monomind 1.19.0 → 2.0.0

package/.claude/commands/mastermind.md

@@ -1,121 +0,0 @@
----
-name: mastermind
-description: Swarm & Hive-Mind architecture picker — presents all topologies, consensus protocols, and strategies, then gives one concrete recommendation for the current task
----
-
-IMPORTANT: Do NOT dump all the reference content at once. Follow the two-phase flow below exactly.
-
-**If $ARGUMENTS is non-empty**, treat it as the user's task description and skip Phase 1 — go straight to Phase 2 with that description.
-
----
-
-## Phase 1 — Present the picker and STOP
-
-Output this menu and WAIT for the user's reply before doing anything else:
-
----
-
-**MASTERMIND — Swarm & Hive-Mind Picker**
-
-Describe your task and I'll recommend the right mode, or pick directly from the options below.
-
-### Swarm Topologies
-| # | Topology | Shape | Best for |
-|---|---|---|---|
-| **1** | `hierarchical` | One coordinator → all workers | Feature dev, bug fixes, most coding tasks |
-| **2** | `mesh` | Every agent ↔ every agent | Research, brainstorming, docs |
-| **3** | `hierarchical-mesh` | Queen + peer lanes | Large projects, 10–15 agents |
-| **4** | `ring` | Agent → next → next → loop | Pipelines: research→draft→edit→review |
-| **5** | `star` | Hub aggregates independent workers | Parallel analysis, test coverage |
-| **6** | `adaptive` | Starts hierarchical, self-reconfigures | Long-running or unknown workloads |
-
-### Hive-Mind Modes
-| # | Mode | Consensus | Best for |
-|---|---|---|---|
-| **7** | `hive-mind hierarchical-mesh` | `byzantine` | Security-critical, fault-tolerant (f < n/3) |
-| **8** | `hive-mind hierarchical` | `raft` | Refactors, rewrites — leader keeps authoritative state |
-| **9** | `hive-mind mesh` | `gossip` | Large agent counts, eventual consistency |
-| **10** | `hive-mind hierarchical-mesh` | `crdt` | Concurrent writes, collaborative editing |
-| **11** | `hive-mind adaptive` | `quorum` | Custom fault-tolerance, majority vote |
-
-> Type a number (1–11), or just **describe what you want to build** and I'll pick for you.
-
----
-
-## Phase 2 — Give a concrete recommendation
-
-Based on the task or user choice, pick ONE mode and output EXACTLY this structure:
-
----
-
-**Your Plan**
-
-- **Mode:** `<swarm|hive-mind>` · `<topology>` — <one sentence why>
-- **Agents:** <N> · <list agent types>
-- **Consensus:** `<protocol>` — <one sentence why>
-- **Strategy:** `<specialized|balanced|pipeline|parallel>` _(swarm only)_
-
-**Launch command:**
-```bash
-# Swarm:
-npx monomind swarm init --topology <topology> --max-agents <N> --strategy <strategy>
-
-# OR Hive-Mind (no --strategy flag):
-npx monomind hive-mind init --topology <topology> --consensus <protocol> --max-agents <N>
-```
-
-**Agent team:**
-```
-coordinator  → plans and delegates
-<agent>      → <role>
-<agent>      → <role>
-...
-```
-
-**Then spawn in Claude Code (one message):**
-```javascript
-// Bash: init the swarm/hive-mind first (above command)
-// Then Task tool calls — all in the same message:
-Task({ subagent_type: "coordinator", description: "...", run_in_background: true })
-Task({ subagent_type: "<agent>",     description: "...", run_in_background: true })
-// ... one Task call per agent
-```
-
-> Ready? Say **go** and I'll launch it, or adjust any detail first.
-
----
-
-## Recommendation Logic (internal — do not output)
-
-Use this to pick the right mode when the user describes a task:
-
-| Task type | Mode | Topology | Consensus | Agents | Strategy |
-|---|---|---|---|---|---|
-| Bug fix (1–2 files) | swarm | hierarchical | raft | 4 | specialized |
-| Feature (3+ files) | swarm | hierarchical | raft | 6–8 | specialized |
-| Refactor / migration | swarm | hierarchical | raft | 5–6 | specialized |
-| Performance optimization | swarm | star | raft | 4–5 | parallel |
-| Security audit / fix | hive-mind | hierarchical-mesh | byzantine | 6 | specialized |
-| Research / docs | swarm | mesh | gossip | 4–6 | balanced |
-| Docs pipeline | swarm | ring | raft | 4 | pipeline |
-| Testing / coverage | swarm | star | raft | 5–6 | parallel |
-| Architecture design | swarm | hierarchical-mesh | raft | 8–10 | specialized |
-| Full release (end-to-end) | hive-mind | hierarchical-mesh | byzantine | 12–15 | specialized |
-| Long-running / unknown | swarm | adaptive | raft | 8–10 | specialized |
-| Refactor with rollback safety | hive-mind | hierarchical | raft | 5–6 | specialized |
-| Concurrent collaborative writes | hive-mind | hierarchical-mesh | crdt | 4–6 | balanced |
-| Large-scale eventual consistency (20+ agents) | hive-mind | mesh | gossip | 15–20 | balanced |
-| Custom fault-tolerance / majority vote | hive-mind | adaptive | quorum | 8–12 | specialized |
-
-**Quick decision rule:**
-- 1 file → use Edit tool directly, no swarm needed
-- 2–3 files, clear scope → swarm hierarchical, 4–6 agents, raft
-- Security/fault-critical → hive-mind hierarchical-mesh, byzantine
-- Research/exploration → swarm mesh, gossip
-- Pipeline stages (A→B→C) → swarm ring
-- Parallel independent work → swarm star
-- 10+ agents or long-running → hierarchical-mesh or adaptive
-- Refactor needing authoritative rollback → hive-mind hierarchical, raft
-- Concurrent collaborative writes → hive-mind hierarchical-mesh, crdt
-- Large agent pool (20+), eventual consistency → hive-mind mesh, gossip
-- Custom fault-tolerance threshold → hive-mind adaptive, quorum

