monomind 1.19.0 → 2.0.1

package/README.md

@@ -66,7 +66,7 @@ flowchart TD
     R["Reviewer"]
     M["Growth Marketer"]
     BOARD[("Shared\nTask Board")]
-    MEM[("LanceDB\nMemory")]
+    MEM[("Persistent\nMemory")]
 
     U --> CO --> RO --> BOSS
     BOSS -->|spawns| W
@@ -126,7 +126,7 @@ Type "go" to save, or describe changes.
 | **Boss agent** | Coordinator type, no supervisor — owns the goal |
 | **Role agents** | Spawned on demand, specialized by task type |
 | **Task board** | Todo → Doing → Done, shared across all agents |
-| **Memory** | All output stored in org-scoped LanceDB namespace |
+| **Memory** | All output stored in an org-scoped memory namespace |
 | **Checkpoint** | State saved every 30 min — survives crashes and restarts |
 | **Governance** | `auto` (free), `board` (approve sensitive), `strict` (approve all external actions) |
 
@@ -202,10 +202,7 @@ monomind init
 # 3. Wire into Claude Code as an MCP server
 claude mcp add monomind npx monomind mcp start
 
-# 4. Start the background daemon
-monomind daemon start
-
-# 5. Health check
+# 4. Health check
 monomind doctor --fix
 ```
 
@@ -221,13 +218,13 @@ Open Claude Code. You now have 80+ slash commands available:
 
 ## 🧠 Memory That Persists
 
-Every session, every agent, every org writes to **LanceDB** — a hybrid SQLite + HNSW vector store that survives across sessions. The next time you run anything, Monomind already knows what was built, what failed, and which patterns work.
+Every session, every agent, every org writes to a persistent memory store — a JSON pattern store with episodic recall that survives across sessions. The next time you run anything, Monomind already knows what was built, what failed, and which patterns work.
 
 ```mermaid
 graph TD
     L0["L0 - In-flight\nCurrent session drawers\nephemeral"]
     L1["L1 - Working\nCross-session memory\nBM25 K1=1.5, B=0.75"]
-    L2["L2 - Long-term\nLanceDB + HNSW index\nSemantic search"]
+    L2["L2 - Long-term\nEpisodic store\nSemantic recall"]
     L3["L3 - Shared\nCross-agent namespace\nFederated swarm reads"]
 
     L0 -->|promoted| L1 --> L2 --> L3
@@ -259,7 +256,7 @@ Before touching any file, Monomind queries **Monograph** — a SQLite-backed kno
 # → "find all callers of validateToken()"
 ```
 
-23 MCP tools. Impact analysis. Shortest-path queries. Community detection. Zero grep.
+19 default MCP tools (+27 advanced via `MONOGRAPH_MCP_ADVANCED=1`). Impact analysis. Community detection. Zero grep.
 
 ---
 
@@ -275,11 +272,11 @@ flowchart LR
     H --> I["route\nlearn\nbuild-agents"]
     H --> T["teammate-idle\ntask-completed"]
 
-    I --> DB[("LanceDB\npatterns.json")]
+    I --> DB[("patterns.json\nmemory store")]
     DB -->|next session| CE
 ```
 
-**12 background workers** run continuously: `security` · `health` · `swarm` · `learning` · `patterns` · `git` · `performance` and more.
+**15 background workers** run at session start (staleness-gated, refreshed when older than 6 hours): `security` · `health` · `swarm` · `learning` · `patterns` · `git` · `performance` and more.
 
