analyzthis_design 2.3.1 → 2.4.1

package/HOW-TO-USE.md

@@ -108,7 +108,8 @@ npx analyzthis_design sync --target all
 | Review against PRDs and stories | `/ux-story-gate` | Task map + routing before critique |
 | Set visual direction | `/mood-board` | References + design-system patterns + team deliberation |
 | Index the repo for personas | `/kavi` | Kavi → knowledge bank |
-| Get a single-lens opinion | `/arjun`, `/meera`, `/priya`, `/zara`, `/noor`, `/anuj` | Targeted follow-up |
+| Get a single-lens opinion | `/arjun`, `/meera`, `/priya`, `/zara`, `/noor`, `/anuj` | Targeted follow-up. Default is a short verdict — say expand for the full schema |
+| See inferred token spend | `/receipt` | Not a bill. Same as `npx analyzthis_design receipt` |
 
 **Important:** do not use `/persona-orchestrator` or `/design-critic` when you want wireframes. They are for critique.
 
@@ -312,21 +313,39 @@ Each persona reads the session state, so you do not need to repeat the task.
 
 ## 8. After the run — accept, reject, evolve
 
-### Mark an output accepted
+### Designer path (remember this)
 
-```bash
-npx analyzthis_design session accept --persona arjun
+In chat, after `/zara` or any persona:
+
+```
+/accept yes
+```
+
+or
+
+```
+/accept no — too much motion on the daily table
 ```
 
-### Reject with correction
+No terminal flags. `/accept` writes keep or skip for **local** evolution.
+
+To send a correction to the published package:
+
+```
+/share
+```
+
+Then **yes** if the preview looks right. Redacted — no folder names, emails, or keys.
+
+### CLI (same thing, if you prefer the terminal)
 
 ```bash
-npx analyzthis_design session accept --persona arjun --reject \
-  --comment "Invented tokens not in our DS" \
-  --correction "Use --color-primary and spacing-4 from tokens.css" \
-  --rating 2 --tags invented_tokens,missed_ds
+npx analyzthis_design accept --keep --persona arjun
+npx analyzthis_design accept --fix --persona arjun --because "Invented tokens — use tokens.css"
 ```
 
+The older `session accept` / `feedback record` flags still work.
+
 ### Make the team learn
 
 ```bash

package/README.md

@@ -4,6 +4,23 @@ 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.).
 
+## v2.4.1 — `/accept` and `/share` (designer keep / skip / send)
+
+After `/zara` (or any persona), type `/accept yes` or `/accept no` plus one sentence. No CLI flags. Writes keep or skip for **local** evolution. Slash-only notes still count.
+
+To send a correction to the **published** package: `/share` (preview) then `/share yes`. Redacted. Uses the HTTP endpoint if configured; otherwise a GitHub issue on joshirishi/analyzthis_design.
+
+## v2.4.0 — Claude-path efficiency (1 Sep 2026)
+
+Same SHIP / REVISE / BLOCK. Fewer tokens on Claude Code and Claude Desktop. Not Caveman-speak. Not a proxy.
+
+- **Lite MCP catalog (default):** `analyzthis_design` (router) + `analyzthis_retrieve` + `analyzthis_session` + `analyzthis_receipt`. Old 19-tool list: `ANALYZTHIS_MCP_CATALOG=full` or `npx analyzthis_design mcp --catalog full`.
+- **Receipt:** every MCP result ends with inferred tokens (not a bill). CLI: `npx analyzthis_design receipt`. Slash: `/receipt`.
+- **Slim skill fronts:** Arjun, story-gate, and orchestrator load a short front. Call retrieve (`kind=skill`) for the lens. Personas default to verdict + top 3 + one evidence line; say **expand** for the full schema.
+- **Knowledge bank** is an index. Load one persona slice (`kind=knowledge`, `persona=zara`). Do not inject the whole bank.
+- **Tokens per verdict** prints on `receipt` and CLI `run`.
+- Optional: wrap our stdio MCP through Caveman’s shrink if you already run Caveman. We do not ship a proxy.
+
 ## v2.3.1 — independently callable personas (31 Aug 2026)
 
 After install, type `/noor`, `/anuj`, `/arjun`, `/meera`, `/priya`, `/zara`, `/raj`, `/kavi` even if Claude’s slash menu only lists Getting Started.
@@ -37,7 +54,7 @@ Pass `--global` to opt into the legacy merged behavior (read `config.sources` an
 
 Use `npx analyzthis_design run-unchunked` for the legacy single-pass orchestrator.
 