package/.claude/commands/memory/README.md

@@ -1,79 +0,0 @@
----
-name: memory:README
----
-
-# Memory Commands
-
-Commands for the LanceDB memory system — vector search, namespaced storage, HNSW indexing, and cross-session persistence.
-
-## Available Subcommands
-
-| Subcommand | Description |
-|---|---|
-| `memory init` | Initialize memory backend (lancedb, sqlite, hybrid) |
-| `memory store` | Store a memory entry with optional vector embedding |
-| `memory retrieve` | Retrieve a memory entry by key |
-| `memory search` | Search memory (semantic / keyword / hybrid) |
-| `memory list` | List all memory entries with optional filters |
-| `memory edit` | Update an existing memory entry |
-| `memory delete` | Delete one or more memory entries |
-| `memory templates` | Manage memory templates |
-| `memory stats` | Show memory usage statistics |
-| `memory configure` | Configure memory backend settings |
-| `memory cleanup` | Remove expired or stale entries |
-| `memory compress` | Compress stored data and rebuild indexes |
-| `memory export` | Export memories to JSON/JSONL file |
-| `memory import` | Import memories from a file |
-
-## Quick Reference
-
-```bash
-# Initialize
-npx monomind memory init --backend hybrid
-
-# Store
-npx monomind memory store --key "auth-pattern" --value "Use JWT with refresh tokens" --namespace "patterns"
-
-# Search
-npx monomind memory search --query "authentication" --type hybrid --build-hnsw
-
-# Retrieve exact key
-npx monomind memory retrieve --key "auth-pattern"
-
-# List all in namespace
-npx monomind memory list --namespace "patterns"
-
-# Export / Import
-npx monomind memory export --output backup.json --format json
-npx monomind memory import --input backup.json --merge
-```
-
-## Files
-
-- [memory-search.md](./memory-search.md) — Search memory (semantic/keyword/hybrid + HNSW)
-
-## MCP Tools
-
-| Tool | Purpose |
-|---|---|
-| `mcp__monomind__memory_store` | Store a memory entry |
-| `mcp__monomind__memory_retrieve` | Retrieve by key |
-| `mcp__monomind__memory_search` | Search memory |
-| `mcp__monomind__memory_list` | List entries |
-| `mcp__monomind__memory_delete` | Delete entries |
-| `mcp__monomind__memory_stats` | Usage statistics |
-| `mcp__monomind__memory_migrate` | Migrate between backends |
-
-## Backends
-
-| Backend | Description | Recommended |
-|---|---|---|
-| `lancedb` | Full LanceDB with HNSW vector search | Production |
-| `sqlite` | SQLite-only, no vector search | Lightweight |
-| `hybrid` | SQLite + LanceDB HNSW | Default (recommended) |
-
-## See Also
-
-- `hooks intelligence` — pattern learning on top of memory
-- `neural` — neural pattern training
-- `session` — session state (separate from memory)

