prizmkit 1.1.39 → 1.1.41

package/bundled/skills/prizmkit-deploy/references/cloud-platform-deploy.md

@@ -0,0 +1,93 @@
+# Cloud Platform Deployment Path
+
+Guided deployment for Vercel, Netlify, Fly.io, and similar cloud platforms. Full automation isn't available — these platforms require browser-based authentication — but the skill provides structured CLI assistance.
+
+## Detect and Validate
+
+1. Check if the platform CLI is installed: `vercel --version`, `netlify --version`, `fly version`.
+2. If missing, guide the user to install: `npm install -g vercel` or link to docs.
+3. Check authentication: `vercel whoami`, `netlify status`. If not logged in, guide the user through `vercel login`.
+4. Read the platform config file (`vercel.json`, `netlify.toml`, `fly.toml`) to understand existing settings.
+
+## Generate Configuration
+
+1. If no platform config file exists, generate one based on project detection:
+   - **Next.js on Vercel**: minimal config — Vercel auto-detects Next.js. Generate `vercel.json` only if custom rewrites/redirects are needed.
+   - **Static site on Netlify**: generate `netlify.toml` with build command and publish directory.
+   - **Any on Fly.io**: generate `fly.toml` with app name, builder, and HTTP service config.
+2. Set environment variables via the platform CLI: `vercel env add`, `netlify env:set`.
+3. Document all env vars needed (from Discovery Step 1 scan).
+
+## Deploy and Verify
+
+1. Run the platform deploy command: `vercel deploy --prod`, `netlify deploy --prod`, `fly deploy`.
+2. If the command requires interactive input, run it and show output to the user.
+3. After deploy, run health checks against the production URL.
+4. Write a deploy-history event recording: platform, project name, deploy URL, commit SHA, timestamp.
+
+## Operations
+
+| Command | Vercel | Netlify | Fly.io |
+|---------|--------|---------|--------|
+| status | `vercel list` | `netlify status` | `fly status` |
+| logs | `vercel logs` | `netlify logs` | `fly logs` |
+| rollback | `vercel rollback` | `netlify rollback` | `fly rollback` |
+| env | `vercel env ls` | `netlify env:list` | `fly secrets list` |
+
+Platform rollback is instant — no release-based rollback needed.
+
+## Platform-Specific Patterns
+
+### Vercel
+
+Vercel auto-detects Next.js projects — no config file required for basic deployments. Generate `vercel.json` only for custom rewrites, redirects, or headers.
+
+Key behaviors:
+- Next.js: framework auto-detected, build command and output directory inferred automatically
+- Static sites: set build command and output directory via `vercel.json` or CLI
+- Env vars: `vercel env add <KEY>` (supports `production`, `preview`, `development` environments)
+- Deploy preview: every branch gets a preview URL automatically (if connected via GitHub)
+
+### Netlify
+
+Netlify requires explicit build and publish configuration. Use `netlify.toml`:
+
+```toml
+[build]
+  command = "npm run build"
+  publish = "dist"
+
+[[redirects]]
+  from = "/*"
+  to = "/index.html"
+  status = 200
+```
+
+Key behaviors:
+- SPA redirects: the catch-all redirect above is essential for client-side routing
+- Env vars: `netlify env:set <KEY> <VALUE>` (per-context: `production`, `deploy-preview`, `branch-deploy`)
+- Branch deploys: every branch gets a deploy-preview URL automatically (if connected via GitHub)
+
+### Fly.io
+
+Fly.io requires a `fly.toml` with app name, builder, and HTTP service config:
+
+```toml
+app = "<app-name>"
+primary_region = "lhr"
+
+[build]
+  builder = "dockerfile"
+
+[http_service]
+  internal_port = 3000
+  force_https = true
+```
+
+Key behaviors:
+- Builder: `dockerfile` (default, uses Dockerfile) or `static` (static site hosting)
+- Secrets: `fly secrets set <KEY>=<VALUE>` for runtime environment variables
+- Scale: `fly scale count <N>` to adjust VM instances
+- Volumes: for persistent data, configure `[mounts]` in fly.toml
+
+**Note**: These are minimum-viable platform references; browser-based authentication remains a user-action step. Enriched platform coverage is planned for future iterations.