-**npm:** [analyzthis_design](https://www.npmjs.com/package/analyzthis_design) · **Current version:** 2.3.1 · **Step-by-step guide:** [HOW-TO-USE.md](./HOW-TO-USE.md)
+**npm:** [analyzthis_design](https://www.npmjs.com/package/analyzthis_design) · **Current version:** 2.4.1 · **Step-by-step guide:** [HOW-TO-USE.md](./HOW-TO-USE.md)
 
 ---
 
@@ -63,7 +80,7 @@ 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 install --target <ide>` (or `npx analyzthis_design --target <ide>`).
 >
-> **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, **Claude Code**, and Windsurf during install. For Lovable, v0, Bolt, Replit, ChatGPT: run `npx analyzthis_design mcp --configure <tool>` for a config snippet.
+> **MCP (universal):** `npx analyzthis_design mcp` starts a local MCP server. Default catalog is **lite** (router + retrieve + session + receipt). Full 19 named tools: `ANALYZTHIS_MCP_CATALOG=full` or `mcp --catalog full`. Auto-configures for Cursor, Claude Desktop, **Claude Code**, and Windsurf during install. For Lovable, v0, Bolt, Replit, ChatGPT: run `npx analyzthis_design mcp --configure <tool>` for a config snippet.
 
 ### Install by target IDE
 
@@ -138,6 +155,9 @@ Invoke critique personas for targeted, already-grounded questions. For **wirefra
 | `/knowledge-bank` | Auto-populated from your connected vault (or from Kavi collect). All personas read this first. |
 | `/design-reference` | CSV reference data (colors, typography, UX guidelines, stacks, …) |
 | `/collect-knowledge` | Alias for `/kavi` |
+| `/accept` | Keep or skip the last persona note (yes / no). Local evolution — no CLI flags. |
+| `/share` | Send a correction to the package (preview, then yes). Redacted. |
+| `/receipt` | Inferred token receipt for this project. Not a bill. |
 
 ---
 
@@ -731,6 +751,10 @@ npx analyzthis_design status
 
 # Session (agentic)
 npx analyzthis_design session init|show|reset [--project id] [--all]
+npx analyzthis_design accept --keep [--persona zara]          # designer keep (slash: /accept yes)
+npx analyzthis_design accept --fix --because "one sentence"   # designer skip (slash: /accept no)
+npx analyzthis_design share                                   # preview notes for the package
+npx analyzthis_design share --send                            # send (slash: /share yes)
 npx analyzthis_design session accept --persona <id> [--reject] [--comment "..."] [--correction "..."] [--rating 1-5] [--tags a,b]
 
 # Persona feedback (v1.16)
@@ -870,7 +894,7 @@ skills/
 | **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) |
+| **MCP lite + full** | Default: router (`analyzthis_design`) + retrieve + session + receipt. Full 19 named tools behind `--catalog full`. |
 | **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

package/dist/HOW-TO-USE.md

@@ -108,7 +108,8 @@ npx analyzthis_design sync --target all
 | Review against PRDs and stories | `/ux-story-gate` | Task map + routing before critique |
 | Set visual direction | `/mood-board` | References + design-system patterns + team deliberation |
 | Index the repo for personas | `/kavi` | Kavi → knowledge bank |
-| Get a single-lens opinion | `/arjun`, `/meera`, `/priya`, `/zara`, `/noor`, `/anuj` | Targeted follow-up |
+| Get a single-lens opinion | `/arjun`, `/meera`, `/priya`, `/zara`, `/noor`, `/anuj` | Targeted follow-up. Default is a short verdict — say expand for the full schema |
+| See inferred token spend | `/receipt` | Not a bill. Same as `npx analyzthis_design receipt` |
 
 **Important:** do not use `/persona-orchestrator` or `/design-critic` when you want wireframes. They are for critique.
 
@@ -312,21 +313,39 @@ Each persona reads the session state, so you do not need to repeat the task.
 
