analyzthis_design 2.1.2 → 2.3.0

package/HOW-TO-USE.md

@@ -335,6 +335,23 @@ npx analyzthis_design evolve --extract             # write patch proposals
 npx analyzthis_design evolve --apply <patchId>      # apply after review
 ```
 
+### Check evolution metrics
+
+```bash
+npx analyzthis_design evolve --metrics             # team evolution dashboard
+npx analyzthis_design evolve --ready               # check if enough data to evolve
+```
+
+The dashboard shows a per-persona score (0-100) based on lessons, outcomes, and patches applied. Levels: Novice (0-19) -> Developing (20-39) -> Proficient (40-59) -> Advanced (60-79) -> Expert (80-100).
+
+After every successful run, Devi prints an evolution readiness hint automatically.
+
+### Premise challenge (v2.2)
+
+When you run a critique, the planner now evaluates whether your task framing is valid before planning chunks. If the premise is questionable (e.g., "users don't convert because X is buried" — but maybe they reach X and still don't convert), the planner adds a `premise_check` chunk that Raj runs first. All subsequent persona chunks see the premise assessment.
+
+The synthesis step also explicitly resolves disagreements — if Arjun says SHIP and Meera says REVISE, the synthesis picks a winner with a forward path instead of summarizing both sides.
+
 ### Confirm whether the advice actually shipped
 
 ```bash
@@ -426,6 +443,8 @@ npx analyzthis_design moodboard critique --board <id>
 npx analyzthis_design moodboard add --board <id> --url <url> --tags a,b
 
 # Evolve
+npx analyzthis_design evolve --metrics
+npx analyzthis_design evolve --ready
 npx analyzthis_design evolve --extract --dry-run
 npx analyzthis_design evolve --apply <patchId>
 npx analyzthis_design outcome --confirm --persona arjun --result shipped

package/README.md

@@ -4,6 +4,12 @@ A set of AI design personas and a task-first evaluation framework that plugs int
 
 Install once. Run structured UX critiques, multi-phase ideation, and task-grounded screen reviews — directly inside your AI chat. **No external LLM API keys required** for CLI orchestrator runs: **`/devi`** voices each persona from your host IDE (Cursor, Claude, etc.).
 
+## v2.2 — project-scoped knowledge bank
+
+Knowledge sources are now scoped per project by default. `collect`, `connect`, `sync`, `disconnect`, and `status` operate on the project derived from your current working directory, and the built `knowledge-bank` skill is written into that project's local skills directory (`<project>/.claude/skills/knowledge-bank/SKILL.md`, `<project>/.cursor/skills/...`, etc.). Invoking a skill from one project never reads another project's vaults.
+
+Pass `--global` to opt into the legacy merged behavior (read `config.sources` and write into `~/.claude/skills/...`). Use `--global` only when you deliberately want cross-project blending.
+
 ## v2.0 — chunked execution by default
 
 `npx analyzthis_design run --task "..."` now uses a **frontier planner + cheap chunk models**:
@@ -15,7 +21,7 @@ Install once. Run structured UX critiques, multi-phase ideation, and task-ground
 
 Use `npx analyzthis_design run-unchunked` for the legacy single-pass orchestrator.
 
-**npm:** [analyzthis_design](https://www.npmjs.com/package/analyzthis_design) · **Current version:** 2.1.2 · **Step-by-step guide:** [HOW-TO-USE.md](./HOW-TO-USE.md)
+**npm:** [analyzthis_design](https://www.npmjs.com/package/analyzthis_design) · **Current version:** 2.3.0 · **Step-by-step guide:** [HOW-TO-USE.md](./HOW-TO-USE.md)
 
