@prismer/runtime 2.2.55 → 2.2.64

package/built-in-skills/web-artifacts-builder/scripts/init-artifact.sh

@@ -1,7 +1,13 @@
 #!/bin/bash
 
 # Exit on error
-set -e
+set -euo pipefail
+
+PROJECT_NAME="${1:-}"
+if [[ ! "$PROJECT_NAME" =~ ^[a-zA-Z0-9][a-zA-Z0-9_-]*$ ]] || [[ -e "$PROJECT_NAME" ]]; then
+  echo 'Usage: init-artifact.sh <new-project-name>; target must not exist' >&2
+  exit 1
+fi
 
 # Detect Node version
 NODE_VERSION=$(node -v | cut -d'v' -f2 | cut -d'.' -f1)
@@ -14,77 +20,39 @@ if [ "$NODE_VERSION" -lt 18 ]; then
   exit 1
 fi
 
-# Set Vite version based on Node version
-if [ "$NODE_VERSION" -ge 20 ]; then
-  VITE_VERSION="latest"
-  echo "✅ Using Vite latest (Node 20+)"
-else
-  VITE_VERSION="5.4.11"
-  echo "✅ Using Vite $VITE_VERSION (Node 18 compatible)"
-fi
+VITE_VERSION="5.4.11"
 
 # Detect OS and set sed syntax
 if [[ "$OSTYPE" == "darwin"* ]]; then
-  SED_INPLACE="sed -i ''"
+  SED_INPLACE=(sed -i '')
 else
-  SED_INPLACE="sed -i"
+  SED_INPLACE=(sed -i)
 fi
 
 # Check if pnpm is installed. Release 201 sandbox image bakes pnpm@9.
-# If pnpm is missing the image is out of date (or we're in a dev env);
-# try corepack as a per-user fallback (no sudo), else fail loudly so the
-# agent surfaces the missing-baseline error rather than installing pnpm
-# at task time and contaminating the workdir.
+# Do not change global Corepack/pnpm state from a project scaffold.
 if ! command -v pnpm &> /dev/null; then
-  echo "📦 pnpm not found. Trying corepack..."
-  if command -v corepack &> /dev/null; then
-    corepack enable
-    corepack prepare pnpm@9 --activate
-  else
-    echo "❌ Error: pnpm is required but neither pnpm nor corepack is available."
-    echo "   Sandbox image is missing pnpm — rebuild the daemon image with the"
-    echo "   release 201 baseline (infra/sandbox-image/Dockerfile.daemon)."
-    exit 1
-  fi
-fi
-
-# Check if project name is provided
-if [ -z "$1" ]; then
-  echo "❌ Usage: ./create-react-shadcn-complete.sh <project-name>"
+  echo "pnpm is required; install it explicitly before running this scaffold." >&2
   exit 1
 fi
 
-PROJECT_NAME="$1"
-SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-COMPONENTS_TARBALL="$SCRIPT_DIR/shadcn-components.tar.gz"
-
-# Check if components tarball exists
-if [ ! -f "$COMPONENTS_TARBALL" ]; then
-  echo "❌ Error: shadcn-components.tar.gz not found in script directory"
-  echo "   Expected location: $COMPONENTS_TARBALL"
-  exit 1
-fi
 
 echo "🚀 Creating new React + Vite project: $PROJECT_NAME"
 
-# Create new Vite project (always use latest create-vite, pin vite version later)
-pnpm create vite "$PROJECT_NAME" --template react-ts
+# Use a fixed template compatible with the declared Node baseline.
+pnpm dlx create-vite@5.5.5 "$PROJECT_NAME" --template react-ts
 
 # Navigate into project directory
 cd "$PROJECT_NAME"
 
 echo "🧹 Cleaning up Vite template..."
-$SED_INPLACE '/<link rel="icon".*vite\.svg/d' index.html
-$SED_INPLACE 's/<title>.*<\/title>/<title>'"$PROJECT_NAME"'<\/title>/' index.html
+"${SED_INPLACE[@]}" '/<link rel="icon".*vite\.svg/d' index.html
+"${SED_INPLACE[@]}" 's/<title>.*<\/title>/<title>'"$PROJECT_NAME"'<\/title>/' index.html
 
