehensive test results

package/.claude/commands/mastermind/code-review.md

@@ -66,10 +66,10 @@ Based on `STACK`, determine which specialist agents to run beyond the always-on
 - `Security Engineer` — injection, auth gaps, secrets exposure, CVE-prone patterns, OWASP Top 10
 - `Reality Checker` — evidence-based assessment: does the code actually do what it claims?
 
-**Run conditionally** — detect by running these checks and adding the agent if exit 0:
-- `Accessibility Auditor` — `find . -maxdepth 5 \( -name "*.html" -o -name "*.jsx" -o -name "*.tsx" \) -not -path "*/node_modules/*" | head -1 | grep -q .`
-- `API Tester` — `find . -maxdepth 5 \( -name "*.route.*" -o -name "openapi.yml" -o -name "openapi.json" -o -name "swagger.*" \) -not -path "*/node_modules/*" | head -1 | grep -q . || grep -rqEl "express\(|fastify|hono|koa|router\." --include="*.ts" --include="*.js" . 2>/dev/null`
-- `Database Optimizer` — `find . -maxdepth 5 \( -name "*.sql" -o -name "*migration*" -o -name "*schema*" \) -not -path "*/node_modules/*" | head -1 | grep -q . || grep -rqEl "prisma|typeorm|sequelize|drizzle|knex" --include="*.ts" --include="*.js" . 2>/dev/null`
+**Run conditionally** — use `monograph_query` first to detect stack; fall back to find/grep if monograph returns 0 results:
+- `Accessibility Auditor` — `monograph_query({ query: "html jsx tsx component" })` or `find . -maxdepth 5 \( -name "*.html" -o -name "*.jsx" -o -name "*.tsx" \) -not -path "*/node_modules/*" | head -1 | grep -q .`
+- `API Tester` — `monograph_query({ query: "express fastify hono koa router route openapi swagger" })` or `find . -maxdepth 5 \( -name "*.route.*" -o -name "openapi.yml" -o -name "openapi.json" -o -name "swagger.*" \) -not -path "*/node_modules/*" | head -1 | grep -q . || grep -rqEl "express\(|fastify|hono|koa|router\." --include="*.ts" --include="*.js" . 2>/dev/null`
+- `Database Optimizer` — `monograph_query({ query: "prisma typeorm sequelize drizzle knex sql migration schema" })` or `find . -maxdepth 5 \( -name "*.sql" -o -name "*migration*" -o -name "*schema*" \) -not -path "*/node_modules/*" | head -1 | grep -q . || grep -rqEl "prisma|typeorm|sequelize|drizzle|knex" --include="*.ts" --include="*.js" . 2>/dev/null`
 - `SRE` — `find . -maxdepth 3 \( -name "Dockerfile" -o -name "docker-compose*" -o -name "*.yml" -path "*/.github/workflows/*" \) | head -1 | grep -q .`
 - `Mobile App Builder` — `find . -maxdepth 3 \( -name "*.swift" -o -name "*.kt" \) | head -1 | grep -q . || grep -q "react-native" package.json 2>/dev/null`
 

package/.claude/commands/mastermind/help.md

@@ -97,8 +97,8 @@ mcp__monomind__memory_store({ key: "...", value: "...", namespace: "..." })
 mcp__monomind__memory_search({ query: "...", namespace: "..." })
 
 // Knowledge graph
-mcp__monomind__graphify_suggest({ task: "..." })
-mcp__monomind__graphify_query({ query: "..." })
+mcp__monomind__monograph_suggest({ task: "..." })
+mcp__monomind__monograph_query({ query: "..." })
 
 // Swarm
 mcp__monomind__swarm_init({ topology: "hierarchical", maxAgents: 8, strategy: "specialized" })

package/.claude/commands/mastermind/okf-export.md

@@ -0,0 +1,14 @@
+<!-- Export the Second Brain knowledge base as a portable OKF (Open Knowledge Format) bundle. -->
+
+Parse `$ARGUMENTS` for:
+- `--output <dir>` or `-o <dir>` → output directory (default: `.monomind/knowledge-export`)
+- `--scope <name>` or `-s <name>` → knowledge scope (default: `shared`)
+- Remaining positional arg → treated as output directory
+
+Run the export:
+
+```bash
+npx monomind doc export -o "<output_dir>" -s "<scope>"
+```
+
+After completion, report what was exported and where. If 0 documents exported, suggest `monomind doc ingest <path>` first.