 ## 8. After the run — accept, reject, evolve
 
-### Mark an output accepted
+### Designer path (remember this)
 
-```bash
-npx analyzthis_design session accept --persona arjun
+In chat, after `/zara` or any persona:
+
+```
+/accept yes
+```
+
+or
+
+```
+/accept no — too much motion on the daily table
 ```
 
-### Reject with correction
+No terminal flags. `/accept` writes keep or skip for **local** evolution.
+
+To send a correction to the published package:
+
+```
+/share
+```
+
+Then **yes** if the preview looks right. Redacted — no folder names, emails, or keys.
+
+### CLI (same thing, if you prefer the terminal)
 
 ```bash
-npx analyzthis_design session accept --persona arjun --reject \
-  --comment "Invented tokens not in our DS" \
-  --correction "Use --color-primary and spacing-4 from tokens.css" \
-  --rating 2 --tags invented_tokens,missed_ds
+npx analyzthis_design accept --keep --persona arjun
+npx analyzthis_design accept --fix --persona arjun --because "Invented tokens — use tokens.css"
 ```
 
+The older `session accept` / `feedback record` flags still work.
+
 ### Make the team learn
 
 ```bash

package/dist/README.md

@@ -4,6 +4,23 @@ 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.).
 
+## v2.4.1 — `/accept` and `/share` (designer keep / skip / send)
+
+After `/zara` (or any persona), type `/accept yes` or `/accept no` plus one sentence. No CLI flags. Writes keep or skip for **local** evolution. Slash-only notes still count.
+
+To send a correction to the **published** package: `/share` (preview) then `/share yes`. Redacted. Uses the HTTP endpoint if configured; otherwise a GitHub issue on joshirishi/analyzthis_design.
+
+## v2.4.0 — Claude-path efficiency (1 Sep 2026)
+
+Same SHIP / REVISE / BLOCK. Fewer tokens on Claude Code and Claude Desktop. Not Caveman-speak. Not a proxy.
+
+- **Lite MCP catalog (default):** `analyzthis_design` (router) + `analyzthis_retrieve` + `analyzthis_session` + `analyzthis_receipt`. Old 19-tool list: `ANALYZTHIS_MCP_CATALOG=full` or `npx analyzthis_design mcp --catalog full`.
+- **Receipt:** every MCP result ends with inferred tokens (not a bill). CLI: `npx analyzthis_design receipt`. Slash: `/receipt`.
+- **Slim skill fronts:** Arjun, story-gate, and orchestrator load a short front. Call retrieve (`kind=skill`) for the lens. Personas default to verdict + top 3 + one evidence line; say **expand** for the full schema.
+- **Knowledge bank** is an index. Load one persona slice (`kind=knowledge`, `persona=zara`). Do not inject the whole bank.
+- **Tokens per verdict** prints on `receipt` and CLI `run`.
+- Optional: wrap our stdio MCP through Caveman’s shrink if you already run Caveman. We do not ship a proxy.
+
 ## v2.3.1 — independently callable personas (31 Aug 2026)
 
 After install, type `/noor`, `/anuj`, `/arjun`, `/meera`, `/priya`, `/zara`, `/raj`, `/kavi` even if Claude’s slash menu only lists Getting Started.
@@ -37,7 +54,7 @@ Pass `--global` to opt into the legacy merged behavior (read `config.sources` an
 
 Use `npx analyzthis_design run-unchunked` for the legacy single-pass orchestrator.
 