 ---
 
@@ -341,7 +338,7 @@ Everything runs from inside Claude Code via slash commands. Here's the highlight
 | Package | npm | Purpose |
 |---|---|---|
 | `monomind` | [![npm](https://img.shields.io/npm/v/monomind?style=flat-square&color=00D2AA)](https://www.npmjs.com/package/monomind) | Umbrella — **install this one** |
-| `@monoes/monomindcli` | [![npm](https://img.shields.io/npm/v/@monoes/monomindcli?style=flat-square&color=4F46E5)](https://www.npmjs.com/package/@monoes/monomindcli) | CLI engine (41 commands) |
+| `@monoes/monomindcli` | [![npm](https://img.shields.io/npm/v/@monoes/monomindcli?style=flat-square&color=4F46E5)](https://www.npmjs.com/package/@monoes/monomindcli) | CLI engine (31 commands) |
 | `monofence-ai` | [![npm](https://img.shields.io/npm/v/monofence-ai?style=flat-square&color=EF4444)](https://www.npmjs.com/package/monofence-ai) | AI manipulation defence |
 | `@monoes/monograph` | [![npm](https://img.shields.io/npm/v/@monoes/monograph?style=flat-square&color=F59E0B)](https://www.npmjs.com/package/@monoes/monograph) | Code knowledge graph |
 
@@ -353,15 +350,15 @@ Everything runs from inside Claude Code via slash commands. Here's the highlight
 graph TD
     CC["Claude Code"]
     MCP["MCP Server\nmonomind mcp start"]
-    D["Background Daemon\n12 workers"]
+    D["Background Workers\n(@monomind/hooks, in-process)"]
 
-    CC <-->|"23 tools: monograph, memory, swarm"| MCP
+    CC <-->|"MCP tools: monograph, memory, swarm"| MCP
     MCP <--> D
 
-    D --> ADB[("LanceDB\nSQLite + HNSW")]
+    D --> ADB[("Memory store\npatterns + episodes")]
     D --> MG[("Monograph\ncode graph")]
     D --> HK["Hooks\n22 event types"]
-    D --> SW["Swarm\n6 topologies\n5 consensus algos"]
+    D --> SW["Swarm\n4 topologies\n3 consensus strategies"]
 
     CC -->|"Task tool - spawns agents"| AG["Agent Swarm\narchitect, coder\ntester, reviewer\nsecurity, perf"]
     AG <-->|reads and writes| ADB
@@ -383,7 +380,6 @@ graph TD
 - 📋 [All Slash Commands](https://monoes.github.io/monomind/#slash)
 - 🐛 [Issues](https://github.com/monoes/monomind/issues)
 - 💬 [Discussions](https://github.com/monoes/monomind/discussions)
-- 📦 [Changelog v1.11](https://github.com/monoes/monomind/blob/main/CHANGELOG-v1.11.md)
 
