@monoes/monomindcli 2.16.3 → 2.16.5

package/.claude/commands/mastermind/do.md

@@ -1,4 +1,6 @@
-<!-- "Mastermind — Execute tasks from a task file (default, docs/tasks/) or monotask board (--monotask flag) with parallel, minimal, or sequential agent modes, context group routing, and review cycles" -->
+---
+description: Mastermind — Execute tasks from a task file (default, docs/tasks/) or monotask board (--monotask flag) with parallel, minimal, or sequential agent modes, context group routing, and review cycles
+---
 
 ## Repeat Flag Extraction
 
@@ -67,7 +69,7 @@ Otherwise:
 
 ### 2a: Load all pending tasks
 
-**File mode:** Read `TASK_FILE`. Find all `## Task N: <title>` sections with `> status: todo` or `> status: backlog`. Follow the parsing spec in `mastermind-taskfile/SKILL.md`. If `--filter` was set, keep only tasks whose title contains the filter text (case-insensitive).
+**File mode:** Read `TASK_FILE`. Find all `## Task N: <title>` sections with `> status: todo` or `> status: backlog`. Follow the parsing spec in `.claude/commands/mastermind/_taskfile.md`. If `--filter` was set, keep only tasks whose title contains the filter text (case-insensitive).
 
 **Monotask mode:** 
 ```bash
@@ -419,7 +421,7 @@ Proceed to Step 9.
 1. Change `> status: review` → `> status: done` in that task's section
 2. Replace all `- [ ]` with `- [x]` in that task's Checklist section
 3. If DONE_WITH_CONCERNS: append `> concerns: <concerns>` after the status line
-4. **Unblock dependents**: Follow the "Prerequisite Unblock Logic" from `mastermind-taskfile/SKILL.md` — find tasks whose prerequisites are now all `done` and change their status from `backlog` to `todo`.
+4. **Unblock dependents**: Follow the "Prerequisite Unblock Logic" from `.claude/commands/mastermind/_taskfile.md` — find tasks whose prerequisites are now all `done` and change their status from `backlog` to `todo`.
 
 *Monotask mode:*
 ```bash

package/.claude/commands/mastermind/execute.md

@@ -1,4 +1,6 @@
-<!-- Execute a written implementation plan step by step with review checkpoints and finishing handoff. -->
+---
+description: Execute a written implementation plan step by step with review checkpoints and finishing handoff.
+---
 
 **First — extract repeat flags:** Follow REPEAT PREAMBLE from `mastermind-repeat/SKILL.md`.
 

package/.claude/commands/mastermind/finance.md

@@ -1,4 +1,6 @@
-<!-- Mastermind finance domain — invoicing, budget tracking, financial forecasting. Default mode: confirm. -->
+---
+description: "Mastermind finance domain — invoicing, budget tracking, financial forecasting. Default mode: confirm."
+---
 
 **First — extract repeat flags:** Follow the REPEAT PREAMBLE from `mastermind-repeat/SKILL.md`. Extracts `--repeat`, `--tillend`, `--maxruns`, `--wait`, `--rep`, `--loop` from `$ARGUMENTS` before all other parsing. If `is_continuation = true`, skip the empty-prompt check and intake below.
 