 ---
 
@@ -36,6 +42,8 @@ npx analyzthis_design run-unchunked --task "Review invoice approval screen" --pr
 ```
 
 > **Security:** This package publishes **plain source** — no obfuscation, no minification, no dynamic require. Every file in `dist/` is readable and auditable. The `postinstall` script only prints a welcome message; it does **not** write to any AI-agent directories. Skill installation requires an explicit `npx analyzthis_design --target <ide>` command.
+>
+> **MCP (universal):** `npx analyzthis_design mcp` starts a local MCP server with 19 tools (all personas + combination passes + utilities). Auto-configures for Cursor, Claude Desktop, and Windsurf during `--target all` install. For Lovable, v0, Bolt, Replit, ChatGPT: run `npx analyzthis_design mcp --configure <tool>` for a config snippet.
 
 ### Install by target IDE
 
@@ -536,12 +544,14 @@ npx analyzthis_design feedback status
 
 **What does NOT get sent:** project paths, repo names, emails, API keys, full source trees.
 
-**Maintainer setup (Supabase):**
+**Maintainer setup (vendor-neutral HTTP endpoint):**
 
-1. Create a Supabase project
-2. Run `supabase/migrations/001_persona_feedback.sql` in the SQL editor
-3. Copy `supabase/feedback-config.example.json` into `~/.analyzthis_design/config.json` under `"feedback"` (or set env vars `ANALYZTHIS_FEEDBACK_URL` + `ANALYZTHIS_FEEDBACK_ANON_KEY`)
-4. View submissions in Supabase Table Editor → `persona_feedback`
+The `feedback submit` client is a plain HTTPS POST with an `apikey` header — it works with any REST endpoint that accepts anonymous inserts, not only Supabase. A reference schema (with row-level security for insert-only anon access) lives in [`supabase/migrations/001_persona_feedback.sql`](./supabase/migrations/001_persona_feedback.sql) in the repo. That folder is **not** shipped in the npm package, so installing `analyzthis_design` does not pull a Supabase-branded folder into `node_modules`.
+
+1. Stand up any HTTP endpoint that accepts anonymous JSON inserts (Supabase with RLS is one option; a small Cloudflare Worker or a self-hosted Postgres + thin API work too).
+2. If you use the reference schema, run `supabase/migrations/001_persona_feedback.sql` in your SQL editor.
+3. Copy the endpoint URL and anon key into `~/.analyzthis_design/config.json` under `"feedback"` (or set env vars `ANALYZTHIS_FEEDBACK_URL` + `ANALYZTHIS_FEEDBACK_ANON_KEY`).
+4. Read submissions from your endpoint's dashboard.
 
 Users can also file GitHub issues via **Persona feedback** template if they prefer not to use CLI submit.
 
@@ -725,9 +735,18 @@ npx analyzthis_design run --continue --task "..."   # resume host-mode run after
 # CSV validation
 npx analyzthis_design validate    # validate all 28 CSV files against schema.json
 
+# MCP server (for any AI IDE: Cursor, Claude Desktop, Lovable, v0, Bolt, Replit)
+npx analyzthis_design mcp                          # start stdio MCP server
+npx analyzthis_design mcp --configure cursor       # auto-config Cursor
+npx analyzthis_design mcp --configure claude        # auto-config Claude Desktop
+npx analyzthis_design mcp --configure windsurf     # auto-config Windsurf
+npx analyzthis_design mcp --configure <tool>       # print config for any other tool
+
 # Self-evolving team (v1.21)
 npx analyzthis_design evolve --extract [--window N] [--dry-run]
 npx analyzthis_design evolve --apply <patchId> [--dry-run]
+npx analyzthis_design evolve --metrics [--project id]
+npx analyzthis_design evolve --ready [--project id]
 npx analyzthis_design outcome --infer [--window N]
 npx analyzthis_design outcome --pending
 npx analyzthis_design outcome --confirm --persona <id> --result shipped|revised|blocked|missed
@@ -775,6 +794,8 @@ lib/
   chunk-telemetry.js    Per-chunk model quality tracking
   chunk-run.js          Top-level chunked execution coordinator
   reference-pack.js     Shared multi-file CSV + vault retrieval (buildReferencePack)
+  mcp-server.js         MCP server — 19 tools for any MCP-compatible IDE
+  system-prompt.js      Consolidated prompt generator (fallback for non-MCP tools)
   moodboard.js          Mood-board engine: collect web/DS references, tag, deliberate
   dedup.js              Cross-persona redundancy detection
   lessons.js            Self-evolving lessons store (extract/retrieve/inject)
@@ -821,6 +842,27 @@ skills/
 
 ---
 
+## What's new in v2.3
+
+| Feature | Description |
+|---------|-------------|
+| **MCP server** | `npx analyzthis_design mcp` starts a local MCP server exposing 19 tools — all 8 individual personas + 6 combination passes + 5 utilities. Any MCP-compatible client can discover and call them. |
+| **Auto-configure MCP** | `npx analyzthis_design mcp --configure cursor` (or `claude`, `windsurf`) writes the MCP config automatically. `--target all` now auto-configures MCP during install. |
+| **Universal IDE support** | Cursor, Claude Desktop, Windsurf auto-configured. Lovable, v0, Bolt, Replit, ChatGPT: run `mcp --configure <tool>` for a copy-paste config snippet. |
+| **19 MCP tools** | 8 individual personas (arjun, meera, priya, zara, noor, anuj, raj, kavi) + 6 combination passes (ux-ideator, persona-orchestrator, design-critic, ux-story-gate, design-director, mood-board) + 5 utilities (evolve-check, collect, retrieve, session, system-prompt) |
+| **System prompt fallback** | `analyzthis_system_prompt` tool generates a consolidated prompt for tools that don't support MCP yet |
+
+## What's new in v2.2
+
+| Feature | Description |
+|---------|-------------|
+| **Premise challenge** | Planner now evaluates whether the task premise is valid before planning chunks. Can add a `premise_check` chunk (Raj) that runs first and questions "are we solving the right problem?" |
+| **Conflict resolution** | Synthesis must pick a winner when personas disagree — not summarize both sides. Detects disagreements automatically, injects them into the synthesis prompt, and requires a definitive answer with a forward path. |
+| **Raj authority expanded** | Raj can now challenge the task premise (not just arbitrate stalemates). "Accepting the task framing without questioning it" is explicitly forbidden. |
+| **Evolution metrics** | `evolve --metrics` shows a per-persona evolution dashboard (0-100 score, levels: Novice → Expert). `evolve --ready` checks if enough data exists to propose patches. |
+| **Devi evolution check** | After every successful run, Devi prints an evolution readiness hint and asks if the team is ready to evolve. |
+| **Plain source, no obfuscation** | Removed `javascript-obfuscator` entirely. `dist/` is fully auditable plain JavaScript. `postinstall` only prints a message — no auto-install. |
+
 ## What's new in v2.0
 
 | Feature | Description |
@@ -869,6 +911,22 @@ skills/
 
 ---
 
+## Marketing site
+
+The public lab site lives in `website/` and is deployed on Vercel as **analyzthis-lab** (site only — not the npm package). Copy now names two doors: lab products for people who already use Cursor or Claude, and custom teams that arrive in a firm’s existing tools. The Vercel project root is `website/` with no build step — do not set Output Directory to `public`.
+
+- Live: [https://analyzthis-lab.vercel.app](https://analyzthis-lab.vercel.app)
+- Design team deep-dive: [https://analyzthis-lab.vercel.app/design](https://analyzthis-lab.vercel.app/design) (`website/design.html`)
+- Form test (does not write to Airtable): add `?form=mock` to the URL
+- Leads go to Airtable through `website/api/lead.js`. Each step is saved; unfinished fills are marked `partial`.
+- Booking uses Google Calendar: [https://calendar.app.google/KtKJ7hCAx1duA8m58](https://calendar.app.google/KtKJ7hCAx1duA8m58)
+- Form views are counted first-party (no cookies, no third-party pixel). They are only stored if you set the optional `AIRTABLE_EVENTS_TABLE` env var to a separate Airtable table; without it the count is discarded and the Leads table is never touched.
+- There is exactly one privacy disclosure, in the `.privacy-note` directly above the inquiry form. If you change what the site collects, update that sentence — do not add a second notice elsewhere on the page.
+- Header layout: the real `logo.svg` sits left, nav links centre, one orange CTA right. No webfont is loaded, so the wordmark must stay an SVG.
+- The hero is tuned so the primary CTA and trust ticks stay above the fold at 1440×800 — check that before changing hero padding or the `h1` clamp.
+
+---
+
 ## License
 
 MIT — [Rishikesh Joshi](https://github.com/rishikeshjoshi)

package/agents/cards/raj.md

@@ -2,11 +2,11 @@
 
 10+ years product strategy. Speaks ONLY when the Stalemate Protocol activates — does not volunteer opinions. Every position anchored to PRD evidence, user data, or a named product principle.
 
-**Allowed:** resolve stalemates between personas using the 5 product principles; issue final SHIP/REVISE/BLOCK when personas disagree.
+**Allowed:** resolve stalemates between personas using the 5 product principles; issue final SHIP/REVISE/BLOCK when personas disagree; challenge the task premise — "are we solving the right problem?"
 
-**Forbidden:** running with no stalemate/BLOCK condition; code edits without explicit build approval.
+**Forbidden:** running with no stalemate/BLOCK condition; code edits without explicit build approval; accepting the task framing without questioning it.
 
-**Activation criteria (any one):** 2+ unconceded structural objections; a "non-negotiable" claim refused; the same argument repeated without new evidence; a PRD-persona-priority conflict with no established priority.
+**Activation criteria (any one):** 2+ unconceded structural objections; a "non-negotiable" claim refused; the same argument repeated without new evidence; a PRD-persona-priority conflict with no established priority; synthesis phase (always — must resolve conflicts and challenge premise).
 
 ## Output schema (always full — Raj has no lite mode; his output is inherently a short decision)
 ```

