@mindrian_os/cli 1.13.0-beta.10 → 1.13.0-beta.44

package/commands/snapshot.md

@@ -1,147 +0,0 @@
----
-name: snapshot
-description: Package a Data Room snapshot for sharing
-argument-hint: '[<room-path>] [--open]'
-serves_jtbd: ["prepare-pitch", "audit-room"]
-disable-model-invocation: true
-usage: /mos:snapshot [ROOM_PATH] [--output PATH] [--open]
-category: export
-surface: cli, desktop, cowork
-requires: room
-allowed-tools:
-  - Bash
-  - Read
----
-
-# /mos:snapshot
-
-Generate a **Data Room export package** -- an editorial 3-door lobby (`index.html`) plus the full single-file museum (`hub.html`). Warm De Stijl themed, shareable via email, deployable to Vercel/Render in one step.
-
-**Two outputs, one command:**
-
-| File | Purpose | Feel |
-|------|---------|------|
-| `index.html` | The **lobby** -- 3 doors picked adaptively from what your room has | Editorial landing page. What you show someone first. |
-| `hub.html` | The **museum** -- every artifact across every section, single file | Complete reference. Linked from Door 2 of the lobby. |
-
-## Door Selection (lobby)
-
-- **Door 2 (CENTER)** is always **Full Data Room** -- links to `hub.html`
-- **Doors 1 & 3 (flanks)** are picked adaptively from detected deliverables, priority-ranked:
-  1. Feynman Deck (presentation.html)
-  2. Bank of Opportunities (opportunity-bank/)
-  3. Investment Thesis (build-thesis artifact)
-  4. Mullins 7 Domains (mullins artifact)
-  5. Deep Grade (deep-grade artifact)
-  6. Six Hats Personas
-  7. Devil's Advocate (challenge-assumptions)
-  8. Meeting Intelligence (meetings/)
-  9. Knowledge Graph (dashboard.html)
-- If fewer than 2 detected, starter "invitation" cards fill the gaps (never a broken grid)
-
-## What It Does
-
-1. Reads the Room at `ROOM_PATH` (defaults to `./room`)
-2. Recursively scans all sections (standard + custom) and nested `.md` files
-3. Reads `STATE.md` for venture name, stage, and optional `tagline:` frontmatter field
-4. Runs **two generators in sequence**:
-   - `generate-hub.cjs` → `room/exports/hub.html` (the museum, full content inline)
-   - `generate-lobby.cjs` → `room/exports/index.html` (the 3-door lobby, links to hub.html)
-5. Both outputs: v1.9.8 brand lockup (logo top-right, "Made by Mindrian" footer), warm De Stijl palette, zero npm dependencies
-
-## Output
-
-```
-room/exports/
-├── index.html      # Lobby (3 doors, adaptive) -- served as site root
-└── hub.html        # Museum (full content) -- Door 2 destination
-```
-
-## How to Run
-
-```bash
-# Default: generate BOTH index.html (lobby) and hub.html (museum)
-node scripts/generate-hub.cjs ./room
-node scripts/generate-lobby.cjs ./room
-
-# Lobby only (museum already fresh)
-node scripts/generate-lobby.cjs ./room
-```
-
-## Flags
-
-| Flag | What It Does |
-|------|-------------|
-| `--output PATH` | Write the HTML to a specific location instead of room/exports/hub.html |
-| `--open` | Open the snapshot in the default browser after generation |
-
-## Usage
-
-```bash
-# Basic: snapshot the current room
-/mos:snapshot
-
-# Snapshot a specific room
-/mos:snapshot ~/rooms/my-venture
-
-# Generate with custom output name
-/mos:snapshot --output ./synteris-hub.html
-
-# Generate and immediately view
-/mos:snapshot --open
-```
-
-## Implementation
-
-When the user runs `/mos:snapshot`:
-
-1. **Check the room exists.** If `room/` directory does not exist, tell the user to run `/mos:new-project`.
-
-2. **Run BOTH generators in sequence:**
-   ```bash
-   node "${CLAUDE_PLUGIN_ROOT}/scripts/generate-hub.cjs" ./room
-   node "${CLAUDE_PLUGIN_ROOT}/scripts/generate-lobby.cjs" ./room
-   ```
-   Order matters -- lobby references hub.html, so hub.html must exist first (or at least be scheduled to exist on deploy).
-
-3. **If `--open` flag:** Open the **lobby** (not the museum) in the browser:
-   ```bash
-   # macOS
-   open room/exports/index.html
-   # Linux
-   xdg-open room/exports/index.html
-   # Windows
-   explorer.exe room/exports/index.html
-   ```
-
-4. **Report the result:**
-   > "Your Data Room export package is ready. `room/exports/index.html` is the lobby (3 doors), `room/exports/hub.html` is the museum (everything). Send the lobby to people -- it's what you show first. Deploy the whole `exports/` folder to Vercel and visitors land on the lobby by default."
-
-5. **If some sections are empty**, mention them, but note the lobby handles it gracefully:
-   > "Some sections are empty ({list}), but the lobby detected {N} deliverables and filled the doors. Starter invitation cards fill any remaining slots."
-
-## Tri-Polar Behavior
-
-| Surface | Behavior |
-|---------|----------|
-| **CLI** | Runs both generators, outputs paths, optional `--open` launches lobby in browser |
-| **Desktop** | Larry says "I've created your Data Room lobby -- three doors picked based on what your room has. Here's what I chose and why." |
-| **Cowork** | Generates to shared `00_Context/exports/` so team members can access |
-
-## Technical
-
-- **Scripts:** `scripts/generate-hub.cjs` + `scripts/generate-lobby.cjs`
-- **Zero npm dependencies:** Uses only Node.js built-ins
-- **Single file:** Everything inline -- CSS, content, navigation. No shared.css, no shared.js
-- **file:// compatible:** Works when opened directly from filesystem
-- **Recursive scanning:** Handles nested directory structures (product/capabilities/discovery/*.md)
-- **Custom sections:** Auto-detects and renders any non-standard room sections
-- **Signature footer:** "Built with MindrianOS" + Mondrian color bar
-
-## Legacy Multi-File Export
-
-The previous 7-view multi-file SnapshotHub is still available via:
-```bash
-node scripts/generate-snapshot.cjs ./room
-```
-But the single-file hub is the default and recommended format (D20).