package/.claude/commands/mastermind/graph-status.md

@@ -1,4 +1,6 @@
-<!-- Single-line graph stats — nodes, edges, freshness, usage % -->
+---
+description: Single-line graph stats — nodes, edges, freshness, usage %
+---
 
 ```bash
 node "$CLAUDE_PROJECT_DIR/.claude/helpers/hook-handler.cjs" graph-status

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

@@ -1,4 +1,6 @@
-<!-- Mastermind commands reference — quick overview of all skills, CLI subcommands, and MCP tools available in this session -->
+---
+description: Mastermind commands reference — quick overview of all skills, CLI subcommands, and MCP tools available in this session
+---
 
 # Mastermind Help
 
@@ -18,23 +20,17 @@ Quick reference for all Mastermind skills and CLI commands available in this pro
 | `mastermind:swarm` | Swarm coordination reference — topologies, strategies, init patterns |
 | `mastermind:memory` | Memory CLI quick reference |
 
-## Org Runtime (v2 default)
+## Org Runtime
 
 | Command | Description |
 |-------|-------------|
-| `/mastermind:createorg` | Define and save an org (always v2-shaped) |
-| `/mastermind:runorg` | Start a saved org via the Org Runtime v2 daemon (`monomind org run`/`serve`) — auto-migrates v1-shaped configs first |
-| `/mastermind:stoporg` | Stop a running scheduled org loop |
+| `/mastermind:createorg` | Define and save an org |
+| `/mastermind:runorg` | Start a saved org via the Org Runtime daemon (`monomind org run`/`serve`) — converts legacy-format config files first |
+| `/mastermind:stoporg` | Stop a running org (`monomind org stop`) |
 | `/mastermind:orgstatus` | Detailed status for a single org |
 | `/mastermind:orgs` | List all saved orgs |
 
-### Legacy v1 (marker `LEGACY-ORG-V1` — reachable only under these explicit names)
-
-| Command | Description |
-|-------|-------------|
-| `/mastermind:runorgv1` | Legacy prompt-orchestrated org runner — superseded by `/mastermind:runorg` |
-| `/mastermind:approvev1` | Legacy approval queue for v1 orgs — v2 approvals arrive as dashboard question events instead |
-| `/mastermind:heartbeatv1` | Legacy manual agent wake-up for v1 orgs — v2 roles are live SDK sessions with no wake cycle |
+Pending tool approvals from a running org: `monomind org approvals <org>`, then `monomind org approve` / `monomind org deny` (or the dashboard's Human Input tab).
 
 ## Core CLI Commands
 
@@ -42,8 +38,8 @@ Quick reference for all Mastermind skills and CLI commands available in this pro
 # Initialize project
 npx monomind init --wizard
 
-# Start background daemon
-npx monomind daemon start
+# Start the orchestration system (there is no background daemon)
+npx monomind start
 
 # System diagnostics
 npx monomind doctor --fix
@@ -55,9 +51,9 @@ npx monomind agent status --id <agent-id>
 npx monomind agent stop --id <agent-id>
 
 # Swarm management
-npx monomind swarm init --topology hierarchical --max-agents 8 --strategy specialized
-npx monomind swarm status
-npx monomind swarm stop
+npx monomind monoswarm init --topology hierarchical --max-agents 8 --strategy specialized
+npx monomind monoswarm status
+npx monomind monoswarm stop
 
 # Memory operations
 npx monomind memory store --key "my-key" --value "my-value" --namespace patterns
@@ -65,9 +61,10 @@ npx monomind memory search --query "search terms"
 npx monomind memory list --namespace patterns
 npx monomind memory retrieve --key "my-key"
 
-# Workflow management
-npx monomind workflow run -t development --task "Build feature"
-npx monomind workflow list
+# Workflows (org starter templates — there is no workflow command)
+npx monomind org create feature --template dev-team --goal "Build feature"
+npx monomind org run feature --task "Build feature"
+npx monomind org list
 
 # Knowledge graph
 npx monomind monograph build

package/.claude/commands/mastermind/idea.md

@@ -1,4 +1,6 @@
-<!-- Mastermind idea domain — brainstorm products, features, pivots. Default mode: confirm. -->
+---
+description: "Mastermind idea domain — brainstorm products, features, pivots. Default mode: confirm."
+---
 
 **First — extract repeat flags:** Follow the REPEAT PREAMBLE from `mastermind-repeat/SKILL.md`. Extracts `--repeat`, `--tillend`, `--maxruns`, `--wait`, `--rep`, `--loop` from `$ARGUMENTS` before all other parsing. If `is_continuation = true`, skip the empty-prompt check and intake below.
 

package/.claude/commands/mastermind/ideate.md

@@ -1,4 +1,6 @@
-<!-- "Mastermind — Research ideas from a prompt, evaluate them with a PM lens, elaborate, and decompose into subtasks saved to docs/ideas/ (default) or monotask boards (--monotask flag)" -->
+---
+description: Mastermind — Research ideas from a prompt, evaluate them with a PM lens, elaborate, and decompose into subtasks saved to docs/ideas/ (default) or monotask boards (--monotask flag)
+---
 
 **First — extract repeat flags:** Follow the REPEAT PREAMBLE from `mastermind-repeat/SKILL.md`. Extracts `--repeat`, `--tillend`, `--maxruns`, `--wait`, `--rep`, `--loop` from `$ARGUMENTS` before all other parsing. If `is_continuation = true`, skip the empty-arguments check below.
 
@@ -103,7 +105,7 @@ After all agents complete:
 2. Deduplicate by title similarity (fuzzy match — drop ideas whose titles are >80% similar to an already-kept idea).
 3. Persist each unique idea:
 
-**File mode:** Append to `IDEA_FILE` using the idea section format from `mastermind-taskfile/SKILL.md`:
+**File mode:** Append to `IDEA_FILE` using the idea section format from `.claude/commands/mastermind/_taskfile.md`:
 ```markdown
 ### <Idea Title>
 > status: new