package/dist/HOW-TO-USE.md

@@ -335,6 +335,23 @@ npx analyzthis_design evolve --extract             # write patch proposals
 npx analyzthis_design evolve --apply <patchId>      # apply after review
 ```
 
+### Check evolution metrics
+
+```bash
+npx analyzthis_design evolve --metrics             # team evolution dashboard
+npx analyzthis_design evolve --ready               # check if enough data to evolve
+```
+
+The dashboard shows a per-persona score (0-100) based on lessons, outcomes, and patches applied. Levels: Novice (0-19) -> Developing (20-39) -> Proficient (40-59) -> Advanced (60-79) -> Expert (80-100).
+
+After every successful run, Devi prints an evolution readiness hint automatically.
+
+### Premise challenge (v2.2)
+
+When you run a critique, the planner now evaluates whether your task framing is valid before planning chunks. If the premise is questionable (e.g., "users don't convert because X is buried" — but maybe they reach X and still don't convert), the planner adds a `premise_check` chunk that Raj runs first. All subsequent persona chunks see the premise assessment.
+
+The synthesis step also explicitly resolves disagreements — if Arjun says SHIP and Meera says REVISE, the synthesis picks a winner with a forward path instead of summarizing both sides.
+
 ### Confirm whether the advice actually shipped
 