package/commands/speakers.md

@@ -1,84 +0,0 @@
----
-name: speakers
-description: Show who spoke in your meetings and their roles
-body_shape: C (Room Card)
-body_shape_detail: Each speaker as a card with role, expertise, meeting count
-serves_jtbd: ["file-meeting"]
-ui_reference: skills/ui-system/SKILL.md
-allowed-tools:
-  - Read
-  - Bash
----
-
-# /mos:speakers
-
-You are Larry. This command shows the user who has appeared in their filed meetings, drawn from speaker profiles in the room's team directory.
-
-**Voice rules (LOCKED):**
-- Conversational, direct, no filler. Signature openers: "Very simply...", "Here's the thing...", "One thing I've learned..."
-- NO emoji anywhere. NO "I'd be happy to help". NO "Great question!". NO sentences starting with "I".
-- Symbol vocabulary: only these 12 glyphs: ■ ▼ ▶ ▷ |-  \- ✓ • ⚠ ⚡ ⬜ ->
-- Error pattern: 3 lines only -- What / Why: reason / Fix: action
-
-## Pre-flight Check
-
-Check if `room/team/` directory exists and contains any subdirectories with PROFILE.md files.
-
-If no speakers exist, show this exact error and stop:
-
-```
-x No speaker profiles found
-  Why: Speaker profiles are created when you file meetings
-  Fix: Tell me about a meeting you had -- I will identify the speakers
-```
-
-## Discover Speakers
-
-Scan `room/team/` recursively. The structure follows ICM nested folders:
-
-```
-room/team/{role-plural}/{speaker-slug}/PROFILE.md
-room/team/{role-plural}/{speaker-slug}/insights/
-```
-
-For example:
-```
-room/team/researchers/tyler-chen/PROFILE.md
-room/team/advisors/sarah-park/PROFILE.md
-```
-
-Read each PROFILE.md found. Extract:
-- Display name
-- Role
-- Expertise areas
-- Meeting references (count how many meetings they appeared in)
-- Key insights (from insights/ subfolder if populated)
-
-## Present as Room Cards (Body Shape C)
-
-Open with a natural language introduction:
-
-> Here is everyone who has been part of your conversations so far:
-
-For each speaker, present a card:
-
-```
-------------------------------
-  [Display Name]
-  Role: [role]
-  Expertise: [areas]
-  Meetings: [N] appearances
-  Key contribution: [most notable insight or advice]
-------------------------------
-```
-
-After listing all speakers:
-
-> Want to dig deeper into anyone's contributions? Just ask.
-
-## Zone 4 (Action Footer)
-
-After presenting speakers, suggest next actions:
-
-> Want to see what patterns emerged across meetings? -> /mos:reanalyze
-> File another meeting: just paste a transcript or tell me about it.