 ---
 

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "monomind",
-  "version": "1.19.0",
-  "description": "Monomind - Enterprise AI agent orchestration for Claude Code. Deploy 60+ specialized agents in coordinated swarms with self-learning, fault-tolerant consensus, vector memory, and MCP integration",
+  "version": "2.0.1",
+  "description": "Monomind - Power toolkit for Claude Code. Autonomous agent orgs, codebase knowledge graph, keyword-routed specialist prompts, and 80+ slash commands. One init, then walk away.",
   "main": "dist/index.js",
   "type": "module",
   "bin": {
@@ -28,23 +28,19 @@
     "!packages/@monomind/cli/dist/**/*.test.js",
     "!packages/@monomind/cli/dist/**/__tests__/**",
     "!packages/@monomind/cli/dist/**/*.map",
-    "packages/@monomind/cli/bundled-graph/**",
+    "!packages/@monomind/cli/dist/**/.monomind/**",
     "packages/@monomind/cli/scripts/**/*.mjs",
     "packages/@monomind/cli/scripts/**/*.js",
     "packages/@monomind/cli/scripts/**/*.sh",
     "packages/@monomind/cli/package.json",
     "scripts/*.mjs",
     "scripts/*.sh",
-    "packages/@monomind/guidance/dist/**/*.js",
-    "packages/@monomind/guidance/dist/**/*.d.ts",
-    "!packages/@monomind/guidance/dist/**/*.map",
-    "packages/@monomind/guidance/package.json",
     "packages/@monomind/cli/.claude/**",
     "!packages/@monomind/cli/.claude/**/*.db",
-    ".claude-plugin/**",
-    ".claude/**",
-    "!.claude/**/*.db",
-    "!.claude/**/*.map",
+    "!packages/@monomind/cli/.claude/**/.monomind/**",
+    "!packages/@monomind/cli/.claude/**/*.lock",
+    "!packages/@monomind/cli/.claude/agents/generated/**",
+    "!packages/@monomind/cli/.claude/agents/reengineer-squad/**",
     "README.md",
     "LICENSE"
   ],
@@ -55,7 +51,7 @@
     "build:ts": "cd packages/@monomind/cli && npm run build || true",
     "test": "vitest",
     "test:ui": "vitest --ui",
-    "test:security": "vitest run packages/__tests__/security/",
+    "test:security": "vitest run tests/security/",
     "security:audit": "npm audit --audit-level high",
     "security:fix": "npm audit fix",
     "security:test": "npm run test:security",
@@ -64,12 +60,11 @@
     "v1:security": "npm run security:audit && npm run security:test"
   },
   "dependencies": {
-    "@monoes/monobrowse": "^1.0.2",
-    "@monoes/monograph": "^1.3.0",
+    "@monoes/monobrowse": "^1.0.3",
+    "@monoes/monograph": "^1.4.0",
     "mammoth": "^1.12.0",
     "pdf-parse": "^2.4.5",
-    "semver": "^7.6.0",
-    "zod": "^3.22.0"
+    "semver": "^7.6.0"
   },
   "overrides": {
     "hono": ">=4.12.21",
@@ -158,35 +153,21 @@
     "anthropic",
     "ai",
     "ai-agents",
-    "multi-agent",
-    "agent-orchestration",
-    "swarm-intelligence",
-    "swarm",
     "mcp",
     "model-context-protocol",
-    "llm",
-    "large-language-model",
-    "gpt",
-    "chatgpt",
     "automation",
     "workflow",
-    "orchestration",
     "cli",
     "developer-tools",
     "devtools",
     "coding-assistant",
     "code-generation",
-    "enterprise",
-    "vector-database",
-    "embeddings",
-    "machine-learning",
-    "neural-network",
+    "knowledge-graph",
+    "code-analysis",
     "monomind",
-    "distributed-systems",
-    "consensus",
-    "self-learning",
-    "harness",
-    "organizations"
+    "organizations",
+    "autonomous-agents",
+    "hooks"
   ],
   "author": {
     "name": "nokhodian",

package/packages/@monomind/cli/.claude/agents/github/issue-tracker.md

@@ -281,8 +281,6 @@ Updates will be posted automatically by swarm agents during implementation.
 ### Seamless integration with:
 - `/github pr-manager` - Link issues to pull requests
 - `/github release-manager` - Coordinate release issues
-- `/sparc orchestrator` - Complex project coordination
-- `/sparc tester` - Automated testing workflows
 
 ## Metrics and Analytics
 

package/packages/@monomind/cli/.claude/agents/github/pr-manager.md

@@ -145,8 +145,6 @@ mcp__monomind__memory_store {
 - `/github issue-tracker` - For project coordination
 - `/github branch-manager` - For branch strategy
 - `/github ci-orchestrator` - For CI/CD integration
-- `/sparc reviewer` - For detailed code analysis
-- `/sparc tester` - For comprehensive testing
 
 ## Error Handling
 

package/packages/@monomind/cli/.claude/agents/github/repo-architect.md

@@ -72,8 +72,8 @@ mcp__github__push_files {
       content: "[GitHub modes template]"
     },
     {
-      path: ".claude/commands/sparc/sparc-modes.md",
-      content: "[SPARC modes template]"
+      path: ".claude/commands/mastermind/help.md",
+      content: "[Mastermind commands template]"
     },
     {
       path: ".claude/settings.json",
@@ -116,7 +116,6 @@ npx monomind@latest mcp start
 