package/bundled/skills/prizmkit-deploy/references/deploy-config-schema.md

@@ -0,0 +1,147 @@
+# deploy.config.json Schema
+
+This file is the machine-readable deployment configuration. Always read it before executing any deploy operation.
+
+## Top-Level Structure
+
+```json
+{
+  "version": 1,
+  "project": "project-name",
+  "deploymentMode": "ssh",
+  "defaults": { ... },
+  "environments": { ... },
+  "servers": [ ... ],
+  "repository": { ... },
+  "apps": [ ... ],
+  "nginx": { ... },
+  "env": { ... }
+}
+```
+
+## defaults
+
+```json
+{
+  "releaseRetention": 5,
+  "credentialMode": "ai-assisted|user-managed",
+  "secretStorage": "ask-every-time|encrypted-local|plaintext-local|user-managed-on-server-only",
+  "rollbackOnFailure": true,
+  "headlessDefaultEnvironment": "test"
+}
+```
+
+## environments
+
+Keyed by environment name. Each entry:
+```json
+{
+  "dev": {
+    "server": "server-id",
+    "allowHeadless": true,
+    "confirmBeforeDeploy": false
+  }
+}
+```
+
+## servers
+
+Array of server objects:
+```json
+{
+  "id": "prod-1",
+  "host": "IP or hostname",
+  "port": 22,
+  "bootstrapUser": "root",
+  "runtimeUser": "deploy",
+  "roles": ["web"],
+  "validated": {
+    "ssh": true|false,
+    "bootstrap": true|false,
+    "runtimeUser": true|false,
+    "tools": {
+      "node": "version",
+      "npm": "version",
+      "pm2": "version",
+      "nginx": "version",
+      "git": "version"
+    },
+    "directories": true|false,
+    "deployKey": true|false
+  }
+}
+```
+
+## repository
+
+```json
+{
+  "url": "git@github.com:owner/repo.git",
+  "branch": "master",
+  "auth": "deploy-key|ssh-agent|token",
+  "validated": {
+    "clone": true|false
+  }
+}
+```
+
+## apps
+
+Array of app objects:
+```json
+{
+  "id": "web",
+  "path": ".",
+  "runtime": "pm2",
+  "packageManager": "npm",
+  "installCommand": "npm ci",
+  "buildCommand": "npm run build",
+  "startCommand": "npm run start",
+  "ports": {
+    "blue": 3101,
+    "green": 3102
+  },
+  "healthChecks": [
+    { "name": "home", "url": "/", "expectedStatus": [200] },
+    { "name": "login", "url": "/login", "expectedStatus": [200, 302] }
+  ],
+  "activeColor": "blue",
+  "pm2Process": "prizm-ideas-blue"
+}
+```
+
+## nginx
+
+```json
+{
+  "enabled": true,
+  "managed": true,
+  "firstChangeRequiresConfirmation": true,
+  "domain": null,
+  "ipFallback": true,
+  "currentUpstream": "127.0.0.1:3101"
+}
+```
+
+## env
+
+```json
+{
+  "strategy": "ai-assisted|user-managed",
+  "required": ["VAR_NAME"],
+  "secrets": ["SECRET_NAME"],
+  "validated": {
+    "allRequiredPresent": true|false
+  }
+}
+```
+
+## Validation Rules
+
+- `version` must be present (always 1 for first version)
+- `servers` must have at least one entry with host and bootstrapUser
+- `repository.url` must be present
+- `apps` must have at least one entry
+- `apps[*].ports.blue` and `apps[*].ports.green` must differ
+- `apps[*].healthChecks` should have at least one entry
+- Environment referenced in `environments` must have a matching server in `servers`