 echo "📦 Installing base dependencies..."
 pnpm install
 
-# Pin Vite version for Node 18
-if [ "$NODE_VERSION" -lt 20 ]; then
-  echo "📌 Pinning Vite to $VITE_VERSION for Node 18 compatibility..."
-  pnpm add -D vite@$VITE_VERSION
-fi
+pnpm add -D "vite@$VITE_VERSION"
 
 echo "📦 Installing Tailwind CSS and dependencies..."
 pnpm install -D tailwindcss@3.4.1 postcss autoprefixer @types/node tailwindcss-animate
@@ -101,7 +69,7 @@ export default {
 EOF
 
 echo "📝 Configuring Tailwind with shadcn theme..."
-cat > tailwind.config.js << 'EOF'
+cat > tailwind.config.cjs << 'EOF'
 /** @type {import('tailwindcss').Config} */
 module.exports = {
   darkMode: ["class"],
@@ -284,10 +252,6 @@ echo "📦 Installing shadcn/ui dependencies..."
 pnpm install @radix-ui/react-accordion @radix-ui/react-aspect-ratio @radix-ui/react-avatar @radix-ui/react-checkbox @radix-ui/react-collapsible @radix-ui/react-context-menu @radix-ui/react-dialog @radix-ui/react-dropdown-menu @radix-ui/react-hover-card @radix-ui/react-label @radix-ui/react-menubar @radix-ui/react-navigation-menu @radix-ui/react-popover @radix-ui/react-progress @radix-ui/react-radio-group @radix-ui/react-scroll-area @radix-ui/react-select @radix-ui/react-separator @radix-ui/react-slider @radix-ui/react-slot @radix-ui/react-switch @radix-ui/react-tabs @radix-ui/react-toast @radix-ui/react-toggle @radix-ui/react-toggle-group @radix-ui/react-tooltip
 pnpm install sonner cmdk vaul embla-carousel-react react-day-picker react-resizable-panels date-fns react-hook-form @hookform/resolvers zod
 
-# Extract shadcn components from tarball
-echo "📦 Extracting shadcn/ui components..."
-tar -xzf "$COMPONENTS_TARBALL" -C src/
-
 # Create components.json for reference
 echo "📝 Creating components.json config..."
 cat > components.json << 'EOF'
@@ -297,7 +261,7 @@ cat > components.json << 'EOF'
   "rsc": false,
   "tsx": true,
   "tailwind": {
-    "config": "tailwind.config.js",
+    "config": "tailwind.config.cjs",
     "css": "src/index.css",
     "baseColor": "slate",
     "cssVariables": true,
@@ -313,6 +277,15 @@ cat > components.json << 'EOF'
 }
 EOF
 
+mkdir -p src/lib
+cat > src/lib/utils.ts << 'EOF'
+import { clsx, type ClassValue } from "clsx";
+import { twMerge } from "tailwind-merge";
+export function cn(...inputs: ClassValue[]) { return twMerge(clsx(inputs)); }
+EOF
+# Fetch the published component registry instead of a nonexistent local archive.
+pnpm dlx shadcn@2.3.0 add --all --yes
+
 echo "✅ Setup complete! You can now use Tailwind CSS and shadcn/ui in your project."
 echo ""
 echo "📦 Included components (40+ total):"

package/built-in-skills/webapp-qa/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Nous Research
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

package/built-in-skills/webapp-qa/NOTICE.md

@@ -0,0 +1,37 @@
+MIT License
+
+Copyright (c) 2025 Nous Research
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
+
+## Engineering adaptation (2026-09-23)
+
+Source: https://github.com/NousResearch/hermes-agent/tree/1a1f4a59e252e1dc0137e7b2e7bcc8b0381d19c4/skills/software-development/dogfood
+
+Upstream authors: Teknium (teknium1), Hermes Agent.
+Hermes MIT copyright (c) 2025 Nous Research is preserved in LICENSE.
+All bundled references/templates/scripts remain covered by that notice unless
+an additional license is explicitly supplied. External CLI binaries, services,
+accounts and downloaded assets are not redistributed by this skill and retain
+their own terms. No API keys or third-party runtime packages are bundled.
+
+Prismer modifications: unique discovery/ownership mapping where applicable,
+resource-path and authorization corrections, bounded helpers, honest readiness
+and verification states. See docs/bugfix223/implementation-engineering.md in the
+source repository for resource mapping, tests and remaining live acceptance.