-**npm:** [analyzthis_design](https://www.npmjs.com/package/analyzthis_design) · **Current version:** 2.3.1 · **Step-by-step guide:** [HOW-TO-USE.md](./HOW-TO-USE.md)
+**npm:** [analyzthis_design](https://www.npmjs.com/package/analyzthis_design) · **Current version:** 2.4.1 · **Step-by-step guide:** [HOW-TO-USE.md](./HOW-TO-USE.md)
 
 ---
 
@@ -63,7 +80,7 @@ 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 install --target <ide>` (or `npx analyzthis_design --target <ide>`).
 >
-> **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, **Claude Code**, and Windsurf during install. For Lovable, v0, Bolt, Replit, ChatGPT: run `npx analyzthis_design mcp --configure <tool>` for a config snippet.
+> **MCP (universal):** `npx analyzthis_design mcp` starts a local MCP server. Default catalog is **lite** (router + retrieve + session + receipt). Full 19 named tools: `ANALYZTHIS_MCP_CATALOG=full` or `mcp --catalog full`. Auto-configures for Cursor, Claude Desktop, **Claude Code**, and Windsurf during install. For Lovable, v0, Bolt, Replit, ChatGPT: run `npx analyzthis_design mcp --configure <tool>` for a config snippet.
 
 ### Install by target IDE
 
@@ -138,6 +155,9 @@ Invoke critique personas for targeted, already-grounded questions. For **wirefra
 | `/knowledge-bank` | Auto-populated from your connected vault (or from Kavi collect). All personas read this first. |
 | `/design-reference` | CSV reference data (colors, typography, UX guidelines, stacks, …) |
 | `/collect-knowledge` | Alias for `/kavi` |
+| `/accept` | Keep or skip the last persona note (yes / no). Local evolution — no CLI flags. |
+| `/share` | Send a correction to the package (preview, then yes). Redacted. |
+| `/receipt` | Inferred token receipt for this project. Not a bill. |
 
 ---
 
@@ -731,6 +751,10 @@ npx analyzthis_design status
 
 # Session (agentic)
 npx analyzthis_design session init|show|reset [--project id] [--all]
+npx analyzthis_design accept --keep [--persona zara]          # designer keep (slash: /accept yes)
+npx analyzthis_design accept --fix --because "one sentence"   # designer skip (slash: /accept no)
+npx analyzthis_design share                                   # preview notes for the package
+npx analyzthis_design share --send                            # send (slash: /share yes)
 npx analyzthis_design session accept --persona <id> [--reject] [--comment "..."] [--correction "..."] [--rating 1-5] [--tags a,b]
 
 # Persona feedback (v1.16)
@@ -870,7 +894,7 @@ skills/
 | **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) |
+| **MCP lite + full** | Default: router (`analyzthis_design`) + retrieve + session + receipt. Full 19 named tools behind `--catalog full`. |
 | **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

package/dist/bin/cli.js

@@ -60,6 +60,10 @@ Usage:
   session accept  Mark a persona's last output accepted, for training export
                   (--persona <id>, optional --reject to unmark)
                   Optional feedback: --comment, --correction, --rating 1-5, --tags a,b
+  accept          Designer keep / skip (same as /accept). --keep or --fix
+                  Optional: --persona, --because "one sentence", --liked (keep, not shipped)
+  share           Designer send-to-package (same as /share). Preview, then --send
+                  Optional: --because "one sentence", --persona
 
 ── Persona feedback commands ─────────────────────────────────
   feedback record   Record unhappiness or a correction for a persona output
@@ -75,6 +79,7 @@ Usage:
 ── Efficiency / cost commands ────────────────────────────────
   metrics             Print the last run's cost metrics (--all for every project)
   cost                Print the last run's $ cost from config.pricing (--all for every project)
+  receipt             Inferred token receipt for host (slash/MCP) turns — not a bill
   export-training     Write accepted-output JSONL pairs for LoRA prep
                       (--persona <id>, --all, --output <path>)
   feedback export     Write rejected + correction JSONL pairs (DPO / negative examples)
@@ -86,9 +91,11 @@ Usage:
 ── 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 claude    Write MCP config to Claude Desktop + Claude Code
   mcp --configure windsurf   Write MCP config to Windsurf
   mcp --configure <tool>    Print manual MCP config for any other tool
+  mcp --catalog lite|full   Lite (default): router + retrieve + session + receipt
+                            full: all 19 named tools. Or ANALYZTHIS_MCP_CATALOG=full
 
 ── Mood board commands ─────────────────────────────────────
   moodboard create --task <text>   Build a mood board from web + DS references
@@ -217,6 +224,10 @@ Usage:
   npx analyzthis_design devi respond --run ~/.analyzthis_design/runs/... --step 001-arjun --file out.md
   npx analyzthis_design run-unchunked --task "Review this screen" --provider anthropic
 