package/.claude/commands/memory/memory-search.md

@@ -1,77 +0,0 @@
----
-name: memory:memory-search
----
-
-# memory search
-
-Search stored memory using semantic, keyword, or hybrid search.
-
-## Usage
-
-```bash
-npx monomind memory search [options]
-```
-
-## Options
-
-| Flag | Short | Type | Default | Description |
-|---|---|---|---|---|
-| `--query` | `-q` | string | — | Search query text |
-| `--namespace` | `-n` | string | `default` | Namespace to search |
-| `--limit` | `-l` | number | `10` | Maximum results to return |
-| `--threshold` | — | number | `0.7` | Minimum similarity threshold (0–1) |
-| `--type` | `-t` | string | `hybrid` | Search type: `semantic`, `keyword`, `hybrid` |
-| `--build-hnsw` | — | boolean | `false` | Build pure-JS HNSW index before search (O(log n) vs O(n) linear) |
-| `--format` | — | string | — | Output format: `json` |
-
-## Examples
-
-```bash
-# Semantic search
-npx monomind memory search --query "authentication patterns"
-
-# Keyword search
-npx monomind memory search -q "JWT" --type keyword
-
-# Hybrid search with namespace
-npx monomind memory search -q "error handling" -n "project-x" --type hybrid
-
-# Build HNSW index first for large datasets
-npx monomind memory search -q "config" --build-hnsw --limit 20
-
-# High-precision search with threshold
-npx monomind memory search -q "OAuth flow" --threshold 0.9
-
-# JSON output
-npx monomind memory search -q "auth" --format json
-```
-
-## Search Types
-
-| Type | Description | Best For |
-|---|---|---|
-| `semantic` | Vector similarity search | Concept/meaning matching |
-| `keyword` | BM25 full-text search | Exact term matching |
-| `hybrid` | Combined semantic + keyword | General purpose (recommended) |
-
-## HNSW Index
-
-Use `--build-hnsw` when searching large memory stores (1,000+ entries). The pure-JS HNSW index gives O(log n) approximate-nearest-neighbor queries (vs O(n) linear scan) after the one-time build cost.
-
-## MCP Tool
-
-```javascript
-mcp__monomind__memory_search({
-  query: "authentication patterns",
-  namespace: "default",
-  limit: 10,
-  threshold: 0.7,
-  type: "hybrid"
-})
-```
-
-## See Also
-
-- `memory store` — store new memories
-- `memory list` — list all memories
-- `memory retrieve` — retrieve by exact key