 ## Features
 - Monomind swarm coordination
-- SPARC development modes
 - GitHub workflow automation
 - Knowledge graph integration
 
@@ -270,16 +269,11 @@ monomind/
 │   │   ├── pr-manager.md
 │   │   ├── issue-tracker.md
 │   │   └── sync-coordinator.md
-│   ├── sparc/
-│   │   ├── sparc-modes.md
-│   │   ├── coder.md
-│   │   └── tester.md
 │   └── swarm/
 │       ├── coordination.md
 │       └── orchestration.md
 ├── agents/
-│   ├── github/
-│   └── sparc/
+│   └── github/
 └── settings.json
 ```
 
@@ -355,5 +349,3 @@ const integrationPattern = {
 
 - `/github sync-coordinator` - For cross-repo synchronization
 - `/github release-manager` - For coordinated releases
-- `/sparc architect` - For detailed architecture design
-- `/sparc optimizer` - For performance optimization

package/packages/@monomind/cli/.claude/agents/goal/goal-planner.md

@@ -140,7 +140,6 @@ When handling requests:
 Integration with Monomind:
 - Coordinate with other specialized agents for specific actions
 - Use swarm coordination for parallel action execution
-- Leverage SPARC methodology for structured development tasks
 - Apply concurrent execution patterns from CLAUDE.md
 
 Advanced swarm coordination patterns:

package/packages/@monomind/cli/.claude/commands/github/issue-tracker.md

@@ -275,8 +275,6 @@ Generated with Claude Code
 ### Seamless integration with:
 - `/github pr-manager` - Link issues to pull requests
 - `/github release-manager` - Coordinate release issues
-- `/sparc orchestrator` - Complex project coordination
-- `/sparc tester` - Automated testing workflows
 
 ## Metrics and Analytics
 

package/packages/@monomind/cli/.claude/commands/github/pr-manager.md

@@ -155,8 +155,6 @@ mcp__monomind__memory_store {
 - `/github issue-tracker` - For project coordination
 - `/github branch-manager` - For branch strategy
 - `/github ci-orchestrator` - For CI/CD integration
-- `/sparc reviewer` - For detailed code analysis
-- `/sparc tester` - For comprehensive testing
 
 ## Error Handling
 

package/packages/@monomind/cli/.claude/commands/github/repo-architect.md

@@ -78,8 +78,8 @@ mcp__github__push_files {
       content: "[GitHub modes template]"
     },
     {
-      path: ".claude/commands/sparc/sparc-modes.md",
-      content: "[SPARC modes template]"
+      path: ".claude/commands/mastermind/help.md",
+      content: "[Mastermind commands template]"
     },
     {
       path: ".claude/config.json",
@@ -121,14 +121,13 @@ mcp__github__push_files {
 
 ## Quick Start
 \`\`\`bash
-npx monomind init --sparc
+npx monomind init
 npm install
 npx monomind start --ui
 \`\`\`
 
 ## Features
 - Monomind swarm integration
-- SPARC development modes
 - GitHub workflow automation
 - Advanced coordination capabilities
 
@@ -280,10 +279,6 @@ monomind/
 │   │   ├── pr-manager.md
 │   │   ├── issue-tracker.md
 │   │   └── sync-coordinator.md
-│   ├── sparc/
-│   │   ├── sparc-modes.md
-│   │   ├── coder.md
-│   │   └── tester.md
 │   └── swarm/
 │       ├── coordination.md
 │       └── orchestration.md
@@ -368,8 +363,6 @@ const integrationPattern = {
 
 - `/github sync-coordinator` - For cross-repo synchronization
 - `/github release-manager` - For coordinated releases
-- `/sparc architect` - For detailed architecture design
-- `/sparc optimizer` - For performance optimization
 
 ### Workflow Enhancement:
 

package/packages/@monomind/cli/.claude/commands/mastermind/help.md

@@ -57,8 +57,8 @@ npx monomind monograph search -q "authentication"
 npx monomind monograph stats
 
 # Pattern logging
-npx monomind neural patterns --action list
-npx monomind neural status --verbose
+npx monomind hooks intelligence patterns --action list
+npx monomind hooks intelligence status --verbose
 
 # Hooks
 npx monomind hooks pre-task --description "task description"
@@ -78,7 +78,7 @@ npx monomind performance benchmark --suite all
 
 ## Built-in Workflow Templates
 
-`development`, `research`, `testing`, `security-audit`, `code-review`, `refactoring`, `sparc`, `custom`
+`development`, `research`, `testing`, `security-audit`, `code-review`, `refactoring`, `custom`
 
 ## Swarm Topologies
 

package/packages/@monomind/cli/.claude/commands/workflows/README.md

@@ -51,7 +51,6 @@ npx monomind workflow template create --name "my-workflow"
 | `security-audit` | Threat Model → Static → Dynamic → Report | security-architect, auditor |
 | `code-review` | Initial → Security → Quality → Feedback | reviewer, auditor, analyst |
 | `refactoring` | Analysis → Planning → Refactor → Validation | architect, coder, reviewer |
-| `sparc` | Spec → Pseudocode → Architecture → Refinement → Completion | architect, coder, tester, reviewer |
 | `custom` | Define your own stages | configurable |
 
 ## MCP Tools

package/packages/@monomind/cli/.claude/commands/workflows/workflow-create.md

@@ -29,7 +29,6 @@ npx monomind workflow template list
 
 # Show a specific template's stages and agents
 npx monomind workflow template show development
-npx monomind workflow template show sparc
 ```
 