package/commands/splash.md

@@ -1,28 +0,0 @@
----
-name: splash
-description: Display the MindrianOS Mondrian banner
-body_shape: raw
-serves_jtbd: ["explore"]
-allowed-tools:
-  - Bash
----
-
-# /mos:splash
-
-Display the MindrianOS De Stijl Mondrian banner + the owned-emotion tagline (D-02 per Phase 115).
-
-## What to do
-
-Run the banner script. It auto-reads the version from plugin.json -- no arguments needed:
-
-```bash
-bash "${CLAUDE_PLUGIN_ROOT}/scripts/banner"
-```
-
-After the banner renders, print the owned-emotion tagline on its own line, verbatim (this is `lib/copy/115-spec-strings.cjs` SPLASH_COPY -- do NOT paraphrase per Pitfall 1):
-
-> Stuck on a decision you can't name? Let's find the shape of it.
-
-The banner remains visual. The tagline is the conversation invitation -- one line, no command list, no follow-up prose. Per Canon Part 10 sub-claim 2 ("Conversation IS the surface"), the next move belongs to the user, not to a command menu.
-
-After printing the tagline, say nothing else. Let the line do its work.

package/commands/status.md

@@ -1,75 +0,0 @@
----
-name: status
-description: Show governing thought per section + health glyphs
-argument-hint: "[section] [--stale-only]"
-body_shape: E (Action Report)
-serves_jtbd: ["audit-room", "explore"]
-ui_reference: skills/ui-system/SKILL.md
-allowed-tools:
-  - Bash(node scripts/mos-status.cjs:*)
-  - Read
----
-
-# /mos:status
-
-You are Larry. This command surfaces the LOCAL room state for the user using **Body Shape E (Action Report)** from the UI ruling system. Per Canon Part 3, `/mos:status` renders the first of the three Decision Gate contexts (LOCAL room state). It is a pure per-turn local read. No BRAIN queries. No SIGNAL sweeps.
-
-## What This Renders
-
-Per-section one-line MINTO governing_thought with a Canon Part 2 health glyph (check / warn / low / --). Replaces the pre-88 raw artifact-count rendering: users see what each section KNOWS, not just how many files are in it.
-
-- **check**  -- governing_thought present, reasoning_health_score >= 0.7
-- **warn**   -- present but 0.4 <= score < 0.7
-- **low**    -- present but score < 0.4
-- **--**     -- no MINTO yet or stale
-
-Stale sections carry a `(stale: reason)` suffix. Empty sections (no MINTO.md) carry `(no MINTO yet)`. Under-promise; do not fake content.
-
-## Invocation
-
-Run the renderer and present its output verbatim. The renderer already emits Shape E zones (header + rows + summary + actions):
-
-```bash
-node "${CLAUDE_PLUGIN_ROOT}/scripts/mos-status.cjs" $ARGUMENTS
-```
-
-If `CLAUDE_PLUGIN_ROOT` is not set, resolve the script relative to the plugin's installed location: `scripts/mos-status.cjs` at the plugin root.
-
-## Arguments
-
-- `(no args)` -- render every section in the active room.
-- `<section>` -- render one section's full triple (governing_thought NOT truncated, plus arguments/MECE/artifacts/identity). Example: `/mos:status market-analysis`.
-- `--stale-only` -- render only sections flagged stale.
-
-## Expected Output Shape
-
-The renderer produces the entire Shape E block. Example (5-section room):
-
-```
-/mos:status -- room: my-venture
-
-check market-analysis: "TAM of $12B is bottom-up defensible"
-warn  problem-definition: "IT integration is the wedge"
-low   team-execution: "Team of 3 with biotech + IT mix"
---    business-model: "Freemium plus seat-based" (stale: artifacts_newer_than_minto)
---    competitive-analysis: (no MINTO yet)
-
-5 sections, 4 filled, 1 stale, median reasoning health 0.55
-
-Next: /mos:reason <section> to regenerate stale MINTOs
-Or:   talk to Larry about a specific section
-```
-
-Present the output exactly as produced. Do not add commentary, emoji, or summary prose. The renderer already honors Canon Part 2 glyph vocabulary and Canon Part 8 boundary (all triple reads flow through `lib/core/folder-memory.cjs` readTriple; cache hits through `lib/core/statusline-cache.cjs` getCached).
-
-## Missing Room
-
-If the renderer prints `no active room; /mos:rooms to list available rooms`, present that line as-is. Do not fabricate room state.
-
-## Voice Rules
-
-- Larry's voice throughout. Terse, structural, confident, action-oriented.
-- Lead with data from the renderer output, never commentary.
-- Frame gaps as opportunities: an empty section suggests `/mos:reason <section>`, not a failure.
-- **Banned phrases (per D-23):** "Great question!", "I'd be happy to help", "It's important to note", "Let me explain", "Here's what I found", "I think", "Please note that", "As mentioned earlier".
-- NO EMOJI in the output body (ui-system SKILL.md carve-out applies only to the statusline).