package/.claude/commands/mastermind/improve.md

@@ -1,4 +1,6 @@
-<!-- "Mastermind — Deeply analyze a component, research improvements online, and create improvement tasks saved to docs/improvements/ (default) or monotask boards (--monotask flag)" -->
+---
+description: Mastermind — Deeply analyze a component, research improvements online, and create improvement tasks saved to docs/improvements/ (default) or monotask boards (--monotask flag)
+---
 
 **First — extract repeat flags:** Follow the REPEAT PREAMBLE from `mastermind-repeat/SKILL.md`. Extracts `--repeat`, `--tillend`, `--maxruns`, `--wait`, `--rep`, `--loop` from `$ARGUMENTS` before all other parsing. If `is_continuation = true`, skip the empty-arguments check below.
 
@@ -175,7 +177,7 @@ The agent must synthesize the code analysis and online research into concrete im
 
 Persist each improvement:
 
-**File mode:** Append to `IMPROVE_FILE` using the improvement section format from `mastermind-taskfile/SKILL.md`:
+**File mode:** Append to `IMPROVE_FILE` using the improvement section format from `.claude/commands/mastermind/_taskfile.md`:
 ```markdown
 ### <Improvement Title>
 > status: discovered

package/.claude/commands/mastermind/loops.md

@@ -1,4 +1,6 @@
-<!-- List active loops — command, type, run count, HIL status -->
+---
+description: List active loops — command, type, run count, HIL status
+---
 
 ```bash
 node "$CLAUDE_PROJECT_DIR/.claude/helpers/hook-handler.cjs" loops-status

package/.claude/commands/mastermind/marketing.md

@@ -1,4 +1,6 @@
-<!-- Mastermind marketing domain — campaigns, copy, SEO, social media. Default mode: confirm. -->
+---
+description: "Mastermind marketing domain — campaigns, copy, SEO, social media. Default mode: confirm."
+---
 
 **First — extract repeat flags:** Follow the REPEAT PREAMBLE from `mastermind-repeat/SKILL.md`. Extracts `--repeat`, `--tillend`, `--maxruns`, `--wait`, `--rep`, `--loop` from `$ARGUMENTS` before all other parsing. If `is_continuation = true`, skip the empty-prompt check and intake below.
 

package/.claude/commands/mastermind/master.md

@@ -1,4 +1,6 @@
-<!-- Use when starting any conversation or receiving any user request — loads the brain, routes to the right mastermind skill, enforces anti-drift discipline, and spawns domain managers for complex multi-domain work. Single entry point for all mastermind capabilities. -->
+---
+description: Use when starting any conversation or receiving any user request — loads the brain, routes to the right mastermind skill, enforces anti-drift discipline, and spawns domain managers for complex multi-domain work. Single entry point for all mastermind capabilities.
+---
 
 <SUBAGENT-STOP>
 If you were dispatched as a subagent to execute a specific task, skip the MASTERMIND PROTOCOL section below and proceed directly to execution.
@@ -249,8 +251,7 @@ Describe your goal. Mastermind identifies the relevant domains, spawns specialis
 