 ## Template Create Flags

package/packages/@monomind/cli/.claude/commands/workflows/workflow-execute.md

@@ -1,6 +1,6 @@
 ---
 name: workflows:workflow-execute
-description: Run multi-agent workflows using built-in templates (development, research, testing, sparc, security-audit, etc.) via real npx monomind workflow run CLI
+description: Run multi-agent workflows using built-in templates (development, research, testing, security-audit, etc.) via real npx monomind workflow run CLI
 ---
 
 # Workflow Execute
@@ -23,7 +23,6 @@ npx monomind workflow run -t development --task "Build REST API with auth"
 npx monomind workflow run -t research --task "Analyze performance bottlenecks"
 npx monomind workflow run -t testing
 npx monomind workflow run -t security-audit
-npx monomind workflow run -t sparc --task "New payment module"
 
 # Run from a workflow file
 npx monomind workflow run -f ./workflow.yaml
@@ -55,7 +54,6 @@ npx monomind workflow run -t development --dry-run
 | `security-audit` | Threat Model → Static → Dynamic → Report | security-architect, auditor |
 | `code-review` | Initial → Security → Quality → Feedback | reviewer, auditor, analyst |
 | `refactoring` | Analysis → Planning → Refactor → Validation | architect, coder, reviewer |
-| `sparc` | Spec → Pseudocode → Architecture → Refinement → Completion | architect, coder, tester, reviewer |
 | `custom` | Define your own | configurable |
 
 ## MCP Tools

package/packages/@monomind/cli/.claude/commands/workflows/workflow-export.md

@@ -23,7 +23,6 @@ npx monomind workflow template list
 
 # Show details for a specific template (stages, agents, estimated duration)
 npx monomind workflow template show development
-npx monomind workflow template show sparc
 npx monomind workflow template show security-audit
 
 # Validate a custom workflow file
@@ -45,7 +44,6 @@ npx monomind workflow list --status all
 | `security-audit` | Threat Model → Static → Dynamic → Report | 20-40 min |
 | `code-review` | Initial → Security → Quality → Feedback | 10-25 min |
 | `refactoring` | Analysis → Planning → Refactor → Validation | 15-35 min |
-| `sparc` | Spec → Pseudocode → Architecture → Refinement → Completion | 25-45 min |
 | `custom` | Define your own stages | varies |
 