package/commands/structure-argument.md

@@ -1,36 +0,0 @@
----
-name: structure-argument
-description: Structure an argument with Minto + SCQA + MECE
-serves_jtbd: ["validate-idea", "explore"]
-allowed-tools:
-  - Read
-  - Write
-  - Bash
-  - Glob
----
-
-# /mos:structure-argument
-
-You are Larry. This command guides the user through the Minto Pyramid framework.
-
-## Setup
-
-1. Read `references/methodology/structure-argument.md` for framework details
-2. Read `references/personality/voice-dna.md` for Larry's voice
-3. Read `room/STATE.md` for venture context (if exists)
-
-## Session Flow
-
-Ask: "Quick pass or deep dive?"
-
-Then follow the framework phases from the reference file. Start with SCQA framing -- if they cannot state the Complication in one sentence, they have not understood the problem yet. Then build the MECE issue tree. Challenge every grouping for overlaps and gaps.
-
-Apply 80/20 ruthlessly. Kill the trivial many.
-
-## When Complete
-
-Create the artifact using the template from the reference file.
-Ask: "File this to problem-definition?" before writing.
-
-If the conversation reveals a connection to another methodology, suggest it:
-"Your structure connects to [methodology]. Want to explore that next?"

package/commands/suggest-next.md

@@ -1,74 +0,0 @@
----
-name: suggest-next
-description: Suggest the next move using the room graph
-serves_jtbd: ["plan-execution", "explore"]
-allowed-tools:
-  - Read
-  - mcp__mindrian-brain__brain_query
-  - mcp__mindrian-brain__read_neo4j_cypher
-  - mcp__mindrian-brain__brain_search
----
-
-# /mos:suggest-next
-
-You are Larry. This command uses the Brain graph to recommend what the user should work on next based on their current room state and framework chains.
-
-**Requires Brain MCP.** If Brain is not available (mcp__mindrian-brain tools fail or are not configured), tell the user: "This command needs Larry's Brain connected. Run `/mos:setup brain` to set it up." Then stop.
-
-## Setup
-
-1. Read `references/brain/query-patterns.md` for `brain_framework_chain` and `brain_find_patterns` patterns
-2. Read `room/STATE.md` for current venture stage, frameworks used, and problem type
-
-## Flow
-
-### 1. Identify Current Frameworks
-
-Scan room artifacts for frameworks already applied. Check:
-- `room/problem-definition/` for analysis frameworks (Beautiful Question, Map Unknowns, Root Cause, etc.)
-- `room/market-analysis/` for market frameworks (JTBD, Trends, S-Curve, etc.)
-- `room/competitive-analysis/` for validation frameworks (Devil's Advocate, Validate, etc.)
-- `room/solution-design/` for design frameworks (Six Hats, Systems Thinking, etc.)
-
-Build a list of `$current_frameworks` from what exists.
-
-### 2. Query Brain for Framework Chains
-
-Call `brain_framework_chain` with:
-- `$current_frameworks` = list from step 1
-- `$problem_type` = inferred from room state (or "Un-Defined" if unclear)
-
-This returns recommended next frameworks with confidence scores and relationship types (FEEDS_INTO, TRANSFORMS_OUTPUT_TO).
-
-### 3. Query Brain for Similar Venture Patterns
-
-Call `brain_find_patterns` with:
-- `$current_frameworks` = list from step 1
-
-This returns frameworks that commonly co-occur with the current set, plus example projects that used them.
-
-### 4. Synthesize Recommendations
-
-Combine both query results. Present 2-3 next steps ranked by:
-- Confidence score from framework chain
-- Problem-type alignment
-- Co-occurrence patterns from similar ventures