 **Persistent agent orgs** — named teams that coordinate across sessions
 `/mastermind:createorg` — define an org: roles, hierarchy, goal
-`/mastermind:runorg` — start a saved org via the Org Runtime v2 daemon (auto-migrates v1 configs); legacy prompt-orchestrated path: `/mastermind:runorgv1`
-`/mastermind:approvev1` — review and action pending approval requests from running org agents (v1 orgs only — v2 approvals arrive in the dashboard Human Input tab)
+`/mastermind:runorg` — start a saved org via the Org Runtime daemon (converts legacy-format config files first); pending tool approvals: `monomind org approvals <org>` or the dashboard Human Input tab
 
 **Autonomous & advanced**
 `/mastermind:repeat` — wrap any mastermind command in a loop (`--tillend` supported)

package/.claude/commands/mastermind/memory.md

@@ -1,14 +1,16 @@
-<!-- LanceDB memory system — store, search, retrieve, list, delete, and manage cross-session persistent memory with vector embeddings -->
+---
+description: Memory system — store, search, retrieve, list, delete, and manage cross-session persistent memory in local SQLite with vector embeddings
+---
 
 # Monomind Memory System
 
-Persistent memory backed by LanceDB with pure-JS HNSW vector indexing for semantic search (O(log n) approximate nearest neighbor). Supports cross-session and cross-agent collaboration.
+Persistent memory in local SQLite (sql.js/WASM when no native driver is available) with on-device embeddings for semantic search. Above 5,000 entries (`MONOMIND_HNSW_THRESHOLD`) search switches to an HNSW approximate-nearest-neighbour index; below it, brute-force cosine is faster. Supports cross-session and cross-agent collaboration.
 
 ## Subcommands
 
 | Subcommand | Alias | Description |
 |---|---|---|
-| `init` | — | Initialize memory database (sql.js + LanceDB) |
+| `init` | — | Initialize the SQLite memory database |
 | `store` | — | Store a key/value entry |
 | `edit` | — | Edit an existing entry |
 | `retrieve` | `get` | Retrieve entry by key |
@@ -18,8 +20,6 @@ Persistent memory backed by LanceDB with pure-JS HNSW vector indexing for semant
 | `templates` | — | Show best-practice entry templates |
 | `stats` | — | Show memory statistics |
 | `configure` | `config` | Configure memory backend |
-| `cleanup` | — | Clean expired/stale entries |
-| `compress` | — | Compress and optimize storage |
 | `export` | — | Export memory to file |
 | `import` | — | Import memory from file |
 
@@ -27,11 +27,11 @@ Persistent memory backed by LanceDB with pure-JS HNSW vector indexing for semant
 
 ```bash
 npx monomind memory init
-npx monomind memory init --backend lancedb --verbose --verify
+npx monomind memory init --backend sqlite --verbose --verify
 npx monomind memory init --force  # Overwrite existing
 ```
 
-**Flags:** `--backend hybrid|sqlite|lancedb` (default: `hybrid`), `--path`, `--force`, `--verbose`, `--verify` (default: true), `--load-embeddings`
+**Flags:** `--backend hybrid|sqlite` (default: `hybrid`; `lancedb` is accepted as a legacy alias for SQLite), `--path`, `--force`, `--verbose`, `--verify` (default: true), `--load-embeddings`
 
 ## store — Store Data
 
@@ -132,40 +132,12 @@ Shows backend, total entries, storage size, oldest/newest entry.
 ## configure — Backend Settings
 
 ```bash
-npx monomind memory configure --backend lancedb
+npx monomind memory configure --backend sqlite
 npx monomind memory configure --backend hybrid --cache-size 512 --hnsw-m 16 --hnsw-ef 200
 ```
 
