@allenpan2026/harshjudge 0.4.1 → 0.4.2

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "harshjudge",
-  "version": "0.4.1",
+  "version": "0.4.2",
   "description": "AI-native E2E testing orchestration for Claude Code",
   "author": {
     "name": "Allen Pan"

package/README.md

@@ -34,7 +34,10 @@ harshjudge init my-app
 
 - **Node.js**: 18+ LTS
 - **Claude Code**: Latest version
-- **Playwright MCP Server**: For browser automation (screenshots, navigation, clicks)
+- **A browser automation tool** (any one of):
+  - Playwright MCP (default, most common)
+  - browser-use MCP (token efficient alternative)
+  - Chrome DevTools MCP
 
 ## Installation
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@allenpan2026/harshjudge",
-  "version": "0.4.1",
+  "version": "0.4.2",
   "description": "AI-native E2E testing orchestration CLI for Claude Code.",
   "type": "module",
   "main": "./dist/index.js",

package/skills/harshjudge/references/run-browser.md

@@ -0,0 +1,63 @@
+# Browser Tool Reference
+
+Used during step execution in [[run]].
+
+HarshJudge is **browser-tool-agnostic**. Use whatever browser automation tool is available in your environment. The step agent needs these capabilities:
+
+## Required Capabilities
+
+| Action | What to do |
+|--------|-----------|
+| Navigate | Go to a URL |
+| Inspect page | Get current page state (DOM, accessibility tree) before interacting |
+| Click | Click an element by text, role, or reference |
+| Type | Enter text into an input field |
+| Select | Choose an option from a dropdown |
+| Wait | Wait for text to appear/disappear, or for a timeout |
+| Screenshot | Capture the current page as an image file |
+| Console logs | Read browser console output |
+| Network logs | Read network requests/responses |
+
+## Supported Browser Tools
+
+### Playwright MCP (Default)
+
+Most common. Available as a Claude Code plugin.
+
+```json
+{
+  "playwright": {
+    "command": "npx",
+    "args": ["@playwright/mcp@latest"]
+  }
+}
+```
+
+Tools: `browser_navigate`, `browser_click`, `browser_type`, `browser_snapshot`, `browser_take_screenshot`, `browser_wait_for`, `browser_console_messages`, `browser_network_requests`
+
+### browser-use MCP (Token Efficient Alternative)
+
+Compresses DOM before sending to LLM — significantly fewer tokens per interaction. Python-based.
+
+Setup: See [browser-use MCP docs](https://docs.browser-use.com/customize/integrations/mcp-server)
+
+### Chrome DevTools MCP
+
+Connects to an already-running Chrome instance via remote debugging.
+
+```json
+{
+  "chrome-devtools": {
+    "command": "npx",
+    "args": ["chrome-devtools-mcp"]
+  }
+}
+```
+
+## Best Practices
+
+- Always inspect the page before clicking or typing to get current element state
+- Take a screenshot **before** and **after** each significant action
+- Wait after navigation to confirm the page loaded
+- Capture console errors on unexpected behavior
+- Save screenshots to a temp path, then record via `harshjudge evidence`

package/skills/harshjudge/references/run-step-agent.md

@@ -20,8 +20,8 @@ Status: {pass|fail|first step}
 ## Your Task
 1. Navigate to the base URL if not already there
 2. Execute the actions described in the step content
-3. Use browser_snapshot before clicking to get element refs
-4. Capture before/after screenshots using browser_take_screenshot
+3. Use the available browser tool to inspect the page before interacting
+4. Take before/after screenshots using the browser tool
 5. Record evidence:
    harshjudge evidence {runId} --step {stepNumber} --type screenshot --name before --data /path/to/screenshot.png
 6. Verify the expected outcome

package/skills/harshjudge/references/run.md

@@ -15,7 +15,7 @@ Use this workflow when user wants to:
 3. `harshjudge complete-step <runId>` — Complete each step, get next step
 4. `harshjudge complete-run <runId>` — Finalize with pass/fail status
 
-See [[run-playwright]] for Playwright tool reference.
+See [[run-browser]] for browser tool reference (Playwright MCP, browser-use, Chrome DevTools).
 
 > **TOKEN OPTIMIZATION**: Each step executes in its own spawned agent. This isolates context and prevents token accumulation.
 

package/skills/harshjudge/references/run-playwright.md

@@ -1,41 +0,0 @@
-# Playwright Tools Reference
-
-Used during step execution in [[run]].
-
-## Navigation & State
-
-| Tool | Usage |
-|------|-------|
-| `browser_navigate` | `{ "url": "http://localhost:3000" }` |
-| `browser_snapshot` | `{}` → Returns accessibility tree with refs |
-| `browser_take_screenshot` | `{ "filename": "step-01-before.png" }` |
-
-## Interactions
-
-| Tool | Usage |
-|------|-------|
-| `browser_click` | `{ "element": "Login button", "ref": "e5" }` |
-| `browser_type` | `{ "element": "Email input", "ref": "e4", "text": "test@example.com" }` |
-| `browser_select_option` | `{ "element": "Country", "ref": "e7", "values": ["USA"] }` |
-
-## Waiting
-
-| Tool | Usage |
-|------|-------|
-| `browser_wait_for` | `{ "text": "Welcome" }` |
-| `browser_wait_for` | `{ "textGone": "Loading..." }` |
-| `browser_wait_for` | `{ "time": 2 }` |
-
-## Debugging
-
-| Tool | Usage |
-|------|-------|
-| `browser_console_messages` | `{ "level": "error" }` |
-| `browser_network_requests` | `{}` |
-
-## Best Practices
-
-- Always call `browser_snapshot` before `browser_click` or `browser_type` to get current element refs
-- Take a screenshot **before** and **after** each significant action
-- Use `browser_wait_for` after navigation to confirm page loaded
-- Capture console errors on any unexpected behavior