+  npx analyzthis_design accept --keep --persona zara
+  npx analyzthis_design accept --fix --persona zara --because "too much motion on the table"
+  npx analyzthis_design share
+  npx analyzthis_design share --send
   npx analyzthis_design session accept --persona arjun
   npx analyzthis_design session accept --persona arjun --reject \\
     --comment "Invented tokens not in our DS" \\
@@ -319,6 +330,11 @@ const budgetVal    = getFlag('budget');
 const sequentialFlag = flags.includes('--sequential');
 const maxChunksVal = getFlag('max-chunks');
 const unchunkedFlag = flags.includes('--unchunked');
+const keepFlag = flags.includes('--keep');
+const fixFlag = flags.includes('--fix') || flags.includes('--no');
+const likedFlag = flags.includes('--liked');
+const becauseVal = getFlag('because');
+const sendFlag = flags.includes('--send');
 
 // ─── Commands ────────────────────────────────────────────────────────────────
 
@@ -769,11 +785,12 @@ switch (cmd) {
   case 'mcp': {
     const mcpServer = require('../lib/mcp-server');
     const configureTarget = getFlag('configure');
+    const catalogVal = getFlag('catalog');
     if (configureTarget) {
-      mcpServer.writeMcpConfig(configureTarget);
+      mcpServer.writeMcpConfig(configureTarget, { catalog: catalogVal });
       break;
     }
-    mcpServer.startStdioServer();
+    mcpServer.startStdioServer(catalogVal);
     break;
   }
 
@@ -965,6 +982,8 @@ switch (cmd) {
       console.log(`    objections_raised: ${m.objections_raised ?? 0}`);
       console.log(`    objections_resolved: ${m.objections_resolved ?? 0}`);
       console.log(`    raj_escalations:   ${m.raj_escalations ?? 0}`);
+      console.log(`    host_turns:        ${(m.host_turns || []).length}`);
+      console.log(`    tokens_per_verdict: ${m.tokens_per_verdict ?? 'n/a'}`);
       const d = state.deliberation;
       if (d?.mode) {
         console.log(`    deliberation_mode: ${d.mode}, consensus=${d.consensus_reached}`);
@@ -981,6 +1000,129 @@ switch (cmd) {
     break;
   }
 