package/.claude/commands/mastermind/okf-import.md

@@ -0,0 +1,15 @@
+<!-- Import an OKF (Open Knowledge Format) bundle into the Second Brain knowledge base. -->
+
+Parse `$ARGUMENTS` for:
+- `--scope <name>` or `-s <name>` → knowledge scope (default: `shared`)
+- Remaining positional arg → bundle directory path (REQUIRED)
+
+If no bundle directory provided, ask: "Which directory contains the OKF bundle to import?"
+
+Run the import:
+
+```bash
+npx monomind doc ingest "<bundle_dir>" -s "<scope>"
+```
+
+After completion, report files processed, chunks indexed, and any errors. If the bundle directory doesn't exist or contains no `.md` files, say so.

package/.claude/helpers/handlers/agent-start-handler.cjs

@@ -65,44 +65,19 @@ module.exports = {
       );
     } catch (e) { /* non-fatal — never block a subagent from starting */ }
 
-    // Subagent context inheritance — inject graph god nodes + parent's last
-    // pre-resolved suggestions so the spawned agent inherits spatial map.
+    // monolean: compact single-line graph context instead of multi-line map.
+    // Subagents get task-relevant files only — god nodes are noise for a focused task.
     try {
-      var subDb = _openMonographDb();
-      if (subDb) {
-        try {
-          var godRows = subDb.prepare(
-            "SELECT n.name, n.label, n.file_path AS file, " +
-            "(SELECT COUNT(*) FROM edges WHERE source_id=n.id OR target_id=n.id) AS deg " +
-            "FROM nodes n " +
-            "WHERE n.label NOT IN ('Concept') AND n.file_path IS NOT NULL AND n.file_path != '' " +
-            "ORDER BY deg DESC LIMIT 5"
-          ).all();
-          if (godRows.length > 0) {
-            console.log('[MONOGRAPH_SUBAGENT_CTX] Graph map inherited from parent:');
-            for (var gi = 0; gi < godRows.length; gi++) {
-              var gr = godRows[gi];
-              console.log('  · ' + gr.name + ' [' + gr.label + '] — ' + (gr.file || '') + ' (deg ' + gr.deg + ')');
-            }
-            try {
-              var subAgentDesc = hookInput.description || hookInput.prompt_description || '';
-              if (subAgentDesc && subAgentDesc.length > 8) {
-                var subHints = getMonographSuggestions(subAgentDesc, 3);
-                if (subHints.length > 0) {
-                  console.log('  Top files for this subagent task:');
-                  for (var si2 = 0; si2 < subHints.length; si2++) {
-                    var sh = subHints[si2];
-                    console.log('    · ' + sh.name + ' [' + sh.label + '] — ' + (sh.file || ''));
-                  }
-                }
-              }
-            } catch (_) {}
-            console.log('  Use mcp__monomind__monograph_suggest / monograph_query in this subagent before grepping.');
-          }
-        } catch (e) { /* non-fatal */ }
+      var subAgentDesc = hookInput.description || hookInput.prompt_description || '';
+      if (subAgentDesc && subAgentDesc.length > 8) {
+        var subHints = getMonographSuggestions(subAgentDesc, 3);
+        if (subHints.length > 0) {
+          var parts = subHints.map(function(s) {
+            return s.name + ' [' + s.label + '] — ' + (s.file || '');
+          });
+          console.log('[MONOGRAPH] Top files: ' + parts.join(' · '));
+        }
       }
     } catch (e) { /* non-fatal */ }
-
-    console.log('[OK] Agent registered');
   },
 };