 ## MCP Tools

package/packages/@monomind/cli/.claude/helpers/handlers/agent-start-handler.cjs

@@ -6,7 +6,7 @@ const path = require('path');
 const fs = require('fs');
 
 module.exports = {
-  handle: function(hCtx) {
+  handle: async function(hCtx) {
     var hookInput = hCtx.hookInput;
     var CWD = hCtx.CWD;
     var _openMonographDb = hCtx._openMonographDb;
@@ -79,5 +79,22 @@ module.exports = {
         }
       }
     } catch (e) { /* non-fatal */ }
+
+    // Bridge to @monomind/hooks registry — fires AgentSpawn hooks (was previously never
+    // wired: HookEvent.AgentSpawn existed but no CJS handler ever fired it).
+    try {
+      var _hooksModule = hCtx._ensureHooksModule ? await hCtx._ensureHooksModule() : null;
+      if (_hooksModule && _hooksModule.executeHooks && _hooksModule.HookEvent) {
+        var agentTypeBridge = String(hookInput.subagent_type || hookInput.agentType || hookInput.agent_type || hookInput.agentSlug || 'unknown');
+        var agentDescBridge = String(hookInput.description || hookInput.prompt_description || '');
+        _hooksModule.executeHooks(_hooksModule.HookEvent.AgentSpawn, {
+          agent: {
+            id: hookInput.agentId || hookInput.agent_id || (agentTypeBridge + '-' + Date.now()),
+            type: agentTypeBridge,
+            description: agentDescBridge.slice(0, 500),
+          },
+        }, { continueOnError: true, timeout: 1500 }).catch(function() {});
+      }
+    } catch (e) { /* non-fatal */ }
   },
 };

package/packages/@monomind/cli/.claude/helpers/handlers/edit-handler.cjs

@@ -140,6 +140,21 @@ module.exports = {
       }
     } catch (e) { /* non-fatal */ }
 
+    // Bridge to @monomind/hooks registry — fires PostEdit hooks (observability bus, guidance provider).
+    // Each hook event runs in a fresh process, so hCtx._hooksModule set by session-restore in an
+    // earlier invocation is never visible here — must (re)load lazily via _ensureHooksModule().
+    var _hooksModule = hCtx._hooksModule || (hCtx._ensureHooksModule ? await hCtx._ensureHooksModule() : null);
+    if (_hooksModule && _hooksModule.executeHooks && _hooksModule.HookEvent) {
+      try {
+        var editFileBridge = hookInput.file_path || toolInput.file_path
+          || process.env.TOOL_INPUT_file_path || args[0] || '';
+        _hooksModule.executeHooks(_hooksModule.HookEvent.PostEdit, {
+          file: { path: editFileBridge, operation: 'modify' },
+          duration: 0,
+        }, { continueOnError: true, timeout: 1500 }).catch(function() {});
+      } catch (e) { /* non-fatal */ }
+    }
+
     console.log('[OK] Edit recorded');
   }
 };

package/packages/@monomind/cli/.claude/helpers/handlers/gates-handler.cjs

@@ -2,14 +2,8 @@
  * Enforcement Gates Handler
  *
  * Inline gate logic for PreToolUse hooks — no ESM/package dependency.
- *
- * Patterns are an INTENTIONAL SUPERSET of @monomind/guidance/src/gates.ts defaults:
- *   - All categories from DEFAULT_GATE_CONFIG are covered here
- *   - Many patterns are enhanced (e.g. --force-with-lease, -fr reversed flags, broader kubectl)
- *   - Key thresholds MUST stay aligned: password/secret min length = 8 chars (both files)
- *
- * When updating patterns in gates.ts, check whether the corresponding pattern here
- * also needs updating — and vice versa.
+ * This regex table is the canonical (and only) gate definition; the former
+ * @monomind/guidance package it mirrored has been removed.
  *
  * Gates enforced at runtime:
  *   pre-bash  → destructive-ops  (require-confirmation → block)