 **Flags:** `--backend/-b`, `--path`, `--cache-size`, `--hnsw-m`, `--hnsw-ef`
 
-## cleanup — Remove Stale Entries
-
-```bash
-# Preview without deleting
-npx monomind memory cleanup --dry-run
-
-# Delete entries older than 30 days
-npx monomind memory cleanup --older-than 30d
-
-# Remove expired TTL entries only
-npx monomind memory cleanup --expired-only
-
-# Clean specific namespace
-npx monomind memory cleanup --namespace temp --older-than 7d --force
-```
-
-**Flags:** `--dry-run/-d`, `--older-than/-o` (e.g., `7d`, `30d`), `--expired-only/-e`, `--namespace/-n`, `--force/-f`
-
-## compress — Optimize Storage
-
-```bash
-npx monomind memory compress
-npx monomind memory compress --quantize --bits 4  # 32x size reduction
-npx monomind memory compress --level max --target vectors
-```
-
-**Flags:** `--level fast|balanced|max` (default: `balanced`), `--target vectors|text|patterns|all`, `--quantize/-z`, `--bits 4|8|16`, `--rebuild-index/-r` (default: true)
-
 ## export / import
 
 ```bash

package/.claude/commands/mastermind/monoswarm.md

@@ -1,4 +1,6 @@
-<!-- Multi-agent swarm coordination — init, start, status, stop, scale, and coordinate agent teams -->
+---
+description: Multi-agent swarm coordination — init, start, status, stop, scale, and coordinate agent teams
+---
 
 # Monomind Swarm Coordination
 
@@ -141,7 +143,6 @@ These are real agent names (Task `subagent_type`). For a task-specific pick use
 ## See Also
 
 - `npx monomind agent spawn` — Spawn individual agents
-- `npx monomind hive-mind init` — Byzantine fault-tolerant consensus
 - `/mastermind` — Interactive swarm topology selection
 
 Documentation: https://github.com/monoes/monomind

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

@@ -1,4 +1,6 @@
-<!-- Export the Second Brain knowledge base as a portable OKF (Open Knowledge Format) bundle. -->
+---
+description: 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`)

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

@@ -1,4 +1,6 @@
-<!-- Import an OKF (Open Knowledge Format) bundle into the Second Brain knowledge base. -->
+---
+description: 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`)

package/.claude/commands/mastermind/ops.md

@@ -1,4 +1,6 @@
-<!-- Mastermind ops domain — workflow automation, reporting, process optimization. Default mode: auto. -->
+---
+description: "Mastermind ops domain — workflow automation, reporting, process optimization. Default mode: auto."
+---
 
 **First — extract repeat flags:** Follow the REPEAT PREAMBLE from `mastermind-repeat/SKILL.md`. Extracts `--repeat`, `--tillend`, `--maxruns`, `--wait`, `--rep`, `--loop` from `$ARGUMENTS` before all other parsing. If `is_continuation = true`, skip the empty-prompt check and intake below.
 

package/.claude/commands/mastermind/orgs.md

@@ -1,4 +1,6 @@
-<!-- List all saved orgs with their status, schedule interval, and last/next run times. Shows stopped/active/paused state for scheduled orgs. -->
+---
+description: List all saved orgs with their runtime status, schedule, and last run time. Flags crashed runs and legacy-format config files.
+---
 
 **If $ARGUMENTS is empty:** Execute the listing below directly.
 

package/.claude/commands/mastermind/orgstatus.md

@@ -1,4 +1,6 @@
-<!-- Show detailed status for a single org — lifecycle state, schedule, last/next run, recent activity, and roles. For scheduled orgs shows loop health. -->
+---
+description: Show detailed status for a single org — runtime state, schedule, config health, pending approvals, recent activity, and roles.
+---
 
 **If $ARGUMENTS is empty:** Output the following and wait.
 

package/.claude/commands/mastermind/plan.md

@@ -1,4 +1,6 @@
-<!-- Write a comprehensive implementation plan from a spec or requirements. Saves to docs/mastermind/plans/. Default mode: confirm. -->
+---