package/built-in-skills/webapp-qa/SKILL.md

@@ -0,0 +1,41 @@
+---
+name: webapp-qa
+scope: common
+description: Perform scoped exploratory QA of a web application, reproduce defects, collect screenshots and console evidence, and deliver a prioritized report.
+license: MIT
+metadata:
+  nativeReplaces: [dogfood]
+  upstream: Hermes Agent skills/software-development/dogfood at 1a1f4a59e2
+---
+# Web Application QA
+
+For the full five-phase exploratory method, read references/dogfood/GUIDE.md;
+its taxonomy and report-template links resolve within this bundle.
+
+Use the user-supplied target URL, scope and existing test accounts. Inspect the
+available browser tools or Playwright setup first; never invent browser tool
+names. Without a working browser, report the blocker and limit claims to checks
+actually performed.
+
+1. Map the main user journeys, navigation, forms and error/empty states.
+2. Exercise each journey with positive and negative inputs. Inspect console and
+   network failures after navigation and significant interactions.
+3. Inspect screenshots at desktop and mobile sizes for clipping, overlap,
+   loading failures and keyboard accessibility.
+4. Reproduce each suspected defect. Record URL, exact steps, expected/actual
+   behavior, console evidence and screenshot file. Separate application bugs
+   from unavailable dependencies or test-environment failures.
+5. Deduplicate, prioritize by user impact, and use references/issue-taxonomy.md
+   plus templates/dogfood-report-template.md as report structure.
+6. State tested, untested and blocked areas. Passing HTTP status alone is not a
+   passing user journey. Never fill missing evidence with plausible descriptions.
+7. Attach the report and requested evidence as task-bound assets using the
+   actual platform delivery contract. Do not invent flags or use MEDIA markers.
+
+Use a task-owned local fixture for browser-tool smoke tests before touching a
+live account. Record desktop/mobile viewport, keyboard, console, clipping and
+positive/negative form results independently; a fixture does not certify the
+user's real application.
+
+Keep test mutations within the user's authorized scope. Do not submit real
+payments or send external messages as incidental QA actions.

