Add a script to update the prompts

README.md

@@ -37,37 +37,37 @@ Sub-agents and utilities.
 ### Creation Assistants
 
 - [Agent Prompt: Agent creation architect](./system-prompts/agent-prompt-agent-creation-architect.md) (**1111** tks) - System prompt for creating custom AI agents with detailed specifications.
-- [Agent Prompt: CLAUDE.md creation](./system-prompts/agent-prompt-claudemd-creation.md) (**384** tks) - System prompt for analyzing codebases and creating CLAUDE.md documentation.
-- [Agent Prompt: Status line setup](./system-prompts/agent-prompt-status-line-setup.md) (**993** tks) - System prompt for the statusline-setup agent that configures status line.
+- [Agent Prompt: CLAUDE.md creation](./system-prompts/agent-prompt-claudemd-creation.md) (**384** tks) - System prompt for analyzing codebases and creating CLAUDE.md documentation files.
+- [Agent Prompt: Status line setup](./system-prompts/agent-prompt-status-line-setup.md) (**993** tks) - System prompt for the statusline-setup agent that configures status line display.
 
 ### Slash commands
 
 - [Agent Prompt: /pr-comments slash command](./system-prompts/agent-prompt-pr-comments-slash-command.md) (**404** tks) - System prompt for fetching and displaying GitHub PR comments.
 - [Agent Prompt: /review-pr slash command](./system-prompts/agent-prompt-review-pr-slash-command.md) (**245** tks) - System prompt for reviewing GitHub pull requests with code analysis.
-- [Agent Prompt: /security-review slash](./system-prompts/agent-prompt-security-review-slash.md) (**2614** tks) - Comprehensive security review prompt for analyzing code changes with focus on.
+- [Agent Prompt: /security-review slash](./system-prompts/agent-prompt-security-review-slash.md) (**2614** tks) - Comprehensive security review prompt for analyzing code changes with focus on exploitable vulnerabilities.
 
 ### Utilities
 
 - [Agent Prompt: Bash command file path extraction](./system-prompts/agent-prompt-bash-command-file-path-extraction.md) (**286** tks) - System prompt for extracting file paths from bash command output.
 - [Agent Prompt: Bash command prefix detection](./system-prompts/agent-prompt-bash-command-prefix-detection.md) (**835** tks) - System prompt for detecting command prefixes and command injection.
 - [Agent Prompt: Bash output summarization](./system-prompts/agent-prompt-bash-output-summarization.md) (**605** tks) - System prompt for determining whether bash command output should be summarized.
-- [Agent Prompt: Conversation summarization](./system-prompts/agent-prompt-conversation-summarization.md) (**1121** tks) - System prompt for creating detailed conversation summaries.
 - [Agent Prompt: Conversation summarization with additional instructions](./system-prompts/agent-prompt-conversation-summarization-with-additional-instructions.md) (**1133** tks) - Extended summarization prompt with support for custom additional instructions.
-- [Agent Prompt: Prompt Hook execution](./system-prompts/agent-prompt-prompt-hook-execution.md) (**134** tks) - Prompt given to Claude when acting evaluating whether to pass or fail a prompt.
+- [Agent Prompt: Conversation summarization](./system-prompts/agent-prompt-conversation-summarization.md) (**1121** tks) - System prompt for creating detailed conversation summaries.
+- [Agent Prompt: Prompt Hook execution](./system-prompts/agent-prompt-prompt-hook-execution.md) (**134** tks) - Prompt given to Claude when acting evaluating whether to pass or fail a prompt hook..
 - [Agent Prompt: Session notes template](./system-prompts/agent-prompt-session-notes-template.md) (**226** tks) - Template structure for session notes tracking coding work and decisions.
 - [Agent Prompt: Session notes update instructions](./system-prompts/agent-prompt-session-notes-update-instructions.md) (**730** tks) - Instructions for updating session notes files during conversations.
 - [Agent Prompt: Session title generation](./system-prompts/agent-prompt-session-title-generation.md) (**159** tks) - System prompt for generating succinct titles for coding sessions.
-- [Agent Prompt: Update Magic Docs](./system-prompts/agent-prompt-update-magic-docs.md) (**718** tks) - Prompt for the magic-docs agent.
+- [Agent Prompt: Update Magic Docs](./system-prompts/agent-prompt-update-magic-docs.md) (**718** tks) - Prompt for the magic-docs agent..
 - [Agent Prompt: User sentiment analysis](./system-prompts/agent-prompt-user-sentiment-analysis.md) (**205** tks) - System prompt for analyzing user frustration and PR creation requests.
-- [Agent Prompt: WebFetch summarizer](./system-prompts/agent-prompt-webfetch-summarizer.md) (**147** tks) - Prompt for agent that summarizes verbose output from WebFetch for the main.
+- [Agent Prompt: WebFetch summarizer](./system-prompts/agent-prompt-webfetch-summarizer.md) (**147** tks) - Prompt for agent that summarizes verbose output from WebFetch for the main model.
 