package/.claude/commands/monitoring/README.md

@@ -1,69 +0,0 @@
----
-name: monitoring:README
----
-
-# Monitoring Commands
-
-Commands for monitoring Monomind system health — swarm status, agents, tasks, memory, and performance metrics.
-
-## Available Commands
-
-| Command | Description |
-|---|---|
-| `status` | Full system status (swarm, agents, tasks, memory, MCP) |
-| `status agents` | Detailed agent table with uptime and success rate |
-| `status tasks` | Detailed task table with progress and priority |
-| `status memory` | Memory backend stats and HNSW performance |
-| `agent metrics` | Agent performance metrics by type and time period |
-| `agent health` | Per-agent health check with optional watch mode |
-| `swarm status` | Swarm-specific status (topology, consensus, agents) |
-
-## Quick Reference
-
-```bash
-# One-shot system snapshot
-npx monomind status
-
-# Live watch (refreshes every 2s)
-npx monomind status --watch
-
-# Health checks with pass/warn/fail
-npx monomind status --health-check
-
-# Detailed agent view
-npx monomind status agents
-
-# Agent performance metrics
-npx monomind agent metrics --period 7d
-
-# Swarm status
-npx monomind swarm status
-```
-
-## Files
-
-- [status.md](./status.md) — Full system status + watch mode + health checks
-- [agents.md](./agents.md) — `status agents` subcommand
-- [agent-metrics.md](./agent-metrics.md) — `agent metrics` by type and period
-
-## MCP Tools
-
-| Tool | Purpose |
-|---|---|
-| `mcp__monomind__swarm_status` | Swarm health and agent counts |
-| `mcp__monomind__swarm_health` | Swarm health check |
-| `mcp__monomind__agent_list` | All agents with metrics |
-| `mcp__monomind__agent_status` | Specific agent status |
-| `mcp__monomind__agent_health` | Agent health check |
-| `mcp__monomind__memory_stats` | Memory backend stats |
-| `mcp__monomind__task_summary` | Task counts by status |
-| `mcp__monomind__task_list` | All tasks with progress |
-| `mcp__monomind__system_health` | Full system health |
-| `mcp__monomind__system_metrics` | System performance metrics |
-| `mcp__monomind__mcp_status` | MCP server status |
-
-## See Also
-
-- `doctor` — comprehensive diagnostics (`npx monomind doctor`)
-- `hooks metrics` — learning and intelligence metrics
-- `performance` — performance profiling commands

package/.claude/commands/monitoring/agent-metrics.md

@@ -1,65 +0,0 @@
----
-name: monitoring:agent-metrics
----
-
-# agent metrics
-
-Show agent performance metrics — tasks completed, success rate, and memory vectors by agent type.
-
-## Usage
-
-```bash
-npx monomind agent metrics [agentId] [options]
-```
-
-The optional `agentId` positional argument filters to a specific agent. Omit for all agents.
-
-## Options
-
-| Flag | Short | Type | Default | Description |
-|---|---|---|---|---|
-| `--period` | `-p` | string | `24h` | Time period: `1h`, `24h`, `7d`, `30d` |
-| `--format` | — | string | — | Output format: `json` |
-
-## Examples
-
-```bash
-# All agents — last 24 hours
-npx monomind agent metrics
-
-# Last hour
-npx monomind agent metrics --period 1h
-
-# Last 7 days
-npx monomind agent metrics -p 7d
-
-# Specific agent
-npx monomind agent metrics agent-001
-
-# JSON output
-npx monomind agent metrics --format json
-```
-
-## Output Sections
-
-**Summary table** — total agents, active agents, tasks completed, average success rate, memory vector count
-
-**By Agent Type table** — per-type breakdown: count, tasks completed, success rate
-
-**Memory** — vector count and search backend (HNSW-indexed once vectors exist)
-
-## Data Source
-
-Metrics are read from `.swarm/agents/` state files and `.swarm/swarm-activity.json`. If no agents have been spawned yet, the output will note this with a suggestion to run `agent spawn`.
-
-## MCP Tool
-
-```javascript
-mcp__monomind__agent_status({ agentId: "agent-001" })
-```
-
-## See Also
-
-- `status agents` — live agent status table
-- `agent health` — per-agent health check with `--watch` mode
-- `agent list` — list all agents