package/built-in-skills/webapp-qa/references/dogfood/GUIDE.md

@@ -0,0 +1,161 @@
+
+# Dogfood: Systematic Web Application QA Testing
+
+## Overview
+
+This skill guides you through systematic exploratory QA testing of web applications using the browser toolset. You will navigate the application, interact with elements, capture evidence of issues, and produce a structured bug report.
+
+## Tool mapping and authorization
+
+Resolve actual browser tools from the native browser-use entry or an installed
+Playwright harness. The browser_* calls below are historical pseudocode, not
+registered tool names. Map operations to the exposed schema before executing;
+never invent @eN handles. Preserve the user's live session. Use only authorized
+test mutations; payments, external messages and destructive writes need their
+own explicit scope. Use a unique task-owned output directory.
+
+## Prerequisites
+
+- Browser toolset must be available (`browser_navigate`, `browser_snapshot`, `browser_click`, `browser_type`, `browser_vision`, `browser_console`, `browser_scroll`, `browser_back`, `browser_press`)
+- A target URL and testing scope from the user
+
+## Inputs
+
+The user provides:
+1. **Target URL** — the entry point for testing
+2. **Scope** — what areas/features to focus on (or "full site" for comprehensive testing)
+3. **Output directory** (optional) — where to save screenshots and the report (default: `./dogfood-output`)
+
+## Workflow
+
+Follow this 5-phase systematic workflow:
+
+### Phase 1: Plan
+
+1. Create the output directory structure:
+   ```
+   {output_dir}/
+   ├── screenshots/       # Evidence screenshots
+   └── report.md          # Final report (generated in Phase 5)
+   ```
+2. Identify the testing scope based on user input.
+3. Build a rough sitemap by planning which pages and features to test:
+   - Landing/home page
+   - Navigation links (header, footer, sidebar)
+   - Key user flows (sign up, login, search, checkout, etc.)
+   - Forms and interactive elements
+   - Edge cases (empty states, error pages, 404s)
+
+### Phase 2: Explore
+
+For each page or feature in your plan:
+
+1. **Navigate** to the page:
+   ```
+   browser_navigate(url="https://example.com/page")
+   ```
+
+2. **Take a snapshot** to understand the DOM structure:
+   ```
+   browser_snapshot()
+   ```
+
+3. **Check the console** for JavaScript errors:
+   ```
+   browser_console(clear=true)
+   ```
+   Do this after every navigation and after every significant interaction. Silent JS errors are high-value findings.
+
+4. **Take an annotated screenshot** to visually assess the page and identify interactive elements:
+   ```
+   browser_vision(question="Describe the page layout, identify any visual issues, broken elements, or accessibility concerns", annotate=true)
+   ```
+   Use only handles returned by the actual browser tool. Re-snapshot after navigation or a stale-handle failure.
+
+5. **Test interactive elements** systematically:
+   - Click buttons and links: `browser_click(ref="@eN")`
+   - Fill forms: `browser_type(ref="@eN", text="test input")`
+   - Test keyboard navigation: `browser_press(key="Tab")`, `browser_press(key="Enter")`
+   - Scroll through content: `browser_scroll(direction="down")`
+   - Test form validation with invalid inputs
+   - Test empty submissions
+
+6. **After each interaction**, check for:
+   - Console errors: `browser_console()`
+   - Visual changes: `browser_vision(question="What changed after the interaction?")`
+   - Expected vs actual behavior
+
+### Phase 3: Collect Evidence
+
+For every issue found:
+
+1. **Take a screenshot** showing the issue:
+   ```
+   browser_vision(question="Capture and describe the issue visible on this page", annotate=false)
+   ```
+   Save the `screenshot_path` from the response — you will reference it in the report.
+
+2. **Record the details**:
+   - URL where the issue occurs
+   - Steps to reproduce
+   - Expected behavior
+   - Actual behavior
+   - Console errors (if any)
+   - Screenshot path
+
+3. **Classify the issue** using the issue taxonomy (see `../issue-taxonomy.md`):
+   - Severity: Critical / High / Medium / Low
+   - Category: Functional / Visual / Accessibility / Console / UX / Content
+
+### Phase 4: Categorize
+
+1. Review all collected issues.
+2. De-duplicate — merge issues that are the same bug manifesting in different places.
+3. Assign final severity and category to each issue.
+4. Sort by severity (Critical first, then High, Medium, Low).
+5. Count issues by severity and category for the executive summary.
+
+### Phase 5: Report
+
+Generate the final report using the template at `../../templates/dogfood-report-template.md`.
+
+The report must include:
+1. **Executive summary** with total issue count, breakdown by severity, and testing scope
+2. **Per-issue sections** with:
+   - Issue number and title
+   - Severity and category badges
+   - URL where observed
+   - Description of the issue
+   - Steps to reproduce
+   - Expected vs actual behavior
+   - Screenshot references (use an attached task asset with its explicit path for inline images)
+   - Console errors if relevant
+3. **Summary table** of all issues
+4. **Testing notes** — what was tested, what was not, any blockers
+
+Save the report to `{output_dir}/report.md`.
+
+## Tools Reference
+
+| Tool | Purpose |
+|------|---------|
+| `browser_navigate` | Go to a URL |
+| `browser_snapshot` | Get DOM text snapshot (accessibility tree) |
+| `browser_click` | Click an element by ref (`@eN`) or text |
+| `browser_type` | Type into an input field |
+| `browser_scroll` | Scroll up/down on the page |
+| `browser_back` | Go back in browser history |
+| `browser_press` | Press a keyboard key |
+| `browser_vision` | Screenshot + AI analysis; use `annotate=true` for element labels |
+| `browser_console` | Get JS console output and errors |
+
+## Tips
+
+- **Always check `browser_console()` after navigating and after significant interactions.** Silent JS errors are among the most valuable findings.
+- **Use `annotate=true` with `browser_vision`** when you need to reason about interactive element positions or when the snapshot refs are unclear.
+- **Test with both valid and invalid inputs** — form validation bugs are common.
+- **Scroll through long pages** — content below the fold may have rendering issues.
+- **Test navigation flows** — click through multi-step processes end-to-end.
+- **Check responsive behavior** at named desktop/mobile viewports, inspect screenshots and horizontal overflow, and test keyboard focus. Record untested breakpoints.
+- **Don't forget edge cases**: empty states, very long text, special characters, rapid clicking.
+- When reporting screenshots to the user, include an attached task asset with its explicit path so they can see the evidence inline.