 ```bash
@@ -426,6 +443,8 @@ npx analyzthis_design moodboard critique --board <id>
 npx analyzthis_design moodboard add --board <id> --url <url> --tags a,b
 
 # Evolve
+npx analyzthis_design evolve --metrics
+npx analyzthis_design evolve --ready
 npx analyzthis_design evolve --extract --dry-run
 npx analyzthis_design evolve --apply <patchId>
 npx analyzthis_design outcome --confirm --persona arjun --result shipped

package/dist/README.md

@@ -4,6 +4,12 @@ A set of AI design personas and a task-first evaluation framework that plugs int
 
 Install once. Run structured UX critiques, multi-phase ideation, and task-grounded screen reviews — directly inside your AI chat. **No external LLM API keys required** for CLI orchestrator runs: **`/devi`** voices each persona from your host IDE (Cursor, Claude, etc.).
 
+## v2.2 — project-scoped knowledge bank
+
+Knowledge sources are now scoped per project by default. `collect`, `connect`, `sync`, `disconnect`, and `status` operate on the project derived from your current working directory, and the built `knowledge-bank` skill is written into that project's local skills directory (`<project>/.claude/skills/knowledge-bank/SKILL.md`, `<project>/.cursor/skills/...`, etc.). Invoking a skill from one project never reads another project's vaults.
+
+Pass `--global` to opt into the legacy merged behavior (read `config.sources` and write into `~/.claude/skills/...`). Use `--global` only when you deliberately want cross-project blending.
+
 ## v2.0 — chunked execution by default
 
 `npx analyzthis_design run --task "..."` now uses a **frontier planner + cheap chunk models**:
@@ -15,7 +21,7 @@ Install once. Run structured UX critiques, multi-phase ideation, and task-ground
 
 Use `npx analyzthis_design run-unchunked` for the legacy single-pass orchestrator.
 
-**npm:** [analyzthis_design](https://www.npmjs.com/package/analyzthis_design) · **Current version:** 2.1.2 · **Step-by-step guide:** [HOW-TO-USE.md](./HOW-TO-USE.md)
+**npm:** [analyzthis_design](https://www.npmjs.com/package/analyzthis_design) · **Current version:** 2.3.0 · **Step-by-step guide:** [HOW-TO-USE.md](./HOW-TO-USE.md)
 