package/.claude/commands/monitoring/agents.md

@@ -1,71 +0,0 @@
----
-name: monitoring:agents
----
-
-# status agents
-
-Show detailed agent status — ID, type, current task, uptime, and success rate for all running agents.
-
-## Usage
-
-```bash
-npx monomind status agents [options]
-```
-
-## Options
-
-| Flag | Type | Description |
-|---|---|---|
-| `--format` | string | Output format: `json` |
-
-## Examples
-
-```bash
-# Show all agents
-npx monomind status agents
-
-# JSON output
-npx monomind status agents --format json
-```
-
-## Output Columns
-
-| Column | Description |
-|---|---|
-| ID | Agent identifier |
-| Type | Agent type (coder, reviewer, tester, etc.) |
-| Status | `healthy` / `degraded` / `stopped` |
-| Current Task | Task the agent is executing (or `-`) |
-| Uptime | How long the agent has been running |
-| Success | Task success rate (%) |
-
-## Related Commands
-
-```bash
-# Quick agent count overview (in main status)
-npx monomind status
-
-# Agent performance metrics by type
-npx monomind agent metrics
-
-# Agent health check
-npx monomind agent health
-
-# List all agents
-npx monomind agent list
-```
-
-## MCP Tool
-
-```javascript
-mcp__monomind__agent_list({
-  includeMetrics: true,
-  status: "all"
-})
-```
-
-## See Also
-
-- `status` — full system status including agents
-- `agent metrics` — performance metrics over time
-- `agent health` — per-agent health checks

package/.claude/commands/monitoring/status.md

@@ -1,108 +0,0 @@
----
-name: monitoring:status
----
-
-# status
-
-Show system status — swarm health, agents, tasks, memory, and MCP server. The primary monitoring command.
-
-## Usage
-
-```bash
-npx monomind status [options]
-npx monomind status <subcommand>
-```
-
-## Options
-
-| Flag | Short | Type | Default | Description |
-|---|---|---|---|---|
-| `--watch` | `-w` | boolean | `false` | Continuously refresh status (live view) |
-| `--interval` | `-i` | number | `2` | Refresh interval in seconds (watch mode) |
-| `--health-check` | — | boolean | `false` | Run structured health checks and exit |
-| `--format` | — | string | — | Output format: `json` |
-
-## Subcommands
-
-| Subcommand | Description |
-|---|---|
-| `status agents` | Detailed agent status table (ID, type, current task, uptime, success rate) |
-| `status tasks` | Detailed task status table (ID, type, priority, agent, progress) |
-| `status memory` | Memory backend stats (entries, size, HNSW, performance metrics) |
-
-## Examples
-
-```bash
-# One-shot status snapshot
-npx monomind status
-
-# Live watch mode (refreshes every 2s)
-npx monomind status --watch
-
-# Watch with custom interval
-npx monomind status --watch -i 5
-
-# Health checks with pass/warn/fail output
-npx monomind status --health-check
-
-# JSON output for scripting
-npx monomind status --format json
-
-# Detailed agent table
-npx monomind status agents
-
-# Detailed task table
-npx monomind status tasks
-
-# Memory backend details
-npx monomind status memory
-```
-
-## Status Display Sections
-
-- **Swarm** — ID, topology, health (`healthy` / `degraded` / `stopped`), uptime
-- **Agents** — active / idle / total counts
-- **Tasks** — pending / running / completed / failed / total
-- **Memory** — backend, entries, size, search time, cache hit rate
-- **MCP Server** — running state, transport, port
-- **Performance** — CPU usage, memory usage, vector search speed
-
-## Health Check Mode
-
-`--health-check` runs structured checks and exits with code 0 (all pass) or 1 (any fail):
-
-| Check | Pass Condition |
-|---|---|
-| System Running | MCP/swarm reachable |
-| Swarm Health | status = `healthy` |
-| Agents Available | active > 0 |
-| MCP Server | running |
-| Memory Backend | backend != `none` |
-| Task Success Rate | < 5% failure rate |
-
-## Watch Mode
-
-`--watch` clears the screen and re-renders on each interval. Press `Ctrl+C` to exit.
-
-## MCP Tools (equivalent)
-
-```javascript
-// Swarm status
-mcp__monomind__swarm_status({ includeMetrics: true })
-
-// Memory stats
-mcp__monomind__memory_stats({})
-
-// Task summary
-mcp__monomind__task_summary({})
-
-// Agent list
-mcp__monomind__agent_list({ includeMetrics: true, status: "all" })
-```
-
-## See Also
-
-- `agent metrics` — performance metrics per agent type
-- `agent health` — agent-specific health check
-- `swarm status` — swarm-specific status
-- `doctor` — comprehensive system diagnostics