package/bundled/skills/prizmkit-deploy/references/deploy-history-schema.md

@@ -0,0 +1,62 @@
+# Deploy History Record Schema
+
+Each event in `.prizmkit/deploy/deploy-history/<id>.json` follows this schema:
+
+```json
+{
+  "eventId": "<releaseId or event id>",
+  "eventType": "deploy|rollback|status|validation|failed-deploy|user-aborted|takeover|adapter-gap",
+  "timestamp": "<ISO 8601>",
+  "serverId": "<server id from deploy.config.json>",
+  "appIds": ["<app ids involved>"],
+  "branch": "<git branch>",
+  "commitSha": "<full or short commit SHA>",
+  "releasePath": "<full server path, e.g. /var/www/prizm-ideas/releases/20260430-22783a3>",
+  "previousReleasePath": "<previous release path or null for first deploy>",
+  "targetPort": 3101,
+  "targetColor": "blue|green",
+  "previousPort": 3102,
+  "phases": {
+    "preflight": "success|failed|skipped",
+    "prepareRelease": "success|failed|skipped",
+    "fetchCode": "success|failed|skipped",
+    "installDependencies": "success|failed|skipped",
+    "build": "success|failed|skipped",
+    "stageRuntime": "success|failed|skipped",
+    "healthCheck": "success|failed|skipped",
+    "switchTraffic": "success|failed|skipped",
+    "verifyLive": "success|failed|skipped",
+    "cleanupOldReleases": "success|failed|skipped",
+    "recordHistory": "success|failed|skipped"
+  },
+  "healthCheckResults": [
+    {
+      "name": "home",
+      "url": "/",
+      "expected": [200],
+      "actual": 200,
+      "pass": true
+    }
+  ],
+  "rollbackResult": null,
+  "logPath": "<server log path>",
+  "operatorMode": "ai-assisted|user-managed",
+  "notes": "<human-readable summary of what happened>"
+}
+```
+
+## Field Notes
+
+- `eventId`: Use `<releaseId>` for deploy events, `<releaseId>-rollback` for rollbacks.
+- `eventType`: Use `failed-deploy` when deploy fails before traffic switch, `deploy` when it succeeds. Use `adapter-gap` when no adapter exists for the detected project type or target — include `detectedProjectType`, `missingAdapter`, and `fallbackOutput` in the record.
+- `phases`: Only include phases that were attempted. Skip phases that were never reached.
+- `healthCheckResults`: Include all configured health checks. `pass` = actual status matches one of the expected status codes.
+- `rollbackResult`: `null` for non-rollback events, `"success"` or `"failed"` for rollbacks.
+- `notes`: Keep concise but include any anomalies or manual interventions.
+
+## What NOT to record
+
+- Raw secret values or API keys — never.
+- Unsalted hashes of secret values — inferable with rainbow tables.
+- Passphrases or decryption keys — even if hashed.
+- Full environment variable values — presence metadata only (e.g., `{"SUPABASE_KEY": {"present": true}}`).

package/bundled/skills/prizmkit-deploy/references/docker-deploy.md

@@ -0,0 +1,31 @@
+# Docker Deployment Path
+
+Guided deployment when a `Dockerfile` or `docker-compose.yml` is detected, or the user requests Docker deployment.
+
+## Detect and Configure
+
+1. Read `Dockerfile` — extract base image, exposed ports, build steps.
+2. Read `docker-compose.yml` if present — extract services, volumes, environment, ports.
+3. Identify image name: from compose project name or repo directory name.
+4. Identify port mappings: from `EXPOSE`, `ports:` in compose, or ask the user.
+
+## Build and Deploy
+
+1. Build: `docker build -t <project>:<releaseId> .` or `docker compose build`.
+2. Check for running containers with the same name: `docker ps -a --filter name=<project>`.
+3. If a previous container exists:
+   - For blue/green on a server with Nginx: start new container on different port, health check, switch upstream.
+   - For single-container setup: stop old, start new — warn about brief downtime.
+4. Start: `docker run -d --name <project>-<releaseId> -p <port>:<port> <project>:<releaseId>` or `docker compose up -d`.
+5. Health check the new container.
+6. Write deploy-history event.
+
+## Operations
+
+| Command | Docker CLI |
+|---------|-----------|
+| status | `docker ps --filter name=<project>` |
+| logs | `docker logs <container-name> --tail 100` |
+| restart | `docker restart <container-name>` |
+| rollback | `docker stop <new-container> && docker start <old-container>` |
+| cleanup | `docker image prune -a --filter "label=project=<project>"` |