 <!--
 ### Data
 
 Misc large strings.
 
-- [Data: GitHub Actions workflow for @claude mentions](./system-prompts/data-github-actions-workflow-for-claude-mentions.md) (**531** tks) - GitHub Actions workflow template for triggering Claude Code via @claude.
-- [Data: GitHub Actions workflow for automated code review (beta)](./system-prompts/data-github-actions-workflow-for-automated-code-review-beta.md) (**573** tks) - GitHub Actions workflow template for automated Claude Code reviews using.
+- [Data: GitHub Actions workflow for @claude mentions](./system-prompts/data-github-actions-workflow-for-@claude-mentions.md) (**531** tks) - GitHub Actions workflow template for triggering Claude Code via @claude mentions.
+- [Data: GitHub Actions workflow for automated code review (beta)](./system-prompts/data-github-actions-workflow-for-automated-code-review-beta.md) (**573** tks) - GitHub Actions workflow template for automated Claude Code reviews using direct_prompt.
 - [Data: GitHub App installation PR description](./system-prompts/data-github-app-installation-pr-description.md) (**424** tks) - Template for PR description when installing Claude Code GitHub App integration.
 -->
 
@@ -75,9 +75,9 @@ Misc large strings.
 
 Parts of the main system prompt.
 
-- [**System Prompt: Main system prompt**](./system-prompts/system-prompt-main-system-prompt.md) (**2601** tks) - Core system prompt for Claude Code defining behavior, tone, and tool usage.
-- [System Prompt: Learning mode](./system-prompts/system-prompt-learning-mode.md) (**1042** tks) - System Prompt: Main system prompt for learning mode with human collaboration.
+- [**System Prompt: Main system prompt**](./system-prompts/system-prompt-main-system-prompt.md) (**2601** tks) - Core system prompt for Claude Code defining behavior, tone, and tool usage policies.
 - [System Prompt: Learning mode (insights)](./system-prompts/system-prompt-learning-mode-insights.md) (**142** tks) - Instructions for providing educational insights when learning mode is active.
+- [System Prompt: Learning mode](./system-prompts/system-prompt-learning-mode.md) (**1042** tks) - System Prompt: Main system prompt for learning mode with human collaboration instructions.
 - [System Prompt: MCP CLI](./system-prompts/system-prompt-mcp-cli.md) (**1357** tks) - Instructions for using mcp-cli to interact with Model Context Protocol servers.
 
 ### System Reminders
@@ -87,19 +87,19 @@ Text for large system reminders.
 > [!NOTE]
 > Note that we're planning to add a **system reminder creator/editor** to [tweakcc](https://github.com/Piebald-AI/tweakcc); :+1: [this issue](https://github.com/Piebald-AI/tweakcc/issues/113) if you're interested in that idea.
 
-- [System Reminder: Plan mode is active](./system-prompts/system-reminder-plan-mode-is-active.md) (**242** tks) - System reminder sent to Claude when the user enters plan mode.
 - [System Reminder: Plan mode is active (enhanced)](./system-prompts/system-reminder-plan-mode-is-active-enhanced.md) (**1093** tks) - Enhanced plan mode system reminder.
 - [System Reminder: Plan mode is active (for subagents)](./system-prompts/system-reminder-plan-mode-is-active-for-subagents.md) (**310** tks) - Simplified plan mode system reminder for sub agents.
+- [System Reminder: Plan mode is active](./system-prompts/system-reminder-plan-mode-is-active.md) (**242** tks) - System reminder sent to Claude when the user enters plan mode.
 