package/.claude/commands/monobrowse.md

@@ -1,21 +0,0 @@
----
-name: monobrowse
-description: Launch monomind browse for web UI testing and automation — native TypeScript CDP client, no external binary needed
----
-
-Invoke the agent-browser-testing skill to test or automate a web UI.
-
-`monomind browse` is built-in — no install needed. Invoke the skill:
-
-Skill("agent-browser-testing")
-
-Pass the user's argument (if any) as the URL or task description: $1
-
-Use the full monomind browse workflow:
-1. `npx monomind browse open <url>`
-2. `npx monomind browse snapshot -i`
-3. Act using element refs (@e1, @e2, ...)
-4. Re-snapshot to verify
-5. Report results (PASS / FAIL / WARN)
-
-Examples: `/monobrowse`, `/monobrowse https://example.com`, `/monobrowse test the login flow`

package/.claude/commands/monoes/README.md

@@ -1,30 +0,0 @@
----
-name: monoes:README
-description: monoes tool family commands — install and manage monotask, mono-agent, and mono-clip
----
-
-# monoes Commands
-
-Commands for interacting with the `monoes` tool family — separate sibling projects (not part of this monorepo) that live alongside it on disk.
-
-| Tool | What it is | Distribution |
-|---|---|---|
-| `monotask` | P2P kanban / task board (Rust, CLI + Tauri desktop app) | Homebrew tap `monoes/tap` (renamed from `nokhodian/tap`) |
-| `mono-agent` | Workflow/browser automation agent (Go CLI + Wails GUI), binary name `monoagentcli` | Prebuilt GitHub releases (`monoes/mono-agent`), or build from source |
-| `mono-clip` | Desktop clipboard/utility app (Tauri + SvelteKit) + `mclip` CLI sidecar | Homebrew tap `monoes/tap` (renamed from `nokhodian/tap`) |
-
-## Files
-
-- [install.md](./install.md) — Detect, install, and troubleshoot any of the three tools; records their existence in monomind's memory once installed
-- [monoagent.md](./monoagent.md) — Drive the mono-agent CLI (`monoagentcli`): logins, search/message/comment, actions, workflows, node execution
-- [monotask.md](./monotask.md) — Drive the monotask CLI: boards/columns/cards, spaces, GitHub/Linear/mail sync
-- [monoclip.md](./monoclip.md) — Drive mono-clip's `mclip` sidecar CLI: clipboard history and folders
-
-## Crash reporting
-
-All four tools (monomind, mono-agent, monotask, mono-clip) auto-file a GitHub issue on their own repo when they hit an uncaught crash — on by default, `monomind crash-reporting disable` to opt out. That only covers hard crashes. If a user is stuck on non-crash friction with any of these tools — a confusing error, undocumented behavior, something that looks like a real bug — suggest opening an issue yourself (`gh issue create -R monoes/<repo> ...`) rather than staying silent about it.
-
-## See Also
-
-- CLAUDE.md Knowledge Graph / memory sections — how monomind persists cross-session knowledge
-- CLAUDE.md's "Crash reporting" behavioral rule