+  case 'receipt': {
+    const receipt = require('../lib/receipt');
+    console.log('\n' + receipt.report({ project: projectVal }) + '\n');
+    break;
+  }
+
+  case 'accept': {
+    const accept = require('../lib/accept');
+    const wantKeep = keepFlag || yesFlag;
+    const wantFix = fixFlag;
+    try {
+      if (wantKeep && wantFix) {
+        console.error('\n  ✗  Use --keep or --fix, not both.\n');
+        process.exit(1);
+      }
+      if (!wantKeep && !wantFix) {
+        const peek = accept.preview({ project: projectVal });
+        console.log('\n  Keep the last note?');
+        console.log('    Yes:  npx analyzthis_design accept --keep' + (peek.persona ? ` --persona ${peek.persona}` : ''));
+        console.log('    No:   npx analyzthis_design accept --fix --because "one sentence"');
+        if (peek.persona) console.log(`  Last persona: ${peek.persona}`);
+        else console.log('  Last persona: not sure — add --persona zara (or arjun, meera, …)');
+        console.log('');
+        break;
+      }
+      if (wantKeep) {
+        const result = accept.keep({
+          project: projectVal,
+          persona: personaVal,
+          comment: commentVal || becauseVal || '',
+          shipped: !likedFlag,
+          note: commentVal || '',
+        });
+        console.log(`\n✅ Kept ${result.persona}'s note.` + (result.shipped ? ' Marked as shipped for evolution.' : ' Saved as liked (not shipped).') + '\n');
+        break;
+      }
+      const result = accept.fix({
+        project: projectVal,
+        persona: personaVal,
+        because: becauseVal || commentVal || '',
+        correction: correctionVal || '',
+        rating: ratingVal,
+        tags: parseFeedbackTags(tagsVal),
+      });
+      console.log(`\n✅ Logged your fix for ${result.persona}. The team can learn from it.\n`);
+    } catch (err) {
+      if (err.code === 'NEED_PERSONA') {
+        console.error('\n  ✗  Which note? Add --persona zara (or arjun, meera, priya, noor, anuj, raj).\n');
+        process.exit(1);
+      }
+      if (err.code === 'NEED_BECAUSE') {
+        console.error('\n  ✗  Add one sentence: --because "what was wrong or what you did instead"\n');
+        process.exit(1);
+      }
+      console.error(`\n  ✗  ${err.message}\n`);
+      process.exit(1);
+    }
+
+    break;
+  }
+
+  case 'share': {
+    const share = require('../lib/share');
+    const acceptMod = require('../lib/accept');
+    const wantSend = sendFlag || yesFlag;
+    (async () => {
+      try {
+        if (!wantSend) {
+          if (becauseVal || commentVal) {
+            acceptMod.fix({
+              project: projectVal,
+              persona: personaVal,
+              because: becauseVal || commentVal,
+              correction: correctionVal || becauseVal || commentVal,
+            });
+          }
+          const peek = share.preview({ project: projectVal, persona: personaVal, all: allFlag });
+          if (!peek.count) {
+            console.log('\n  Nothing to send yet. After a critique: /accept no plus one sentence, then /share.\n');
+            return;
+          }
+          console.log(`\n  Ready to send ${peek.count} note(s) to the package (redacted — no folders, emails, or keys).`);
+          peek.rows.slice(0, 5).forEach((r) => {
+            console.log(`    • ${r.persona}: ${(r.comment || r.correction || '').slice(0, 100)}`);
+          });
+          if (peek.rows.length > 5) console.log(`    … and ${peek.rows.length - 5} more`);
+          console.log(peek.hasHttp ? '  Path: configured HTTP endpoint.' : '  Path: GitHub issue on joshirishi/analyzthis_design.');
+          console.log('  Send?  Run: npx analyzthis_design share --send\n');
+          return;
+        }
+        const result = await share.send({
+          project: projectVal,
+          persona: personaVal,
+          because: becauseVal || commentVal || '',
+          correction: correctionVal || '',
+          all: allFlag,
+        });
+        if (result.via === 'github-link') {
+          console.log(`\n  ${result.message}`);
+          console.log(`  ${result.url}\n`);
+          return;
+        }
+        console.log(`\n✅ ${result.message}` + (result.url ? `\n   ${result.url}` : '') + '\n');
+      } catch (err) {
+        if (err.code === 'NOTHING') {
+          console.error('\n  ✗  Nothing to send yet. /accept no plus one sentence, then /share.\n');
+          process.exit(1);
+        }
+        if (err.code === 'NEED_PERSONA') {
+          console.error('\n  ✗  Which note? Add --persona zara (or arjun, meera, priya, noor, anuj, raj).\n');
+          process.exit(1);
+        }
+        if (err.code === 'NEED_BECAUSE') {
+          console.error('\n  ✗  Add one sentence: --because "what was wrong or what you did instead"\n');
+          process.exit(1);
+        }
+        console.error(`\n  ✗  ${err.message}\n`);
+        process.exit(1);
+      }
+    })();
+    break;
+  }
+
   // ── Persona feedback (v1.16) ────────────────────────────────────────────
 