 ---
 
@@ -36,6 +42,8 @@ npx analyzthis_design run-unchunked --task "Review invoice approval screen" --pr
 ```
 
 > **Security:** This package publishes **plain source** — no obfuscation, no minification, no dynamic require. Every file in `dist/` is readable and auditable. The `postinstall` script only prints a welcome message; it does **not** write to any AI-agent directories. Skill installation requires an explicit `npx analyzthis_design --target <ide>` command.
+>
+> **MCP (universal):** `npx analyzthis_design mcp` starts a local MCP server with 19 tools (all personas + combination passes + utilities). Auto-configures for Cursor, Claude Desktop, and Windsurf during `--target all` install. For Lovable, v0, Bolt, Replit, ChatGPT: run `npx analyzthis_design mcp --configure <tool>` for a config snippet.
 
 ### Install by target IDE
 
@@ -536,12 +544,14 @@ npx analyzthis_design feedback status
 
 **What does NOT get sent:** project paths, repo names, emails, API keys, full source trees.
 
-**Maintainer setup (Supabase):**
+**Maintainer setup (vendor-neutral HTTP endpoint):**
 
-1. Create a Supabase project
-2. Run `supabase/migrations/001_persona_feedback.sql` in the SQL editor
-3. Copy `supabase/feedback-config.example.json` into `~/.analyzthis_design/config.json` under `"feedback"` (or set env vars `ANALYZTHIS_FEEDBACK_URL` + `ANALYZTHIS_FEEDBACK_ANON_KEY`)
-4. View submissions in Supabase Table Editor → `persona_feedback`
+The `feedback submit` client is a plain HTTPS POST with an `apikey` header — it works with any REST endpoint that accepts anonymous inserts, not only Supabase. A reference schema (with row-level security for insert-only anon access) lives in [`supabase/migrations/001_persona_feedback.sql`](./supabase/migrations/001_persona_feedback.sql) in the repo. That folder is **not** shipped in the npm package, so installing `analyzthis_design` does not pull a Supabase-branded folder into `node_modules`.
+
+1. Stand up any HTTP endpoint that accepts anonymous JSON inserts (Supabase with RLS is one option; a small Cloudflare Worker or a self-hosted Postgres + thin API work too).
+2. If you use the reference schema, run `supabase/migrations/001_persona_feedback.sql` in your SQL editor.
+3. Copy the endpoint URL and anon key into `~/.analyzthis_design/config.json` under `"feedback"` (or set env vars `ANALYZTHIS_FEEDBACK_URL` + `ANALYZTHIS_FEEDBACK_ANON_KEY`).
+4. Read submissions from your endpoint's dashboard.
 
 Users can also file GitHub issues via **Persona feedback** template if they prefer not to use CLI submit.
 
@@ -725,9 +735,18 @@ npx analyzthis_design run --continue --task "..."   # resume host-mode run after
 # CSV validation
 npx analyzthis_design validate    # validate all 28 CSV files against schema.json
 
+# MCP server (for any AI IDE: Cursor, Claude Desktop, Lovable, v0, Bolt, Replit)
+npx analyzthis_design mcp                          # start stdio MCP server
+npx analyzthis_design mcp --configure cursor       # auto-config Cursor
+npx analyzthis_design mcp --configure claude        # auto-config Claude Desktop
+npx analyzthis_design mcp --configure windsurf     # auto-config Windsurf
+npx analyzthis_design mcp --configure <tool>       # print config for any other tool
+
 # Self-evolving team (v1.21)
 npx analyzthis_design evolve --extract [--window N] [--dry-run]
 npx analyzthis_design evolve --apply <patchId> [--dry-run]
+npx analyzthis_design evolve --metrics [--project id]
+npx analyzthis_design evolve --ready [--project id]
 npx analyzthis_design outcome --infer [--window N]
 npx analyzthis_design outcome --pending
 npx analyzthis_design outcome --confirm --persona <id> --result shipped|revised|blocked|missed
@@ -775,6 +794,8 @@ lib/
   chunk-telemetry.js    Per-chunk model quality tracking
   chunk-run.js          Top-level chunked execution coordinator
   reference-pack.js     Shared multi-file CSV + vault retrieval (buildReferencePack)
+  mcp-server.js         MCP server — 19 tools for any MCP-compatible IDE
+  system-prompt.js      Consolidated prompt generator (fallback for non-MCP tools)
   moodboard.js          Mood-board engine: collect web/DS references, tag, deliberate
   dedup.js              Cross-persona redundancy detection
   lessons.js            Self-evolving lessons store (extract/retrieve/inject)
@@ -821,6 +842,27 @@ skills/
 
 ---
 
+## What's new in v2.3
+
+| Feature | Description |
+|---------|-------------|
+| **MCP server** | `npx analyzthis_design mcp` starts a local MCP server exposing 19 tools — all 8 individual personas + 6 combination passes + 5 utilities. Any MCP-compatible client can discover and call them. |
+| **Auto-configure MCP** | `npx analyzthis_design mcp --configure cursor` (or `claude`, `windsurf`) writes the MCP config automatically. `--target all` now auto-configures MCP during install. |
+| **Universal IDE support** | Cursor, Claude Desktop, Windsurf auto-configured. Lovable, v0, Bolt, Replit, ChatGPT: run `mcp --configure <tool>` for a copy-paste config snippet. |
+| **19 MCP tools** | 8 individual personas (arjun, meera, priya, zara, noor, anuj, raj, kavi) + 6 combination passes (ux-ideator, persona-orchestrator, design-critic, ux-story-gate, design-director, mood-board) + 5 utilities (evolve-check, collect, retrieve, session, system-prompt) |
+| **System prompt fallback** | `analyzthis_system_prompt` tool generates a consolidated prompt for tools that don't support MCP yet |
+
+## What's new in v2.2
+
+| Feature | Description |
+|---------|-------------|
+| **Premise challenge** | Planner now evaluates whether the task premise is valid before planning chunks. Can add a `premise_check` chunk (Raj) that runs first and questions "are we solving the right problem?" |
+| **Conflict resolution** | Synthesis must pick a winner when personas disagree — not summarize both sides. Detects disagreements automatically, injects them into the synthesis prompt, and requires a definitive answer with a forward path. |
+| **Raj authority expanded** | Raj can now challenge the task premise (not just arbitrate stalemates). "Accepting the task framing without questioning it" is explicitly forbidden. |
+| **Evolution metrics** | `evolve --metrics` shows a per-persona evolution dashboard (0-100 score, levels: Novice → Expert). `evolve --ready` checks if enough data exists to propose patches. |
+| **Devi evolution check** | After every successful run, Devi prints an evolution readiness hint and asks if the team is ready to evolve. |
+| **Plain source, no obfuscation** | Removed `javascript-obfuscator` entirely. `dist/` is fully auditable plain JavaScript. `postinstall` only prints a message — no auto-install. |
+
 ## What's new in v2.0
 
 | Feature | Description |
@@ -869,6 +911,22 @@ skills/
 
 ---
 
+## Marketing site
+
+The public lab site lives in `website/` and is deployed on Vercel as **analyzthis-lab** (site only — not the npm package). Copy now names two doors: lab products for people who already use Cursor or Claude, and custom teams that arrive in a firm’s existing tools. The Vercel project root is `website/` with no build step — do not set Output Directory to `public`.
+
+- Live: [https://analyzthis-lab.vercel.app](https://analyzthis-lab.vercel.app)
+- Design team deep-dive: [https://analyzthis-lab.vercel.app/design](https://analyzthis-lab.vercel.app/design) (`website/design.html`)
+- Form test (does not write to Airtable): add `?form=mock` to the URL
+- Leads go to Airtable through `website/api/lead.js`. Each step is saved; unfinished fills are marked `partial`.
+- Booking uses Google Calendar: [https://calendar.app.google/KtKJ7hCAx1duA8m58](https://calendar.app.google/KtKJ7hCAx1duA8m58)
+- Form views are counted first-party (no cookies, no third-party pixel). They are only stored if you set the optional `AIRTABLE_EVENTS_TABLE` env var to a separate Airtable table; without it the count is discarded and the Leads table is never touched.
+- There is exactly one privacy disclosure, in the `.privacy-note` directly above the inquiry form. If you change what the site collects, update that sentence — do not add a second notice elsewhere on the page.
+- Header layout: the real `logo.svg` sits left, nav links centre, one orange CTA right. No webfont is loaded, so the wordmark must stay an SVG.
+- The hero is tuned so the primary CTA and trust ticks stay above the fold at 1440×800 — check that before changing hero padding or the `h1` clamp.
+
+---
+
 ## License
 
 MIT — [Rishikesh Joshi](https://github.com/rishikeshjoshi)

package/dist/agents/cards/raj.md

@@ -2,11 +2,11 @@
 
 10+ years product strategy. Speaks ONLY when the Stalemate Protocol activates — does not volunteer opinions. Every position anchored to PRD evidence, user data, or a named product principle.
 
-**Allowed:** resolve stalemates between personas using the 5 product principles; issue final SHIP/REVISE/BLOCK when personas disagree.
+**Allowed:** resolve stalemates between personas using the 5 product principles; issue final SHIP/REVISE/BLOCK when personas disagree; challenge the task premise — "are we solving the right problem?"
 
-**Forbidden:** running with no stalemate/BLOCK condition; code edits without explicit build approval.
+**Forbidden:** running with no stalemate/BLOCK condition; code edits without explicit build approval; accepting the task framing without questioning it.
 
-**Activation criteria (any one):** 2+ unconceded structural objections; a "non-negotiable" claim refused; the same argument repeated without new evidence; a PRD-persona-priority conflict with no established priority.
+**Activation criteria (any one):** 2+ unconceded structural objections; a "non-negotiable" claim refused; the same argument repeated without new evidence; a PRD-persona-priority conflict with no established priority; synthesis phase (always — must resolve conflicts and challenge premise).
 
 ## Output schema (always full — Raj has no lite mode; his output is inherently a short decision)
 ```

