boundary-bbcr-fallback
Execute automatic BBCR (Collapse-Rebirth Correction) when knowledge boundaries are exceeded or reasoning fails.
Execute JavaScript code in the Tauri app's webview context
$ npx -y skills add qdhenry/Claude-Command-Suite --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
/exec-jsContext preview
What this command does when you run it.
Execute JavaScript code in the Tauri app's webview context
name: rust:tauri:exec-js description: Execute JavaScript code in the Tauri app's webview context allowed-tools: mcp__tauri-mcp__execute_js author: Quintin Henry (https://github.com/qdhenry/)
<objective> Execute arbitrary JavaScript in the Tauri application's webview. Useful for inspecting state, triggering actions, or debugging frontend behavior. </objective>
<instructions> Execute JavaScript in the Tauri app: **$ARGUMENTS**
Arguments format: `[process_id] [javascript_code]`
1. **Parse Arguments** Extract process_id and JavaScript code from $ARGUMENTS.
2. **Execute the Code** Use `mcp__tauri-mcp__execute_js` with:
3. **Return Results**
# Get current URL/route
/tauri:exec-js 12345 window.location.href
# Check React state (if using React)
/tauri:exec-js 12345 document.querySelector('[data-testid="project-list"]').textContent
# Get localStorage data
/tauri:exec-js 12345 JSON.stringify(localStorage)
# Check DOM element exists
/tauri:exec-js 12345 !!document.querySelector('.task-card')
# Get current theme
/tauri:exec-js 12345 document.documentElement.classList.contains('dark')
# Trigger a click
/tauri:exec-js 12345 document.querySelector('button[data-action="refresh"]').click()
# Call Tauri invoke directly
/tauri:exec-js 12345 window.__TAURI__.invoke('get_projects')</instructions>
<output_format>
=== JavaScript Execution === Process: [PID] --- Code --- [the executed code] --- Result --- [formatted return value] --- Console Output --- [any console.log output if captured]
</output_format>
<common_snippets> **State Inspection:**
// Get all data attributes on body
Object.fromEntries([...document.body.attributes].map(a => [a.name, a.value]))
// Find all buttons with text
[...document.querySelectorAll('button')].map(b => b.textContent.trim())
// Get form values
Object.fromEntries(new FormData(document.querySelector('form')))**Debug Helpers:**
// Log React component tree (if React DevTools installed)
window.__REACT_DEVTOOLS_GLOBAL_HOOK__
// Check for errors in DOM
document.querySelectorAll('[data-error], .error, .text-red-500').length
// Get current route (React Router)
window.location.pathname**UI Interaction:**
// Simulate user typing
document.querySelector('input').value = 'test'
document.querySelector('input').dispatchEvent(new Event('input', {bubbles: true}))
// Click and wait
document.querySelector('button').click()</common_snippets>
<security_note> JavaScript execution has full access to the webview context. Use carefully:
</security_note>
A comprehensive development toolkit designed following Anthropic's Claude Code Best Practices for AI-assisted software development.
Repo: qdhenry/Claude-Command-Suite
Execute automatic BBCR (Collapse-Rebirth Correction) when knowledge boundaries are exceeded or reasoning fails.
Analyze semantic position relative to knowledge boundaries to prevent hallucination and identify uncertainty zones.
Generate a visual heatmap of knowledge boundaries showing safe zones, risk areas, and semantic coverage.
Evaluate the current risk level and provide detailed analysis of potential hallucination or reasoning failure.
Find and construct semantic bridges to safely navigate from current position to target concept without crossing dangerous boundaries.
Takes an input prompt and returns ONLY a token-optimized version that preserves meaning while minimizing token count. Based on LLM tokenization principles:…