package/bundled/skills/prizmkit-deploy/references/nginx-blue-green.md

@@ -0,0 +1,59 @@
+# Nginx Blue/Green Configuration Template
+
+## Server Block Template
+
+```nginx
+# PrizmKit Managed: <project> — DO NOT EDIT MANUALLY
+upstream <project>_backend {
+    server 127.0.0.1:<activePort>;
+}
+
+server {
+    listen 80 default_server;
+    server_name _;
+
+    # PrizmKit managed marker: <project>
+    location / {
+        proxy_pass http://<project>_backend;
+        proxy_http_version 1.1;
+        proxy_set_header Host $host;
+        proxy_set_header X-Real-IP $remote_addr;
+        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+        proxy_set_header X-Forwarded-Proto $scheme;
+    }
+}
+```
+
+## Traffic Switch Procedure
+
+When switching from one color to another:
+
+1. Update the `upstream` block: change `server 127.0.0.1:<oldPort>` to `server 127.0.0.1:<newPort>`
+2. Run `nginx -t` to validate syntax
+3. If syntax check passes: `systemctl reload nginx`
+4. If syntax check fails: DO NOT reload. Abort the switch. Report the error.
+
+## Managed Marker
+
+All PrizmKit-generated Nginx config must contain:
+```
+# PrizmKit Managed: <project> — DO NOT EDIT MANUALLY
+```
+
+Before modifying any server block that lacks this marker, ask for user confirmation.
+
+## First-Time Setup
+
+- Disable default nginx site: `rm -f /etc/nginx/sites-enabled/default`
+- Create new config: `/etc/nginx/sites-available/<project>`
+- Symlink: `ln -sf /etc/nginx/sites-available/<project> /etc/nginx/sites-enabled/<project>`
+- Test: `nginx -t`
+- Reload: `systemctl reload nginx`
+
+## Rediscovery of Active Port
+
+If `deploy-metadata.json` is missing, rediscover the active upstream port from Nginx config:
+```
+grep "server 127.0.0.1:" /etc/nginx/sites-available/<project>
+```
+Then match the port against configured blue/green ports to determine active color.

package/bundled/skills/prizmkit-init/SKILL.md

@@ -138,7 +138,6 @@ Detect database and deployment signals, then ask 1-2 brief questions. This phase
      - **Target**: [platform name or "undecided"]
      ```
      → This is intentionally minimal (Quick Scan). Full conventions and deployment details will be added by app-planner or prizmkit-deploy later.
-   - Create `.prizmkit/deploy.md` skeleton from `prizmkit-deploy` template if it does not exist, pre-filling known sections (Prerequisites, basic deployment method)
    - If user selects "Skip — decide later" for BOTH topics: write deferred marker instead:
      ```markdown
      ### Infrastructure
@@ -265,7 +264,6 @@ Infrastructure Quick Scan:
   Database: PostgreSQL (Prisma) — detected from dependencies
   Deployment: Vercel — detected from vercel.json
   → Written to CLAUDE.md ### Infrastructure
-  → Created .prizmkit/deploy.md skeleton
 
 Modules discovered:
   src/routes/     → .prizm-docs/routes.prizm (12 files)

package/bundled/skills/prizmkit-plan/SKILL.md

@@ -68,9 +68,6 @@ A universal spec + plan generator. Takes a natural-language description of ANY d
    - Behavior preservation strategy (if the task modifies existing behavior — include what must remain unchanged and how to verify)
 5. Cross-check: every goal in spec.md maps to plan components — unmapped goals = coverage gaps
 6. Check alignment with `.prizm-docs/root.prizm` RULES section
-7. **Deployment strategy check** (skip if no deployment impact):
-   - Read `.prizmkit/config.json` `deploy_strategy` field
-   - No strategy and new infra needed → ask user, write to config.json
 
 ### Phase 2: Task Generation (plan.md → Tasks section)
 

package/bundled/skills/recovery-workflow/SKILL.md

@@ -65,9 +65,13 @@ recovery-workflow
   │   ├── Based on artifact presence → infer current phase
   │   └── No match → reject and guide user
   │
-  ├── Phase 1: Report + user choice
-  │   ├── Display detection results
+  ├── Phase 1: Diagnose + report + user choice
+  │   ├── Check branch and working tree state
+  │   ├── Scan all pipelines for failed/in-progress tasks
+  │   ├── Find residual dev branches from failed tasks
+  │   ├── Display diagnosis + detection results
   │   ├── If code changes exist → run test suite
+  │   ├── If multiple failed tasks → ask user which to recover
   │   └── User chooses: run-recovery.sh (recommended) | interactive | start fresh
   │
   └── Phase 2: Execute remaining steps
@@ -119,9 +123,73 @@ To start a new workflow:
 