package/dist/bin/cli.js

@@ -33,14 +33,20 @@ Usage:
   welcome    Print getting-started banner for your AI tool (--target)
 
 ── Knowledge bank commands ──────────────────────────────────
-  connect    Register a vault or knowledge folder as a source
-  sync       Read all sources and build the knowledge-bank skill
-  disconnect Remove a source from the registry
-  status     Show connected sources and last sync time
+  connect    Register a vault or knowledge folder as a source (scoped to cwd project)
+  sync       Read this project's sources and build the knowledge-bank skill
+  disconnect Remove a source from this project's registry
+  status     Show this project's sources and last sync time
   collect    Kavi: scan codebase → Obsidian vault → enrich → sync knowledge bank
              (--vault path, --dry-run, --no-enrich, --no-web, --no-discover,
               --web-limit N, --target cursor|claude|codex|grok|windsurf|agents|all)
 
+  Scope flags (connect/sync/disconnect/status):
+  --project <id>   Explicit project id (overrides cwd-derived id)
+  --global         Use the legacy merged pool (config.sources → ~/.claude/skills/...)
+                   instead of per-project scoping. Only use when you want
+                   multiple projects' notes blended together.
+
 ── Design spec commands ─────────────────────────────────────
   spec show      Print design_spec from session state
   spec validate  Validate a DesignSpec JSON file (--file) or session
@@ -61,7 +67,7 @@ Usage:
   feedback list     List feedback entries for this project (--all for every project)
   feedback export   Export rejected + correction JSONL pairs for training
                     (--persona <id>, --all, --output <path>, --include-positive)
-  feedback submit   Opt-in: send anonymized corrections to community store (Supabase)
+  feedback submit   Opt-in: send anonymized corrections to a community store (HTTP endpoint)
                     (--yes skip prompt, --dry-run preview, --all unsent across projects)
   feedback status   Show submit consent, endpoint config, unsent count
   feedback revoke   Revoke opt-in consent for community submit
@@ -77,6 +83,13 @@ Usage:
   research --url <url>       Fetch a URL and append to session web-context.md
   research --query <text>    Search stub (or provider) appended to web-context.md
 