+description: "Write a comprehensive implementation plan from a spec or requirements. Saves to docs/mastermind/plans/. Default mode: confirm."
+---
 
 **First — extract repeat flags:** Follow the REPEAT PREAMBLE from `mastermind-repeat/SKILL.md`. Extracts `--repeat`, `--tillend`, `--maxruns`, `--wait`, `--rep`, `--loop` from `$ARGUMENTS` before all other parsing. If `is_continuation = true`, skip the empty-prompt check and intake below.
 

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

@@ -1,4 +1,6 @@
-<!-- Use when receiving code review feedback to evaluate and implement it with technical rigor — verifies before implementing, clarifies unclear items first, applies reasoned pushback when warranted -->
+---
+description: Use when receiving code review feedback to evaluate and implement it with technical rigor — verifies before implementing, clarifies unclear items first, applies reasoned pushback when warranted
+---
 
 **First — extract repeat flags:** Follow REPEAT PREAMBLE from `mastermind-repeat/SKILL.md`.
 

package/.claude/commands/mastermind/release.md

@@ -1,4 +1,6 @@
-<!-- Mastermind release domain — versioning, changelog, deployment. Default mode: auto. -->
+---
+description: "Mastermind release domain — versioning, changelog, deployment. Default mode: auto."
+---
 
 **First — extract repeat flags:** Follow the REPEAT PREAMBLE from `mastermind-repeat/SKILL.md`. Extracts `--repeat`, `--tillend`, `--maxruns`, `--wait`, `--rep`, `--loop` from `$ARGUMENTS` before all other parsing. If `is_continuation = true`, skip the empty-prompt check and intake below.
 

package/.claude/commands/mastermind/repeat.md

@@ -1,4 +1,6 @@
-<!-- "Monomind — Repeat any prompt or slash command on a schedule — default 15 min interval, 10 repetitions. This is the universal loop wrapper for all commands." -->
+---
+description: Monomind — Repeat any prompt or slash command on a schedule — default 15 min interval, 10 repetitions. This is the universal loop wrapper for all commands.
+---
 
 ## Argument Parsing
 

package/.claude/commands/mastermind/research.md

@@ -1,4 +1,6 @@
-<!-- Mastermind research domain — market research, competitor analysis, user research, trend scanning. Default mode: auto. -->
+---
+description: "Mastermind research domain — market research, competitor analysis, user research, trend scanning. Default mode: auto."
+---
 
 **First — extract repeat flags:** Follow the REPEAT PREAMBLE from `mastermind-repeat/SKILL.md`. Extracts `--repeat`, `--tillend`, `--maxruns`, `--wait`, `--rep`, `--loop` from `$ARGUMENTS` before all other parsing. If `is_continuation = true`, skip the empty-prompt check and intake below.
 

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

@@ -1,4 +1,6 @@
-<!-- Mastermind review domain — code review, security audit, content and strategy review. Trigger on "review this session's work," "full review of this session," or "review this worktree" — add --tillend for exhaustive find-fix-verify looping. Default mode: auto. -->
+---
+description: "Mastermind review domain — code review, security audit, content and strategy review. Trigger on \"review this session's work,\" \"full review of this session,\" or \"review this worktree\" — add --tillend for exhaustive find-fix-verify looping. Default mode: auto."
+---
 
 **First — extract repeat flags:** Follow the REPEAT PREAMBLE from `mastermind-repeat/SKILL.md`. Extracts `--repeat`, `--tillend`, `--maxruns`, `--wait`, `--rep`, `--loop` from `$ARGUMENTS` before all other parsing. If `is_continuation = true`, skip the empty-prompt check and intake below.
 

package/.claude/commands/mastermind/runorg.md

@@ -1,4 +1,6 @@
-<!-- Start a saved org via the Org Runtime v2 daemon (monomind org run/serve). Validates the config, auto-migrates v1-shaped configs, starts the daemon, and confirms liveness. The legacy prompt-orchestrated path lives at /mastermind:runorgv1. -->