package/built-in-skills/webapp-qa/references/issue-taxonomy.md

@@ -0,0 +1,109 @@
+# Issue Taxonomy
+
+Use this taxonomy to classify issues found during dogfood QA testing.
+
+## Severity Levels
+
+### Critical
+The issue makes a core feature completely unusable or causes data loss.
+
+**Examples:**
+- Application crashes or shows a blank white page
+- Form submission silently loses user data
+- Authentication is completely broken (can't log in at all)
+- Payment flow fails and charges the user without completing the order
+- Security vulnerability (e.g., XSS, exposed credentials in console)
+
+### High
+The issue significantly impairs functionality but a workaround may exist.
+
+**Examples:**
+- A key button does nothing when clicked (but refreshing fixes it)
+- Search returns no results for valid queries
+- Form validation rejects valid input
+- Page loads but critical content is missing or garbled
+- Navigation link leads to a 404 or wrong page
+- Uncaught JavaScript exceptions in the console on core pages
+
+### Medium
+The issue is noticeable and affects user experience but doesn't block core functionality.
+
+**Examples:**
+- Layout is misaligned or overlapping on certain screen sections
+- Images fail to load (broken image icons)
+- Slow performance (visible loading delays > 3 seconds)
+- Form field lacks proper validation feedback (no error message on bad input)
+- Console warnings that suggest deprecated or misconfigured features
+- Inconsistent styling between similar pages
+
+### Low
+Minor polish issues that don't affect functionality.
+
+**Examples:**
+- Typos or grammatical errors in text content
+- Minor spacing or alignment inconsistencies
+- Placeholder text left in production ("Lorem ipsum")
+- Favicon missing
+- Console info/debug messages that shouldn't be in production
+- Subtle color contrast issues that don't fail WCAG requirements
+
+## Categories
+
+### Functional
+Issues where features don't work as expected.
+
+- Buttons/links that don't respond
+- Forms that don't submit or submit incorrectly
+- Broken user flows (can't complete a multi-step process)
+- Incorrect data displayed
+- Features that work partially
+
+### Visual
+Issues with the visual presentation of the page.
+
+- Layout problems (overlapping elements, broken grids)
+- Broken images or missing media
+- Styling inconsistencies
+- Responsive design failures
+- Z-index issues (elements hidden behind others)
+- Text overflow or truncation
+
+### Accessibility
+Issues that prevent or hinder access for users with disabilities.
+
+- Missing alt text on meaningful images
+- Poor color contrast (fails WCAG AA)
+- Elements not reachable via keyboard navigation
+- Missing form labels or ARIA attributes
+- Focus indicators missing or unclear
+- Screen reader incompatible content
+
+### Console
+Issues detected through JavaScript console output.
+
+- Uncaught exceptions and unhandled promise rejections
+- Failed network requests (4xx, 5xx errors in console)
+- Deprecation warnings
+- CORS errors
+- Mixed content warnings (HTTP resources on HTTPS page)
+- Excessive console.log output left from development
+
+### UX (User Experience)
+Issues where functionality works but the experience is poor.
+
+- Confusing navigation or information architecture
+- Missing loading indicators (user doesn't know something is happening)
+- No feedback after user actions (e.g., button click with no visible result)
+- Inconsistent interaction patterns
+- Missing confirmation dialogs for destructive actions
+- Poor error messages that don't help the user recover
+
+### Content
+Issues with the text, media, or information on the page.
+
+- Typos and grammatical errors
+- Placeholder/dummy content in production
+- Outdated information
+- Missing content (empty sections)
+- Broken or dead links to external resources
+- Incorrect or misleading labels