 ### Builtin Tool Descriptions
 
 - [Tool Description: Bash](./system-prompts/tool-description-bash.md) (**1074** tks) - Description for the Bash tool, which allows Claude to run shell commands.
 - [Tool Description: Edit](./system-prompts/tool-description-edit.md) (**278** tks) - Tool description for performing exact string replacements in files.
-- [Tool Description: ExitPlanMode](./system-prompts/tool-description-exitplanmode.md) (**342** tks) - Description for the ExitPlanMode tool, which presents a plan dialog for the.
-- [Tool Description: ExitPlanMode v2](./system-prompts/tool-description-exitplanmode-v2.md) (**450** tks) - V2 description for the ExitPlanMode tool, which presents a plan dialog for the.
+- [Tool Description: ExitPlanMode v2](./system-prompts/tool-description-exitplanmode-v2.md) (**450** tks) - V2 description for the ExitPlanMode tool, which presents a plan dialog for the user to approve.
+- [Tool Description: ExitPlanMode](./system-prompts/tool-description-exitplanmode.md) (**342** tks) - Description for the ExitPlanMode tool, which presents a plan dialog for the user to approve.
 - [Tool Description: Glob](./system-prompts/tool-description-glob.md) (**122** tks) - Tool description for file pattern matching and searching by name.
 - [Tool Description: Grep](./system-prompts/tool-description-grep.md) (**300** tks) - Tool description for content search using ripgrep.
-- [Tool Description: LSP](./system-prompts/tool-description-lsp.md) (**172** tks) - Description for the LSP tool.
+- [Tool Description: LSP](./system-prompts/tool-description-lsp.md) (**172** tks) - Description for the LSP tool..
 - [Tool Description: NotebookEdit](./system-prompts/tool-description-notebookedit.md) (**121** tks) - Tool description for editing Jupyter notebook cells.
 - [Tool Description: ReadFile](./system-prompts/tool-description-readfile.md) (**439** tks) - Tool description for reading files.
 - [Tool Description: Skill](./system-prompts/tool-description-skill.md) (**279** tks) - Tool description for executing skills in the main conversation.