 ---
 
-## Phase 1: Report + User Confirmation
-
-**Goal**: Show the user what was found and get confirmation before executing.
+## Phase 1: Diagnose + Report + User Confirmation
+
+**Goal**: Assess workspace health, identify failed tasks across all pipelines, and present recovery options.
+
+### 1.0 Workspace & Failure Diagnosis
+
+Before showing the recovery report, run a comprehensive diagnosis:
+
+1. **Check current branch and working tree**:
+   ```bash
+   git branch --show-current
+   git status --porcelain | head -10
+   ```
+   Report: which branch is active, whether there are uncommitted changes.
+
+2. **Scan all pipelines for failed/in-progress tasks**:
+   ```bash
+   # Feature pipeline
+   python3 dev-pipeline/scripts/update-feature-status.py \
+     --feature-list .prizmkit/plans/feature-list.json \
+     --state-dir .prizmkit/state/features \
+     --action status 2>/dev/null
+
+   # Bugfix pipeline
+   python3 dev-pipeline/scripts/update-bug-status.py \
+     --bug-list .prizmkit/plans/bug-fix-list.json \
+     --state-dir .prizmkit/state/bugfix \
+     --action status 2>/dev/null
+
+   # Refactor pipeline
+   python3 dev-pipeline/scripts/update-refactor-status.py \
+     --refactor-list .prizmkit/plans/refactor-list.json \
+     --state-dir .prizmkit/state/refactor \
+     --action status 2>/dev/null
+   ```
+   For each pipeline that has state, extract: total tasks, completed, failed, in-progress, pending.
+
+3. **Find residual dev branches** from failed/interrupted tasks:
+   ```bash
+   git branch --list 'dev/*' 'feat/*' 'fix/*' 'bugfix/*' 'refactor/*'
+   ```
+   Cross-reference with failed task IDs to identify which branches belong to which failed tasks.
+
+4. **Present diagnosis summary** — show all findings before the recovery report:
+   ```
+   ═══════════════════════════════════════════════════
+     Workspace Diagnosis
+   ═══════════════════════════════════════════════════
+
+     Branch:       fix/B-001-login-crash
+     Working tree: 3 uncommitted changes
+
+     Feature pipeline:  2 completed, 1 failed (F-003), 2 pending
+     Bugfix pipeline:   1 completed, 1 failed (B-002), 0 pending
+     Refactor pipeline: (no state found)
+
+     Residual branches:
+       dev/F-003-payment-integration-202604201030
+       fix/B-002-encoding-bug
+
+     Failed tasks:
+       F-003: Payment integration    [FAILED] → branch: dev/F-003-...
+       B-002: CSV encoding bug       [FAILED] → branch: fix/B-002-...
+   ═══════════════════════════════════════════════════
+   ```
+
+   If no pipelines have state and no failed tasks are found, skip to 1.1 (standard recovery report).
 
 ### 1.1 Display Detection Report
 
@@ -160,7 +228,28 @@ Include test results in the report:
 - How many tests pass/fail
 - If failures exist — which tests and why
 
-### 1.3 Ask User to Choose Recovery Approach
+### 1.3 Select Recovery Target (if multiple failed tasks)
+
+If the diagnosis in 1.0 found **multiple failed/interrupted tasks** across pipelines, ask the user which one to recover first before proceeding:
+
+```
+AskUserQuestion:
+  question: "Multiple failed/interrupted tasks found. Which would you like to recover?"
+  header: "Target"
+  options:
+    - label: "F-003: Payment integration"
+      description: "Feature pipeline — FAILED — branch: dev/F-003-payment-integration-202604201030"
+    - label: "B-002: CSV encoding bug"
+      description: "Bugfix pipeline — FAILED — branch: fix/B-002-encoding-bug"
+    - label: "Recover all sequentially"
+      description: "Recover each failed task one by one in priority order"
+```
+
+Generate the options dynamically from the diagnosis results. Include task ID, title, pipeline type, status, and branch name.
+
+If only one failed/interrupted task is found, skip this step — proceed directly to 1.4 with that task as the recovery target.
+
+### 1.4 Ask User to Choose Recovery Approach
 
 **User choice required (mandatory)** — Use `AskUserQuestion` to present interactive selectable options. **NEVER skip this step. NEVER choose for the user.**
 
@@ -208,7 +297,7 @@ End this skill.
 