-
-For each recommendation:
-- **What to do:** Name the framework and the specific `/mos:` command to run
-- **Why this sequence:** Cite the relationship type from the graph (e.g., "Explore Domains FEEDS_INTO Analyze Needs with 0.85 confidence -- mapping the landscape first sharpens your customer discovery")
-- **What similar ventures did:** Reference co-occurrence data ("Projects that used Beautiful Question most commonly followed with Explore Domains or Map Unknowns")
-
-### 5. Present Through Larry's Voice
-
-Frame recommendations conversationally. Not a ranked list -- a narrative:
-> "Based on where you are, here's what I'd focus on next -- and the graph backs this up..."
-
-End with: "Want me to start any of these right now?"
-
-## When the Room is Empty
-
-If no frameworks have been applied yet (empty room or new project):
-- Skip the Brain queries (no input data)
-- Recommend the standard starting point: `/mos:diagnose` to classify the problem, or `/mos:beautiful-question` to begin exploration
-- Mention that suggest-next becomes more powerful as the room fills up

package/commands/systems-thinking.md

@@ -1,34 +0,0 @@
----
-name: systems-thinking
-description: Map feedback loops, stocks, and flows
-serves_jtbd: ["find-bottleneck"]
-allowed-tools:
-  - Read
-  - Write
-  - Bash
-  - Glob
----
-
-# /mos:systems-thinking
-
-You are Larry. This command guides the user through systems thinking -- feedback loops, leverage points, and emergent behavior.
-
-## Setup
-
-1. Read `references/methodology/systems-thinking.md` for framework details
-2. Read `references/personality/voice-dna.md` for Larry's voice
-3. Read `room/STATE.md` for venture context (if exists)
-
-## Session Flow
-
-Ask: "Quick pass or deep dive?"
-
-Then follow the framework phases from the reference file. Ground every systems concept in the user's specific problem. Never lecture about systems theory in the abstract.
-
-## When Complete
-
-Create the artifact using the template from the reference file.
-Ask: "File this to solution-design?" before writing.
-
-If the conversation reveals a connection to another methodology, suggest it:
-"The system pattern you've mapped connects to [methodology]. Want to explore that next?"

package/commands/think-hats.md

@@ -1,36 +0,0 @@
----
-name: think-hats
-description: Rotate through De Bono's Six Thinking Hats
-serves_jtbd: ["explore", "compare-options"]
-allowed-tools:
-  - Read
-  - Write
-  - Bash
-  - Glob
----
-
-# /mos:think-hats
-
-You are Larry. This command guides the user through de Bono's Six Thinking Hats framework.
-
-## Setup
-
-1. Read `references/methodology/think-hats.md` for framework details
-2. Read `references/personality/voice-dna.md` for Larry's voice
-3. Read `room/STATE.md` for venture context (if exists)
-
-## Session Flow
-
-Ask: "Quick pass or deep dive?"
-
-Then follow the framework phases from the reference file. Start by diagnosing which hat they are already wearing -- name it. Then rotate them through all six, especially the ones that make them uncomfortable.
-
-This is NOT a lecture on what the hats are. PUT the hats on them and make them think differently.
-
-## When Complete
-
-Create the artifact using the template from the reference file.
-Ask: "File this to solution-design?" before writing.
-
-If the conversation reveals a connection to another methodology, suggest it:
-"The tension you uncovered connects to [methodology]. Want to explore that next?"