+── MCP server (for any AI IDE: Cursor, Claude Desktop, Lovable, v0, Bolt) ──
+  mcp                       Start the MCP server on stdio (for MCP client config)
+  mcp --configure cursor    Write MCP config to ~/.cursor/mcp.json
+  mcp --configure claude    Write MCP config to Claude Desktop config
+  mcp --configure windsurf   Write MCP config to Windsurf
+  mcp --configure <tool>    Print manual MCP config for any other tool
+
 ── Mood board commands ─────────────────────────────────────
   moodboard create --task <text>   Build a mood board from web + DS references
                                     [--url <url> ...] [--auto]
@@ -175,9 +188,11 @@ Usage:
   npx analyzthis_design connect --vault ~/Documents/MyVault
   npx analyzthis_design connect --vault ~/docs --tags design,brand,product
   npx analyzthis_design connect --vault ~/vault --include Design,Research
-  npx analyzthis_design sync                               # sync to Cursor
-  npx analyzthis_design sync --target all                  # sync to all tools
-  npx analyzthis_design status                             # show sources
+  npx analyzthis_design sync                               # sync to Cursor (project-scoped)
+  npx analyzthis_design sync --target all                  # sync to all tools (project-scoped)
+  npx analyzthis_design sync --global                      # legacy: blend all projects into ~/.claude/skills/
+  npx analyzthis_design status                             # show this project's sources
+  npx analyzthis_design status --global                    # show the legacy merged pool
   npx analyzthis_design disconnect --vault ~/Documents/MyVault
 
   npx analyzthis_design session init                       # start a new session for this repo
@@ -255,6 +270,7 @@ const vaultVal   = getFlag('vault');
 const tagsVal    = getFlag('tags');
 const includeVal = getFlag('include');
 const projectVal = getFlag('project');
+const globalFlag = flags.includes('--global');
 const allFlag    = flags.includes('--all');
 const urlVal     = getFlag('url');
 const queryVal   = getFlag('query');
@@ -352,8 +368,10 @@ switch (cmd) {
     try {
       const tags    = tagsVal    ? tagsVal.split(',').map(t => t.trim())    : [];
       const include = includeVal ? includeVal.split(',').map(t => t.trim()) : [];
-      const abs = connect({ vaultPath: vaultVal, tags, include });
+      const abs = connect({ vaultPath: vaultVal, tags, include, project: projectVal, global: globalFlag });
+      const scopeLabel = globalFlag ? 'global (merged across projects)' : (projectVal || `project derived from ${path.resolve(process.cwd())}`);
       console.log(`\n✅ Connected: ${abs}`);
+      console.log(`   Scope: ${scopeLabel}`);
       if (tags.length)    console.log(`   Tags filter:    ${tags.join(', ')}`);
       if (include.length) console.log(`   Folder filter:  ${include.join(', ')}`);
       console.log(`\n   Run "npx analyzthis_design sync" to build the knowledge bank.\n`);
@@ -369,7 +387,7 @@ switch (cmd) {
       console.error('\n  ✗  --vault is required.  Example: npx analyzthis_design disconnect --vault ~/Documents/MyVault\n');
       process.exit(1);
     }
-    disconnect(vaultVal);
+    disconnect(vaultVal, { project: projectVal, global: globalFlag });
     console.log(`\n🗑  Disconnected: ${path.resolve(vaultVal)}\n`);
     break;
   }
@@ -381,9 +399,10 @@ switch (cmd) {
       console.error(`\n  ✗  Unknown target "${targetVal}". Choose: ${ALL_TARGET_IDS.join(', ')}, all\n`);
       process.exit(1);
     }
-    console.log('\n⏳ Syncing knowledge bank...\n');
+    const scopeLabel = globalFlag ? 'global (merged across projects)' : (projectVal || `project derived from ${path.resolve(process.cwd())}`);
+    console.log(`\n⏳ Syncing knowledge bank (${scopeLabel})...\n`);
     try {
-      const result = sync({ targets });
+      const result = sync({ targets, project: projectVal, global: globalFlag });
       if (result.message) {
         console.log(`  ⚠  ${result.message}\n`);
       } else {
@@ -399,18 +418,22 @@ switch (cmd) {
   }
 