package/built-in-skills/webapp-qa/templates/dogfood-report-template.md

@@ -0,0 +1,86 @@
+# Dogfood QA Report
+
+**Target:** {target_url}
+**Date:** {date}
+**Scope:** {scope_description}
+**Tester:** Hermes Agent (automated exploratory QA)
+
+---
+
+## Executive Summary
+
+| Severity | Count |
+|----------|-------|
+| 🔴 Critical | {critical_count} |
+| 🟠 High | {high_count} |
+| 🟡 Medium | {medium_count} |
+| 🔵 Low | {low_count} |
+| **Total** | **{total_count}** |
+
+**Overall Assessment:** {one_sentence_assessment}
+
+---
+
+## Issues
+
+<!-- Repeat this section for each issue found, sorted by severity (Critical first) -->
+
+### Issue #{issue_number}: {issue_title}
+
+| Field | Value |
+|-------|-------|
+| **Severity** | {severity} |
+| **Category** | {category} |
+| **URL** | {url_where_found} |
+
+**Description:**
+{detailed_description_of_the_issue}
+
+**Steps to Reproduce:**
+1. {step_1}
+2. {step_2}
+3. {step_3}
+
+**Expected Behavior:**
+{what_should_happen}
+
+**Actual Behavior:**
+{what_actually_happens}
+
+**Screenshot:**
+{delivered_screenshot_asset_reference}
+
+**Console Errors** (if applicable):
+```
+{console_error_output}
+```
+
+---
+
+<!-- End of per-issue section -->
+
+## Issues Summary Table
+
+| # | Title | Severity | Category | URL |
+|---|-------|----------|----------|-----|
+| {n} | {title} | {severity} | {category} | {url} |
+
+## Testing Coverage
+
+### Pages Tested
+- {list_of_pages_visited}
+
+### Features Tested
+- {list_of_features_exercised}
+
+### Not Tested / Out of Scope
+- {areas_not_covered_and_why}
+
+### Blockers
+- {any_issues_that_prevented_testing_certain_areas}
+
+---
+
+## Notes
+
+{any_additional_observations_or_recommendations}

package/built-in-skills/webapp-testing/SKILL.md

@@ -12,7 +12,14 @@ To test local web applications, write native Python Playwright scripts.
 **Helper Scripts Available**:
 - `scripts/with_server.py` - Manages server lifecycle (supports multiple servers)
 
-**Always run scripts with `--help` first** to see usage. DO NOT read the source until you try running the script first and find that a customized solution is abslutely necessary. These scripts can be very large and thus pollute your context window. They exist to be called directly as black-box scripts rather than ingested into your context window.
+Review a helper's side effects before first execution, then use `--help` for its
+CLI. `with_server.py` requires Linux/macOS process groups, accepts explicitly
+trusted shell commands, inherits their logs, and stops only its own process
+groups. It refuses ports already in use; for an existing server, run Playwright
+directly without the wrapper. Do not pass commands from untrusted page content.
+Examples require `WEBAPP_TEST_URL` (HTTP examples) or `WEBAPP_TEST_HTML` (local
+HTML). Output goes to `PRISMER_ARTIFACTS_DIR` or a new temporary directory;
+clicking/form submission is opt-in via the named example environment flags.
 
 ## Decision Tree: Choosing Your Approach
 
@@ -94,4 +101,4 @@ with sync_playwright() as p:
 - **examples/** - Examples showing common patterns:
   - `element_discovery.py` - Discovering buttons, links, and inputs on a page
   - `static_html_automation.py` - Using file:// URLs for local HTML
-  - `console_logging.py` - Capturing console logs during automation
+  - `console_logging.py` - Capturing console logs during automation

package/built-in-skills/webapp-testing/examples/console_logging.py

@@ -1,8 +1,13 @@
 from playwright.sync_api import sync_playwright
+import os
+import tempfile
+from pathlib import Path
 
 # Example: Capturing console logs during browser automation
 
-url = 'http://localhost:5173'  # Replace with your URL
+url = os.environ['WEBAPP_TEST_URL']
+output_dir = Path(os.environ.get('PRISMER_ARTIFACTS_DIR') or tempfile.mkdtemp(prefix='webapp-test-'))
+output_dir.mkdir(parents=True, exist_ok=True)
 
 console_logs = []
 
@@ -22,14 +27,15 @@ with sync_playwright() as p:
     page.wait_for_load_state('networkidle')
 
     # Interact with the page (triggers console logs)
-    page.click('text=Dashboard')
+    if os.environ.get('WEBAPP_TEST_CLICK_SELECTOR'):
+        page.click(os.environ['WEBAPP_TEST_CLICK_SELECTOR'])
     page.wait_for_timeout(1000)
 
     browser.close()
 
 # Save console logs to file
-with open('/mnt/user-data/outputs/console.log', 'w') as f:
+with (output_dir / 'console.log').open('w') as f:
     f.write('\n'.join(console_logs))
 
 print(f"\nCaptured {len(console_logs)} console messages")
-print(f"Logs saved to: /mnt/user-data/outputs/console.log")
+print(f"Logs saved to: {output_dir / 'console.log'}")