 **NEVER proceed to Phase 2 without explicit user selection via `AskUserQuestion`. Do NOT render options as plain text — the user must be able to click/select.**
 
-**CHECKPOINT CP-REC-1**: User chose recovery approach.
+**CHECKPOINT CP-REC-1**: User chose recovery target and approach.
 
 ---
 

package/bundled/skills/refactor-pipeline-launcher/SKILL.md

@@ -49,10 +49,14 @@ Before any action, validate:
 2. **For start**: `.prizmkit/plans/refactor-list.json` must exist in `.prizmkit/plans/` (or user-specified path)
 3. **Dependencies**: `jq`, `python3`, AI CLI (`cbc` or `claude`) must be in PATH
 4. **Python version**: Requires Python 3.8+ for dev-pipeline scripts
+5. **Browser tools** (optional): If any refactor has `browser_interaction` field, check the corresponding tool is available. Refactors may specify `tool: "playwright-cli"`, `tool: "opencli"`, or `tool: "auto"` (AI chooses at runtime).
 
 Quick check:
 ```bash
 command -v jq && command -v python3 && (command -v cbc || command -v claude) && echo "All dependencies OK"
+# Optional: browser interaction support (check both tools — refactors may use either)
+command -v playwright-cli && echo "playwright-cli OK" || echo "playwright-cli not found (playwright browser verification will be skipped)"
+command -v opencli && echo "opencli OK" || echo "opencli not found (opencli browser verification will be skipped)"
 ```
 
 If `.prizmkit/plans/refactor-list.json` is missing, inform user:
@@ -66,6 +70,8 @@ Detect user intent from their message, then follow the corresponding workflow:
 
 #### Intent A: Start Pipeline
 
+> **Execution model**: The pipeline processes refactor tasks **sequentially** (one at a time, in priority order). The `dependencies` field in refactor-list.json is reserved for future parallel execution support and does NOT affect current execution order.
+
 1. **Check prerequisites**:
    ```bash
    ls .prizmkit/plans/refactor-list.json 2>/dev/null && echo "Found" || echo "Missing"
@@ -144,17 +150,37 @@ Detect user intent from their message, then follow the corresponding workflow:
    - 1
    - 5
 
-   **Question 3 — Session timeout** (multiSelect: false):
+   **Question 3 — Strict behavior check** (multiSelect: false):
+   - On (default) — Run full test suite after each refactor task to verify behavior preservation
+   - Off — Skip post-task test verification (faster but riskier)
+
+   **Question 4 — Advanced config?** (multiSelect: false):
+   - No (default) — Use defaults for critic review, session timeout, and failure behavior
+   - Yes — Configure critic review, session timeout, and stop-on-failure options
+
+   Note: Refactor filter defaults to all refactor items (by priority order). If the user selects "Other" on any option, handle their custom input.
+
+   **If user chose "Yes" to Advanced config**, ask a second round of `AskUserQuestion`:
+
+   **Question 1 — Session timeout** (multiSelect: false):
    - None (default) — No timeout
    - 30 min — `SESSION_TIMEOUT=1800`
    - 1 hour — `SESSION_TIMEOUT=3600`
    - 2 hours — `SESSION_TIMEOUT=7200`
 
-   **Question 4 — Strict behavior check** (multiSelect: false):
-   - On (default) — Run full test suite after each refactor task to verify behavior preservation
-   - Off — Skip post-task test verification (faster but riskier)
+   **Question 2 — Stop on failure** (multiSelect: false):
+   - Off (default) — Pipeline continues to next task after failure
+   - On — Pipeline halts immediately when a task exhausts all retries (`STOP_ON_FAILURE=1`)
 
-   Note: Refactor filter defaults to all refactor items (by priority order). If the user selects "Other" on any option, handle their custom input.
+   **Question 3 — Critic review** (multiSelect: false):
+   - Off (default) — Skip adversarial review
+   - On — Enable adversarial critic review: an independent AI agent reviews the refactor plan for completeness and the implementation for regressions, missed edge cases, and behavior violations. Adds ~5-10 min per refactor task.
+
+   **Question 4 — Deploy after completion?** (multiSelect: false):
+   - No (default) — Skip deployment after pipeline completes
+   - Yes — Run /prizmkit-deploy automatically after all refactors complete successfully (`ENABLE_DEPLOY=1`). Deployment is blocked if any refactor did not complete successfully (status not 'completed' or manually 'skipped').
+
+   Default Critic to Off unless refactor items have `priority: "critical"` (in which case default to On).
 