   case 'feedback': {

package/dist/lib/accept.js

@@ -0,0 +1,95 @@
+'use strict';
+
+/**
+ * Designer keep / skip for evolution.
+ * Slash /accept talks in yes/no. This module writes the session flags.
+ */
+
+var session = require('./session');
+var feedback = require('./feedback');
+var outcome = require('./outcome');
+
+var PERSONA_IDS = session.PERSONA_IDS;
+
+function resolvePersona(opts) {
+  var raw = String(opts.persona || '').toLowerCase().trim();
+  if (raw && PERSONA_IDS.indexOf(raw) === -1) {
+    var err = new Error('Unknown persona. Use: ' + PERSONA_IDS.join(', '));
+    err.code = 'BAD_PERSONA';
+    throw err;
+  }
+  var id = raw || session.inferLastPersona({ project: opts.project });
+  if (!id) {
+    var need = new Error('NEED_PERSONA');
+    need.code = 'NEED_PERSONA';
+    throw need;
+  }
+  return id;
+}
+
+function keep(opts) {
+  opts = opts || {};
+  var persona = resolvePersona(opts);
+  session.ensurePersonaOutput({
+    project: opts.project,
+    persona: persona,
+    text: opts.note,
+  });
+  session.markAccepted({ project: opts.project, persona: persona, accepted: true });
+  if (opts.comment) {
+    feedback.recordFeedback({
+      project: opts.project,
+      persona: persona,
+      satisfied: true,
+      rating: 5,
+      comment: opts.comment,
+      correction: '',
+      markRejected: false,
+    });
+  }
+  var shipped = opts.shipped !== false;
+  if (shipped) {
+    outcome.confirmOutcome({ project: opts.project, persona: persona, outcome: 'shipped' });
+  }
+  return { persona: persona, kept: true, shipped: shipped };
+}
+
+function fix(opts) {
+  opts = opts || {};
+  var persona = resolvePersona(opts);
+  var because = String(opts.because || opts.comment || '').trim();
+  var correction = String(opts.correction || because).trim();
+  if (!because) {
+    var need = new Error('NEED_BECAUSE');
+    need.code = 'NEED_BECAUSE';
+    throw need;
+  }
+  session.ensurePersonaOutput({
+    project: opts.project,
+    persona: persona,
+    text: opts.note,
+  });
+  feedback.recordFeedback({
+    project: opts.project,
+    persona: persona,
+    satisfied: false,
+    rating: opts.rating != null ? Number(opts.rating) : 2,
+    comment: because,
+    correction: correction,
+    tags: opts.tags || ['other'],
+    markRejected: true,
+  });
+  outcome.confirmOutcome({ project: opts.project, persona: persona, outcome: 'revised' });
+  return { persona: persona, kept: false, because: because };
+}
+
+function preview(opts) {
+  opts = opts || {};
+  var state = session.show({ project: opts.project });
+  return {
+    persona: session.inferLastPersona({ project: opts.project }),
+    hasSession: !!state,
+  };
+}
+
+module.exports = { keep, fix, preview, PERSONA_IDS };

package/dist/lib/chunk-run.js

@@ -172,6 +172,8 @@ async function runChunked(opts) {
         output_tokens_est: totalOutput,
         cost_usd: Number(totalCost.toFixed(6)),
         mode: 'chunked',
+        verdicts_this_run: 1,
+        tokens_per_verdict: totalInput || null,
         cache_hits: cacheHits,
         effort_log: results.map(function(r) {
           return {

package/dist/lib/feedback-submit.js

@@ -316,6 +316,8 @@ module.exports = {
   resolveSubmitConfig,
   submitFeedback,
   submitStatus,
+  collectUnsentEntries,
+  markEntriesSubmitted,
   loadConsent,
   saveConsent,
   revokeConsent,

package/dist/lib/install.js

@@ -33,6 +33,9 @@ const PROJECT_COMMANDS = [
   'design-critic',
   'getting-started',
   'devi',
+  'receipt',
+  'accept',
+  'share',
 ];
 
 const SKILLS = [
@@ -60,6 +63,9 @@ const SKILLS = [
   'design-personas',
   'design-reference',
   'knowledge-bank',
+  'receipt',
+  'accept',
+  'share',
 ];
 
 function getPackageVersion() {
@@ -127,6 +133,9 @@ function printWelcomeBanner(targetId, log = console.log) {
   log(`    ${p}design-critic            4-persona critique + composite score`);
   log(`    ${p}deliberation-protocol    adversarial review rules (objections, Raj)`);
   log(`    ${p}devi                     host LLM: voice personas when CLI has no API keys`);
+  log(`    ${p}accept                   keep or skip the last note (yes / no) — local evolution`);
+  log(`    ${p}share                    send a correction to the package (preview, then yes)`);
+  log(`    ${p}receipt                  inferred tokens for this project (not a bill)`);
 
   log('');
   log('  CLI (host mode — no API keys):');