scripts/updatePrompts.js

@@ -0,0 +1,470 @@
+#!/usr/bin/env node
+
+import { readFileSync, writeFileSync, readdirSync, unlinkSync } from 'fs';
+import { join, dirname } from 'path';
+import { fileURLToPath } from 'url';
+
+const __filename = fileURLToPath(import.meta.url);
+const __dirname = dirname(__filename);
+const ROOT_DIR = join(__dirname, '..');
+const SYSTEM_PROMPTS_DIR = join(ROOT_DIR, 'system-prompts');
+const README_PATH = join(ROOT_DIR, 'README.md');
+
+// Get API key from environment
+const ANTHROPIC_API_KEY = process.env.ANTHROPIC_API_KEY;
+if (!ANTHROPIC_API_KEY) {
+  console.error('Error: ANTHROPIC_API_KEY environment variable is required');
+  console.error('Set it with: export ANTHROPIC_API_KEY=your-api-key');
+  process.exit(1);
+}
+
+/**
+ * Count tokens using Anthropic's token counting API
+ */
+async function countTokens(text) {
+  const response = await fetch('https://api.anthropic.com/v1/messages/count_tokens', {
+    method: 'POST',
+    headers: {
+      'Content-Type': 'application/json',
+      'anthropic-version': '2023-06-01',
+      'x-api-key': ANTHROPIC_API_KEY
+    },
+    body: JSON.stringify({
+      model: 'claude-sonnet-4-20250514',
+      messages: [
+        {
+          role: 'user',
+          content: text
+        }
+      ]
+    })
+  });
+
+  if (!response.ok) {
+    const error = await response.text();
+    throw new Error(`Token counting API error: ${response.status} ${error}`);
+  }
+
+  const data = await response.json();
+  return data.input_tokens;
+}
+
+/**
+ * Batch count tokens for multiple prompts with rate limiting
+ */
+async function countTokensBatch(prompts, batchSize = 5, delayMs = 100) {
+  const results = new Map();
+
+  for (let i = 0; i < prompts.length; i += batchSize) {
+    const batch = prompts.slice(i, i + batchSize);
+    const promises = batch.map(async ({ filename, content }) => {
+      try {
+        const tokens = await countTokens(content);
+        return { filename, tokens };
+      } catch (err) {
+        console.error(`Error counting tokens for ${filename}: ${err.message}`);
+        return { filename, tokens: 0 };
+      }
+    });
+
+    const batchResults = await Promise.all(promises);
+    batchResults.forEach(({ filename, tokens }) => {
+      results.set(filename, tokens);
+    });
+
+    // Rate limiting delay between batches
+    if (i + batchSize < prompts.length) {
+      await new Promise(resolve => setTimeout(resolve, delayMs));
+    }
+  }
+
+  return results;
+}
+
+/**
+ * Convert prompt name to filename
+ * Examples:
+ *   "Agent Prompt: Explore" → "agent-prompt-explore.md"
+ *   "System Prompt: Main system prompt" → "system-prompt-main-system-prompt.md"
+ *   "Tool Description: Bash" → "tool-description-bash.md"
+ */
+function nameToFilename(name) {
+  // Determine prefix based on the name prefix
+  let prefix = '';
+  let namePart = name;
+
+  if (name.startsWith('Agent Prompt: ')) {
+    prefix = 'agent-prompt-';
+    namePart = name.substring('Agent Prompt: '.length);
+  } else if (name.startsWith('System Prompt: ')) {
+    prefix = 'system-prompt-';
+    namePart = name.substring('System Prompt: '.length);
+  } else if (name.startsWith('System Reminder: ')) {
+    prefix = 'system-reminder-';
+    namePart = name.substring('System Reminder: '.length);
+  } else if (name.startsWith('Tool Description: ')) {
+    prefix = 'tool-description-';
+    namePart = name.substring('Tool Description: '.length);
+  } else if (name.startsWith('Data: ')) {
+    prefix = 'data-';
+    namePart = name.substring('Data: '.length);
+  }
+
+  // Convert to lowercase and replace special chars
+  const filename = namePart
+    .toLowerCase()
+    .replace(/\./g, '') // Remove dots
+    .replace(/\s+/g, '-') // Spaces to hyphens
+    .replace(/[()]/g, '') // Remove parentheses
+    .replace(/\//g, '-') // Slashes to hyphens
+    .replace(/-+/g, '-') // Collapse multiple hyphens
+    .replace(/^-|-$/g, ''); // Trim hyphens from start/end
+
+  return prefix + filename + '.md';
+}
+
+/**
+ * Reconstruct the full prompt content from pieces and identifiers
+ */
+function reconstructPrompt(prompt) {
+  if (prompt.pieces.length === 0) return '';
+  if (prompt.pieces.length === 1) return prompt.pieces[0];
+
+  let result = '';
+  let identifierIndex = 0;
+
+  for (let i = 0; i < prompt.pieces.length; i++) {
+    result += prompt.pieces[i];
+
+    // Add variable name (pieces already contain ${ and } delimiters)
+    if (i < prompt.pieces.length - 1 && identifierIndex < prompt.identifiers.length) {
+      const identifierId = prompt.identifiers[identifierIndex].toString();
+      const variableName = prompt.identifierMap[identifierId];
+      if (variableName) {
+        result += variableName;
+      }
+      identifierIndex++;
+    }
+  }
+
+  return result;
+}
+
+/**
+ * Create markdown file content with HTML comment metadata