    **Environment variable mapping** (for translating user responses → env vars):
 
@@ -163,9 +189,12 @@ Detect user intent from their message, then follow the corresponding workflow:
    | Verbose: On | `VERBOSE=1` |
    | Verbose: Off | `VERBOSE=0` |
    | Max retries: N | `MAX_RETRIES=N` |
-   | Timeout: value | `SESSION_TIMEOUT=<seconds>` |
    | Strict behavior: On | `STRICT_BEHAVIOR_CHECK=1` |
    | Strict behavior: Off | `STRICT_BEHAVIOR_CHECK=0` |
+   | Critic: On | `ENABLE_CRITIC=true` |
+   | Timeout: value | `SESSION_TIMEOUT=<seconds>` |
+   | Stop on failure: On | `STOP_ON_FAILURE=1` |
+   | Deploy: Yes | `ENABLE_DEPLOY=1` |
 
    **Advanced environment variables** (not exposed in interactive menu, pass via `--env`):
 
@@ -179,7 +208,6 @@ Detect user intent from their message, then follow the corresponding workflow:
    | `LOG_CLEANUP_ENABLED` | `1` | Run periodic log cleanup (`0` to disable) |
    | `LOG_RETENTION_DAYS` | `14` | Delete logs older than N days |
    | `LOG_MAX_TOTAL_MB` | `1024` | Keep total logs under N MB via oldest-first cleanup |
-   | `STOP_ON_FAILURE` | `0` | Stop pipeline when a task exhausts all retries (`1` to stop immediately) |
 
    ⚠️ STOP HERE and wait for user response before continuing to step 7.
 
@@ -191,7 +219,7 @@ Detect user intent from their message, then follow the corresponding workflow:
    ```
    With all options:
    ```bash
-   VERBOSE=1 STRICT_BEHAVIOR_CHECK=1 MAX_RETRIES=5 SESSION_TIMEOUT=3600 \
+   VERBOSE=1 STRICT_BEHAVIOR_CHECK=1 MAX_RETRIES=5 SESSION_TIMEOUT=3600 ENABLE_DEPLOY=1 \
      dev-pipeline/run-refactor.sh run .prizmkit/plans/refactor-list.json
    ```
 
@@ -202,7 +230,7 @@ Detect user intent from their message, then follow the corresponding workflow:
    With all options:
    ```bash
    dev-pipeline/launch-refactor-daemon.sh start .prizmkit/plans/refactor-list.json \
-     --env "VERBOSE=1 STRICT_BEHAVIOR_CHECK=1 MAX_RETRIES=5"
+     --env "VERBOSE=1 STRICT_BEHAVIOR_CHECK=1 MAX_RETRIES=5 ENABLE_DEPLOY=1"
    ```
 
    **Manual mode**: Print the assembled command(s) and **stop here**. Do not execute anything. Do not proceed to step 8.
@@ -342,6 +370,9 @@ Notes:
 | Launch failed (process died immediately) | Show last 20 lines of log: `tail -20 .prizmkit/state/refactor/pipeline-daemon.log` |
 | Refactor stuck/blocked | Use `reset-refactor.sh <R-XXX> --clean --run` for a fresh retry |
 | All refactors blocked/failed | Show status, suggest recovery: `dev-pipeline/reset-refactor.sh <R-XXX> --clean --run .prizmkit/plans/refactor-list.json` |
+| `playwright-cli` not installed | Browser verification skipped for playwright refactors (non-blocking). Suggest: `npm install -g @playwright/cli@latest && playwright-cli install --skills` |
+| `opencli` not installed | Browser verification skipped for opencli refactors (non-blocking). Install opencli for Chrome session-based browser verification |
+| Deploy session failed | Pipeline completed but deploy session exited non-zero. Check `.prizmkit/state/refactor/deploy/<session_id>/logs/session.log`. Retry manually: `/prizmkit-deploy`. |
 | Permission denied on script | Run `chmod +x dev-pipeline/launch-refactor-daemon.sh dev-pipeline/run-refactor.sh` |
 
 ### Integration Notes

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "prizmkit",
-  "version": "1.1.39",
+  "version": "1.1.41",
   "description": "Create a new PrizmKit-powered project with clean initialization — no framework dev files, just what you need.",
   "type": "module",
   "bin": {