+---
+description: Start a saved org via the Org Runtime daemon (monomind org run/serve). Validates the config, converts legacy-format config files, starts the daemon, and confirms liveness.
+---
 
 **If $ARGUMENTS is empty:** Output the following and wait.
 
@@ -6,7 +8,7 @@
 
 **MASTERMIND: RUN ORG**
 
-Running an org starts it through the Org Runtime v2 daemon. Every role becomes
+Running an org starts it through the Org Runtime daemon. Every role becomes
 a live SDK session; the daemon forwards dashboard events itself — no boss
 agent, no monotask board, no manual curl emissions.
 

package/.claude/commands/mastermind/sales.md

@@ -1,4 +1,6 @@
-<!-- Mastermind sales domain — outreach sequences, proposals, pipeline management. Default mode: confirm. -->
+---
+description: "Mastermind sales domain — outreach sequences, proposals, pipeline management. Default mode: confirm."
+---
 
 **First — extract repeat flags:** Follow the REPEAT PREAMBLE from `mastermind-repeat/SKILL.md`. Extracts `--repeat`, `--tillend`, `--maxruns`, `--wait`, `--rep`, `--loop` from `$ARGUMENTS` before all other parsing. If `is_continuation = true`, skip the empty-prompt check and intake below.
 

package/.claude/commands/mastermind/skill-builder.md

@@ -1,4 +1,6 @@
-<!-- Use when creating, editing, or verifying mastermind skills — guides the full TDD-for-docs cycle from baseline test through deployment -->
+---
+description: Use when creating, editing, or verifying mastermind skills — guides the full TDD-for-docs cycle from baseline test through deployment
+---
 
 **First — extract repeat flags:** Follow REPEAT PREAMBLE from `mastermind-repeat/SKILL.md`.
 

package/.claude/commands/mastermind/specialagents.md

@@ -1,4 +1,6 @@
-<!-- Activate a specialist agent persona — browse by category, activate by slug, or auto-select based on conversation context -->
+---
+description: Activate a specialist agent persona — browse by category, activate by slug, or auto-select based on conversation context
+---
 
 Activate a specialist agent persona. Three modes:
 

package/.claude/commands/mastermind/stoporg.md

@@ -1,4 +1,6 @@
-<!-- Stop a running scheduled org loop. Sets status to "stopped" — the next scheduled wakeup reads the status, skips all work, and does not reschedule. Loop dies within one interval. -->
+---
+description: Stop a running org. Wraps `monomind org stop`, which writes the stop file the org daemon polls — the daemon exits within about 2s.
+---
 
 **If $ARGUMENTS is empty:** Output the following and wait.
 
@@ -6,7 +8,7 @@
 
 **MASTERMIND: STOP ORG**
 
-Stops a scheduled org loop cleanly. The org's `status` is set to `"stopped"` — the next scheduled wakeup will read the status, skip all work, and not reschedule itself. The loop is guaranteed to die within one interval (no orphaned wakeups).
+Stops a running org cleanly. Runs `monomind org stop <name>`, which writes `.monomind/orgs/<name>/stop`; the org daemon polls for that file and exits within about 2 seconds.
 
 **Usage:**
 
@@ -23,16 +25,12 @@ Stops a scheduled org loop cleanly. The org's `status` is set to `"stopped"` —
 
 **Lifecycle:**
 ```
-stopped  →  (runorg)   →  active
-active   →  (stoporg)  →  stopped
-active   →  (HIL)      →  paused    (set manually in .monomind/orgs/<name>.json)
-paused   →  (set active) →  active  (resume by setting status back to "active" in the JSON)
+stopped  →  (runorg / monomind org run)  →  running
+running  →  (stoporg / monomind org stop) →  stopped
+running  →  (monomind org pause)         →  paused
+paused   →  (monomind org resume)        →  running
 ```
 
-**Note:** v2 orgs (the default) are stopped via `monomind org stop <name>` — this
-command handles both: it routes v2 orgs to the CLI and legacy `.loop` orgs
-through the v1 status-flip path.
-
 Your orgs (with live runtime status):
 