   case 'status': {
-    const cfg = status();
-    if (!cfg.sources || cfg.sources.length === 0) {
-      console.log('\n  No knowledge sources connected.\n  Run: npx analyzthis_design connect --vault /path/to/vault\n');
+    const view = status({ project: projectVal, global: globalFlag });
+    if (!view.sources || view.sources.length === 0) {
+      const scopeHint = view.scope === 'global'
+        ? 'Run: npx analyzthis_design connect --vault /path/to/vault --global'
+        : 'Run: npx analyzthis_design collect (from inside the project) or npx analyzthis_design connect --vault /path/to/vault';
+      console.log(`\n  No knowledge sources connected for this ${view.scope} scope.\n  ${scopeHint}\n`);
     } else {
-      console.log(`\n📚 Knowledge bank sources (${cfg.sources.length}):\n`);
-      for (const s of cfg.sources) {
+      const scopeLabel = view.scope === 'global' ? 'global (merged across projects)' : `project: ${view.projectId}`;
+      console.log(`\n📚 Knowledge bank sources (${view.sources.length}) — ${scopeLabel}:\n`);
+      for (const s of view.sources) {
         console.log(`  • ${s.path}`);
-        if (s.tags.length)    console.log(`    Tags:    ${s.tags.join(', ')}`);
-        if (s.include.length) console.log(`    Folders: ${s.include.join(', ')}`);
+        if (s.tags && s.tags.length)    console.log(`    Tags:    ${s.tags.join(', ')}`);
+        if (s.include && s.include.length) console.log(`    Folders: ${s.include.join(', ')}`);
         console.log(`    Added:   ${s.addedAt}`);
       }
-      if (cfg.lastSync) console.log(`\n  Last sync: ${cfg.lastSync}`);
+      if (view.lastSync) console.log(`\n  Last sync: ${view.lastSync}`);
       console.log('');
     }
     break;
@@ -735,6 +758,19 @@ switch (cmd) {
     process.exit(1);
   }
 
+  // ── MCP server ─────────────────────────────────────────────────────────
+
+  case 'mcp': {
+    const mcpServer = require('../lib/mcp-server');
+    const configureTarget = getFlag('configure');
+    if (configureTarget) {
+      mcpServer.writeMcpConfig(configureTarget);
+      break;
+    }
+    mcpServer.startStdioServer();
+    break;
+  }
+
   // ── Retrieve-on-demand reference rows ───────────────────────────────────
 
   case 'retrieve': {

package/dist/lib/chunk-planner.js

@@ -108,6 +108,17 @@ function plannerSystemPrompt() {
     'Each chunk targets one persona and has a clear goal, prompts, effort level, and dependencies.',
     'You must output ONLY a JSON object inside a ```json code fence.',
     '',
+    'CRITICAL: Before planning chunks, evaluate whether the task premise is valid.',
+    'Ask: "Are we solving the right problem?" If the premise is questionable, add a',
+    'premise_check chunk (persona: raj, effort: hard) that explicitly challenges the',
+    'framing. The premise_check chunk should run FIRST and its output should be',
+    'available to subsequent chunks via depends_on.',
+    '',
+    'Also add a synthesis chunk (persona: raj, effort: hard) that runs LAST and must:',
+    '1. Resolve any disagreements between personas (pick a winner, give a forward path)',
+    '2. Challenge the premise if it was not already challenged',
+    '3. Produce a definitive verdict — not a summary of opinions',
+    '',
     'Allowed personas: arjun (UX/visual), meera (business), priya (feasibility), zara (delight), noor (minimalist IA), anuj (dense power-user), raj (strategy/arbitration).',
     '',
     'Effort levels:',
@@ -119,21 +130,33 @@ function plannerSystemPrompt() {
     '{',
     '  "plan_id": "short-unique-id",',
     '  "task_summary": "one-line summary",',
+    '  "premise_valid": true | false | "questionable",',
+    '  "premise_concern": "if questionable, what is the real problem?",',
     '  "chunks": [',
     '    {',
-    '      "id": "ia",',
-    '      "persona": "noor",',
-    '      "goal": "define information hierarchy",',
+    '      "id": "premise_check",',
+    '      "persona": "raj",',
+    '      "goal": "challenge the task framing — are we solving the right problem?",',
     '      "system_prompt": "...",',
     '      "user_prompt": "...",',
-    '      "effort": "standard",',
+    '      "effort": "hard",',
     '      "depends_on": [],',
-    '      "output_schema": "hierarchy_list"',
+    '      "output_schema": "premise_assessment"',
+    '    },',
+    '    {',
+    '      "id": "arjun",',
+    '      "persona": "arjun",',
+    '      "goal": "...",',
+    '      "system_prompt": "...",',
+    '      "user_prompt": "...",',
+    '      "effort": "standard",',
+    '      "depends_on": ["premise_check"],',
+    '      "output_schema": "ux_audit"',
     '    }',
     '  ],',
     '  "synthesis": {',
     '    "persona": "raj",',
-    '    "goal": "resolve conflicts and produce final verdict",',
+    '    "goal": "resolve conflicts, challenge premise if needed, produce definitive verdict",',
     '    "system_prompt": "...",',
     '    "user_prompt": "..."',
     '  }',