@muggleai/works 4.9.0 → 4.9.1

package/dist/plugin/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "muggle",
   "description": "Run real-browser end-to-end (E2E) acceptance tests on your web app from any AI coding agent. Generate test scripts from plain English, replay them on localhost, capture screenshots, and validate user flows like signup, checkout, and dashboards. Works across Claude Code, Cursor, Codex, and Windsurf.",
-  "version": "4.9.0",
+  "version": "4.9.1",
   "author": {
     "name": "Muggle AI",
     "email": "support@muggle-ai.com"

package/dist/plugin/.cursor-plugin/plugin.json

@@ -2,7 +2,7 @@
   "name": "muggle",
   "displayName": "Muggle AI",
   "description": "Ship quality products with AI-powered end-to-end (E2E) acceptance testing that validates your web app like a real user — from Claude Code and Cursor to PR.",
-  "version": "4.9.0",
+  "version": "4.9.1",
   "author": {
     "name": "Muggle AI",
     "email": "support@muggle-ai.com"

package/dist/plugin/skills/muggle-upgrade/SKILL.md

@@ -24,10 +24,18 @@ Update all Muggle AI components to the latest published version. This means **bo
 4. Run `muggle upgrade` to pull the Electron runner version that the (now-latest) CLI expects.
    - Note: `muggle upgrade` only manages the Electron runner — it does NOT upgrade the CLI npm package. That is why step 3 must run first.
 
-5. Run `/muggle:muggle-status` again to confirm everything is healthy after upgrade.
+5. **Reload plugins** — the npm install (step 3) triggers a postinstall script that updates the plugin cache at `~/.claude/plugins/cache/`, but Claude Code only picks up new skills/agents/hooks after a reload. Tell the user:
+
+   > Run **`/reload-plugins`** to load the updated skills, agents, and hooks.
+
+   Wait for the user to confirm they've reloaded before proceeding.
+
+6. Run `/muggle:muggle-status` again to confirm everything is healthy after upgrade.
 
 ## Output
 
 Show a before/after table for **CLI**, **Electron runner**, **MCP server**, and **Auth**. Call out any version that did not change so the user understands what shipped vs what was already current.
 
+If any component upgraded, always end with the `/reload-plugins` reminder — even if the user doesn't need new features right away, stale cached skills can cause confusing behavior.
+
 If the upgrade fails at any step, report the error and suggest running `/muggle:muggle-repair`.

package/dist/release-manifest.json

@@ -1,7 +1,7 @@
 {
-  "release": "4.9.0",
-  "buildId": "run-25-1",
-  "commitSha": "5562e835de433b7edc6cfe4b2087cb9a3ad6a696",
-  "buildTime": "2026-04-19T08:20:59Z",
+  "release": "4.9.1",
+  "buildId": "run-26-1",
+  "commitSha": "cffcf26eaf2b00b3b1e55dcd509db7b9d8854a0d",
+  "buildTime": "2026-04-19T08:47:53Z",
   "serviceName": "muggle-ai-works-mcp"
 }

package/package.json

@@ -1,7 +1,7 @@
 {
     "name": "@muggleai/works",
     "mcpName": "io.github.multiplex-ai/muggle",
-    "version": "4.9.0",
+    "version": "4.9.1",
     "description": "Ship quality products with AI-powered E2E acceptance testing that validates your web app like a real user — from Claude Code and Cursor to PR.",
     "type": "module",
     "main": "dist/index.js",

package/plugin/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "muggle",
   "description": "Run real-browser end-to-end (E2E) acceptance tests on your web app from any AI coding agent. Generate test scripts from plain English, replay them on localhost, capture screenshots, and validate user flows like signup, checkout, and dashboards. Works across Claude Code, Cursor, Codex, and Windsurf.",
-  "version": "4.9.0",
+  "version": "4.9.1",
   "author": {
     "name": "Muggle AI",
     "email": "support@muggle-ai.com"

package/plugin/.cursor-plugin/plugin.json

@@ -2,7 +2,7 @@
   "name": "muggle",
   "displayName": "Muggle AI",
   "description": "Ship quality products with AI-powered end-to-end (E2E) acceptance testing that validates your web app like a real user — from Claude Code and Cursor to PR.",
-  "version": "4.9.0",
+  "version": "4.9.1",
   "author": {
     "name": "Muggle AI",
     "email": "support@muggle-ai.com"

package/plugin/skills/muggle-upgrade/SKILL.md

@@ -24,10 +24,18 @@ Update all Muggle AI components to the latest published version. This means **bo
 4. Run `muggle upgrade` to pull the Electron runner version that the (now-latest) CLI expects.
    - Note: `muggle upgrade` only manages the Electron runner — it does NOT upgrade the CLI npm package. That is why step 3 must run first.
 
-5. Run `/muggle:muggle-status` again to confirm everything is healthy after upgrade.
+5. **Reload plugins** — the npm install (step 3) triggers a postinstall script that updates the plugin cache at `~/.claude/plugins/cache/`, but Claude Code only picks up new skills/agents/hooks after a reload. Tell the user:
+
+   > Run **`/reload-plugins`** to load the updated skills, agents, and hooks.
+
+   Wait for the user to confirm they've reloaded before proceeding.
+
+6. Run `/muggle:muggle-status` again to confirm everything is healthy after upgrade.
 
 ## Output
 
 Show a before/after table for **CLI**, **Electron runner**, **MCP server**, and **Auth**. Call out any version that did not change so the user understands what shipped vs what was already current.
 
+If any component upgraded, always end with the `/reload-plugins` reminder — even if the user doesn't need new features right away, stale cached skills can cause confusing behavior.
+
 If the upgrade fails at any step, report the error and suggest running `/muggle:muggle-repair`.