 ```bash
@@ -48,7 +46,7 @@ npx -y monomind@latest org list 2>/dev/null || echo "(none — run /mastermind:c
 Parse `$ARGUMENTS` for:
 - `--org <name>` → org_name = <name>
 
-If `--org` is not provided, list orgs with schedules and ask which to stop.
+If `--org` is not provided, list orgs and ask which to stop.
 
 Verify the org file exists:
 ```bash

package/.claude/commands/mastermind/techport.md

@@ -1,4 +1,6 @@
-<!-- Tech Port — deep-analyzes a foreign project folder and recommends porting valuable features, patterns, or infrastructure into the current monomind base project. -->
+---
+description: Tech Port — deep-analyzes a foreign project folder and recommends porting valuable features, patterns, or infrastructure into the current monomind base project.
+---
 
 **First — extract repeat flags:** Follow the REPEAT PREAMBLE from `mastermind-repeat/SKILL.md`. Extracts `--repeat`, `--tillend`, `--maxruns`, `--wait`, `--rep`, `--loop` from `$ARGUMENTS` before all other parsing. If `is_continuation = true`, skip the empty-prompt check below.
 

package/.claude/commands/mastermind/topology.md

@@ -58,10 +58,11 @@ Based on the task or user choice, pick ONE mode and output EXACTLY this structur
 **Launch command:**
 ```bash
 # Swarm:
-npx monomind swarm init --topology <topology> --max-agents <N> --strategy <strategy>
+npx monomind monoswarm 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>
+# OR Hive-Mind: the same command without --strategy. There is no --consensus
+# flag — state the consensus protocol in the coordinator's Task prompt.
+npx monomind monoswarm init --topology <topology> --max-agents <N>
 ```
 
 **Agent team:**

package/.claude/commands/mastermind/understand.md

@@ -1,4 +1,6 @@
-<!-- "Monomind — Run semantic enrichment on the current project's monograph knowledge graph. Uses the active Claude Code session for LLM work — no API key needed." -->
+---
+description: Monomind — Run semantic enrichment on the current project's monograph knowledge graph. Uses the active Claude Code session for LLM work — no API key needed.
+---
 
 # /mastermind:understand — Semantic Enrichment
 

package/.claude/commands/mastermind/worktree.md

@@ -1,4 +1,6 @@
-<!-- Use when starting feature work that needs isolation from the current workspace or before executing implementation plans — sets up an isolated git worktree -->
+---
+description: Use when starting feature work that needs isolation from the current workspace or before executing implementation plans — sets up an isolated git worktree
+---
 
 **First — extract repeat flags:** Follow REPEAT PREAMBLE from `mastermind-repeat/SKILL.md`.
 

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

@@ -1,5 +1,6 @@
 ---
 name: memory:memory-search
+description: Search stored memory using semantic, keyword, or hybrid search.
 ---
 
 # memory search

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

@@ -37,7 +37,7 @@ npx monomind status agents
 npx monomind agent metrics --period 7d
 
 # Swarm status
-npx monomind swarm status
+npx monomind monoswarm status
 ```
 
 ## Files

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

@@ -1,5 +1,6 @@
 ---
 name: monitoring:agent-metrics
+description: Show agent performance metrics — tasks completed, success rate, and memory vectors by agent type.
 ---
 
 # agent metrics

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

@@ -1,5 +1,6 @@
 ---
 name: monitoring:agents
+description: Show detailed agent status — ID, type, current task, uptime, and success rate for all running agents.
 ---
 
 # status agents

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

@@ -1,5 +1,6 @@
 ---
 name: monitoring:status
+description: Show system status — swarm health, agents, tasks, memory, and MCP server.
 ---
 
 # status

package/.claude/commands/monoswarm/README.md

@@ -50,9 +50,9 @@ monoswarm_shutdown        Clear run workers from the agent store, reset run stat
 
 ```bash
 # Initialize and start a run via CLI
-npx monomind swarm init --topology hierarchical --max-agents 8
-npx monomind swarm start "Build REST API" --strategy development
-npx monomind swarm status
+npx monomind monoswarm init --topology hierarchical --max-agents 8
+npx monomind monoswarm start "Build REST API" --strategy development
+npx monomind monoswarm status
 ```
 
 For vote-based decisions, use the MCP tools directly — see

package/.claude/commands/monoswarm/analysis.md

@@ -38,8 +38,8 @@ mcp__monomind__coordination_orchestrate({
 
 ```bash
 # CLI equivalent
-npx monomind swarm init --topology mesh --max-agents 6
-npx monomind swarm start "analyze system performance" --strategy analysis --parallel
+npx monomind monoswarm init --topology mesh --max-agents 6
+npx monomind monoswarm start "analyze system performance" --strategy analysis --parallel
 ```
 
 ## Agent Roles

package/.claude/commands/monoswarm/consensus.md

@@ -1,5 +1,6 @@
 ---
 name: monoswarm:consensus
+description: Propose or vote on a threshold-based decision — vote-count bookkeeping over one JSON state file.
 ---
 
 # monoswarm vote