+ */
+function createMarkdownContent(prompt, reconstructedContent) {
+  const variables = Object.values(prompt.identifierMap || {});
+
+  let content = '<!--\n';
+  content += `name: '${prompt.name}'\n`;
+  content += `description: ${prompt.description.includes('\n') ? '>\n  ' + prompt.description.replace(/\n/g, '\n  ') : prompt.description}\n`;
+  content += `ccVersion: ${prompt.version}\n`;
+
+  if (variables.length > 0) {
+    content += 'variables:\n';
+    variables.forEach(varName => {
+      content += `  - ${varName}\n`;
+    });
+  }
+
+  content += '-->\n';
+  content += reconstructedContent;
+
+  // Ensure file ends with newline
+  if (!content.endsWith('\n')) {
+    content += '\n';
+  }
+
+  return content;
+}
+
+/**
+ * Parse existing markdown file to extract metadata
+ */
+function parseMarkdownFile(filepath) {
+  try {
+    const content = readFileSync(filepath, 'utf-8');
+    const commentMatch = content.match(/<!--\n([\s\S]*?)\n-->/);
+    if (!commentMatch) return null;
+
+    const metadataSection = commentMatch[1];
+    const nameMatch = metadataSection.match(/name: '(.+)'/);
+    const descMatch = metadataSection.match(/description: (.+?)(?=\nccVersion:)/s);
+
+    return {
+      name: nameMatch ? nameMatch[1] : null,
+      description: descMatch ? descMatch[1].replace(/>\n\s+/g, '').trim() : null,
+      fullContent: content
+    };
+  } catch (err) {
+    return null;
+  }
+}
+
+/**
+ * Categorize prompts based on their name
+ */
+function categorizePrompt(name) {
+  if (name.startsWith('Agent Prompt: ')) {
+    const namePart = name.substring('Agent Prompt: '.length);
+    // Sub-categorize agent prompts
+    if (['Explore', 'Plan mode (enhanced)', 'Task tool'].some(sub => namePart.startsWith(sub))) {
+      return { category: 'Agent Prompts', subcategory: 'Sub-agents' };
+    } else if (['Agent creation architect', 'CLAUDE.md creation', 'Status line setup'].some(sub => namePart.includes(sub))) {
+      return { category: 'Agent Prompts', subcategory: 'Creation Assistants' };
+    } else if (namePart.includes('slash command') || namePart.startsWith('/')) {
+      return { category: 'Agent Prompts', subcategory: 'Slash commands' };
+    } else {
+      return { category: 'Agent Prompts', subcategory: 'Utilities' };
+    }
+  } else if (name.startsWith('System Prompt: ')) {
+    return { category: 'System Prompt', subcategory: null };
+  } else if (name.startsWith('System Reminder: ')) {
+    return { category: 'System Reminders', subcategory: null };
+  } else if (name.startsWith('Tool Description: ')) {
+    // Check for "additional notes" subcategory
+    if (name.includes('(') && name.includes(')')) {
+      return { category: 'Builtin Tool Descriptions', subcategory: 'Additional notes for some Tool Descriptions' };
+    }
+    return { category: 'Builtin Tool Descriptions', subcategory: null };
+  } else if (name.startsWith('Data: ')) {
+    return { category: 'Data', subcategory: null };
+  }
+
+  return { category: 'Other', subcategory: null };
+}
+
+/**
+ * Update or create README entry for a prompt
+ */
+function createReadmeEntry(prompt, filename, tokens, isBold = false) {
+  const link = isBold ? `[**${prompt.name}**]` : `[${prompt.name}]`;
+  const path = `./system-prompts/${filename}`;
+  const tokenCount = `(**${tokens}** tks)`;
+  const description = prompt.description.replace(/\n\s+/g, ' ').trim();
+
+  return `- ${link}(${path}) ${tokenCount} - ${description}.`;
+}
+
+/**
+ * Main update function
+ */
+async function updateFromJSON(jsonPath) {
+  console.log(`Reading JSON from: ${jsonPath}`);
+  const jsonData = JSON.parse(readFileSync(jsonPath, 'utf-8'));
+
+  console.log(`Version: ${jsonData.version}`);
+  console.log(`Prompts count: ${jsonData.prompts.length}`);
+
+  // Track all prompts by filename
+  const promptsByFilename = new Map();
+  const changedPrompts = new Set();
+  const newPrompts = new Set();
+  const promptsToCount = [];
+
+  // First pass: Process files and identify what needs token counting
+  for (const prompt of jsonData.prompts) {
+    const filename = nameToFilename(prompt.name);
+    const filepath = join(SYSTEM_PROMPTS_DIR, filename);
+    const reconstructedContent = reconstructPrompt(prompt);
+    const newMarkdownContent = createMarkdownContent(prompt, reconstructedContent);
+
+    // Check if file exists and compare
+    const existingFile = parseMarkdownFile(filepath);
+
+    if (existingFile) {
+      // Compare content
+      if (existingFile.fullContent.trim() !== newMarkdownContent.trim()) {
+        console.log(`⚠️  Changed: ${filename}`);
+        unlinkSync(filepath); // Delete old file
+        writeFileSync(filepath, newMarkdownContent);
+        changedPrompts.add(filename);
+      }
+    } else {
+      console.log(`✨ New: ${filename}`);
+      writeFileSync(filepath, newMarkdownContent);
+      newPrompts.add(filename);