package/.claude/helpers/handlers/capture-handler.cjs

@@ -370,6 +370,84 @@ async function handleSubagentStop(hookInput) {
       ts: Date.now(),
     }) + '\n');
   }
+
+  // ── Wire captured interaction into EpisodicStore ────
+  try {
+    var episodicPath = path.join(CWD, '.monomind', 'episodic', 'episodes.jsonl');
+    var episodicDir = path.dirname(episodicPath);
+    if (!fs.existsSync(episodicDir)) fs.mkdirSync(episodicDir, { recursive: true });
+
+    // Append a lightweight episode entry directly (avoid importing @monomind/memory)
+    var episodeEntry = {
+      episodeId: require('crypto').randomUUID(),
+      sessionId: session || '',
+      runIds: [runId || 'unknown'],
+      summary: [
+        '[agent:' + (agentType || 'unknown') + ']',
+        summary ? summary.slice(0, 500) : '',
+        totalTin ? '[memory:write] tokens_in=' + totalTin : '',
+        totalTout ? '[memory:write] tokens_out=' + totalTout : ''
+      ].filter(Boolean).join('\n'),
+      startedAt: snap.ts || Date.now(),
+      endedAt: Date.now(),
+      agentSlugs: [agentType || 'unknown'],
+      taskTypes: [agentType || 'unknown'],
+      tokenEstimate: Math.ceil(((summary || '').length) / 4)
+    };
+    fs.appendFileSync(episodicPath, JSON.stringify(episodeEntry) + '\n', 'utf-8');
+  } catch (e) { /* non-fatal */ }
+
+  // ── Record agent interaction in Monograph SQLite ────────────────────────────
+  try {
+    var mgDbPath = path.join(CWD, '.monomind', 'monograph.db');
+    if (fs.existsSync(mgDbPath)) {
+      var monographMod = null;
+      var mgCandidates = [
+        path.join(CWD, 'node_modules/.pnpm/node_modules/@monoes/monograph'),
+        path.join(CWD, 'packages/node_modules/.pnpm/node_modules/@monoes/monograph'),
+        path.join(CWD, 'node_modules/@monoes/monograph'),
+      ];
+      for (var mi = 0; mi < mgCandidates.length; mi++) {
+        try { if (fs.existsSync(mgCandidates[mi])) { monographMod = require(mgCandidates[mi]); break; } } catch (e2) {}
+      }
+      if (!monographMod) { try { monographMod = require('@monoes/monograph'); } catch (e2) {} }
+      if (monographMod && monographMod.openDb) {
+        var mgDb = monographMod.openDb(mgDbPath);
+        try {
+          mgDb.prepare(
+            'INSERT OR IGNORE INTO agent_interactions ' +
+            '(id, session_id, org_name, agent_type, parent_agent, prompt_summary, result_summary, tokens_in, tokens_out, cost_usd, success, duration_ms, timestamp) ' +
+            'VALUES (@id, @session_id, @org_name, @agent_type, @parent_agent, @prompt_summary, @result_summary, @tokens_in, @tokens_out, @cost_usd, @success, @duration_ms, @timestamp)'
+          ).run({
+            id: require('crypto').randomUUID(),
+            session_id: session || '',
+            org_name: org || null,
+            agent_type: agentType || 'unknown',
+            parent_agent: null,
+            prompt_summary: agentDesc ? agentDesc.slice(0, 500) : null,
+            result_summary: summary ? summary.slice(0, 1000) : null,
+            tokens_in: totalTin || 0,
+            tokens_out: totalTout || 0,
+            cost_usd: costUsd || 0,
+            success: (function() {
+              // Determine success from result summary — errors/failures/exceptions indicate failure
+              if (summary) {
+                var sumLower = summary.toLowerCase();
+                if (sumLower.includes('error') || sumLower.includes('failed') || sumLower.includes('exception') || sumLower.includes('fatal')) {
+                  return 0;
+                }
+              }
+              return 1;
+            })(),
+            duration_ms: snap.ts ? (Date.now() - snap.ts) : 0,
+            timestamp: Date.now(),
+          });
+        } finally {
+          if (monographMod.closeDb) monographMod.closeDb(mgDb);
+        }
+      }
+    }
+  } catch (e) { /* non-fatal — monograph may not be available */ }
 }
 
 // ─── Phase 3: PreToolUse accumulator (Issue 9) ────────────────────────────────
@@ -424,6 +502,38 @@ async function handlePostTool(hookInput) {
 
   const isBash = toolName === 'bash' || toolName === 'shell';
   const isEdit = toolName === 'edit' || toolName === 'write' || toolName === 'multiedit';
+  const isMemoryStore = toolName.includes('memory_store') || toolName.includes('memory_pattern');
+  const isMemorySearch = toolName.includes('memory_search') || toolName.includes('memory_retrieve');
+
+  // Track real memory ops (writes stats to session file)
+  if (isMemoryStore || isMemorySearch) {
+    try {
+      var sessionId = process.env.CLAUDE_SESSION_ID || '';
+      var statsPath = path.join(CWD, '.monomind', 'memory-ops-' + sessionId.slice(0, 16) + '.json');
+      var stats = { writes: 0, searches: 0, redundantWrites: 0, emptySearches: 0 };
+      try { stats = JSON.parse(fs.readFileSync(statsPath, 'utf-8')); } catch {}
+      if (isMemoryStore) {
+        stats.writes++;
+        // Detect duplicate: response contains "already exists" or "duplicate"
+        var respStr = JSON.stringify(toolResponse).toLowerCase();
+        if (respStr.includes('duplicate') || respStr.includes('already exists') || respStr.includes('skip')) {
+          stats.redundantWrites++;
+        }
+      }
+      if (isMemorySearch) {
+        stats.searches++;
+        // Detect empty results
+        var results = toolResponse.results || toolResponse.entries || toolResponse.data;
+        if (Array.isArray(results) && results.length === 0) {
+          stats.emptySearches++;
+        } else if (toolResponse.count === 0 || toolResponse.total === 0) {
+          stats.emptySearches++;
+        }
+      }
+      fs.mkdirSync(path.dirname(statsPath), { recursive: true });
+      fs.writeFileSync(statsPath, JSON.stringify(stats), 'utf-8');
+    } catch (e) { /* non-fatal */ }
+  }
 
   if (!isBash && !isEdit) return;