+    }
+
+    // Store for token counting
+    promptsToCount.push({ filename, content: reconstructedContent, prompt });
+  }
+
+  // Batch count tokens for all prompts
+  console.log('\n🔢 Counting tokens...');
+  const tokenCounts = await countTokensBatch(promptsToCount);
+
+  // Store prompt info for README updates
+  for (const { filename, prompt } of promptsToCount) {
+    const tokens = tokenCounts.get(filename) || 0;
+    promptsByFilename.set(filename, { prompt, tokens });
+  }
+
+  // Find deleted prompts
+  const allMdFiles = readdirSync(SYSTEM_PROMPTS_DIR).filter(f => f.endsWith('.md'));
+  const deletedFiles = allMdFiles.filter(f => !promptsByFilename.has(f));
+
+  if (deletedFiles.length > 0) {
+    console.log('\n🗑️  Deleting removed prompts:');
+    deletedFiles.forEach(f => {
+      console.log(`   - ${f}`);
+      unlinkSync(join(SYSTEM_PROMPTS_DIR, f));
+    });
+  }
+
+  // Update README
+  console.log('\n📝 Updating README.md...');
+  updateReadme(promptsByFilename, jsonData.version);
+
+  console.log('\n✅ Update complete!');
+  console.log(`   New: ${newPrompts.size}`);
+  console.log(`   Changed: ${changedPrompts.size}`);
+  console.log(`   Deleted: ${deletedFiles.length}`);
+}
+
+/**
+ * Update README.md with new prompt information
+ */
+function updateReadme(promptsByFilename, version) {
+  let readme = readFileSync(README_PATH, 'utf-8');
+  const lines = readme.split('\n');
+
+  // Update version in header
+  lines[2] = `This repository contains an up-to-date list of all Claude Code's various system prompts and their associated token counts as of ${version}.`;
+
+  // Organize prompts by category
+  const categories = {
+    'Agent Prompts': {
+      'Sub-agents': [],
+      'Creation Assistants': [],
+      'Slash commands': [],
+      'Utilities': []
+    },
+    'System Prompt': { 'main': [] },
+    'System Reminders': { 'main': [] },
+    'Builtin Tool Descriptions': {
+      'main': [],
+      'Additional notes for some Tool Descriptions': []
+    },
+    'Data': { 'main': [] }
+  };
+
+  // Categorize all prompts
+  for (const [filename, { prompt, tokens }] of promptsByFilename) {
+    const { category, subcategory } = categorizePrompt(prompt.name);
+
+    // Special handling for bold main system prompt
+    const isBold = prompt.name === 'System Prompt: Main system prompt';
+    const entry = createReadmeEntry(prompt, filename, tokens, isBold);
+
+    if (category === 'Agent Prompts') {
+      categories['Agent Prompts'][subcategory].push(entry);
+    } else if (category === 'System Prompt') {
+      categories['System Prompt']['main'].push(entry);
+    } else if (category === 'System Reminders') {
+      categories['System Reminders']['main'].push(entry);
+    } else if (category === 'Builtin Tool Descriptions') {
+      const subcat = subcategory || 'main';
+      categories['Builtin Tool Descriptions'][subcat].push(entry);
+    } else if (category === 'Data') {
+      categories['Data']['main'].push(entry);
+    }
+  }
+
+  // Sort entries alphabetically within each category
+  for (const category of Object.values(categories)) {
+    for (const subcategory of Object.values(category)) {
+      if (Array.isArray(subcategory)) {
+        subcategory.sort();
+      }
+    }
+  }
+
+  // Rebuild README sections
+  const newLines = [];
+  let i = 0;
+
+  // Copy everything up to "### Agent Prompts"
+  while (i < lines.length && !lines[i].startsWith('### Agent Prompts')) {
+    newLines.push(lines[i]);
+    i++;
+  }
+
+  // Agent Prompts section
+  newLines.push('### Agent Prompts');
+  newLines.push('');
+  newLines.push('Sub-agents and utilities.');
+  newLines.push('');
+  newLines.push('#### Sub-agents');
+  newLines.push('');
+  newLines.push(...categories['Agent Prompts']['Sub-agents']);
+  newLines.push('');
+  newLines.push('### Creation Assistants');
+  newLines.push('');
+  newLines.push(...categories['Agent Prompts']['Creation Assistants']);
+  newLines.push('');
+  newLines.push('### Slash commands');
+  newLines.push('');
+  newLines.push(...categories['Agent Prompts']['Slash commands']);
+  newLines.push('');
+  newLines.push('### Utilities');
+  newLines.push('');
+  newLines.push(...categories['Agent Prompts']['Utilities']);
+  newLines.push('');
+
+  // Data section (commented out if has entries)
+  if (categories['Data']['main'].length > 0) {
+    newLines.push('<!--');
+    newLines.push('### Data');
+    newLines.push('');
+    newLines.push('Misc large strings.');
+    newLines.push('');
+    newLines.push(...categories['Data']['main']);
+    newLines.push('-->');
+    newLines.push('');
+  }
+
+  // System Prompt section
+  newLines.push('### System Prompt');
+  newLines.push('');
+  newLines.push('Parts of the main system prompt.');
+  newLines.push('');
+  newLines.push(...categories['System Prompt']['main']);
+  newLines.push('');
+
+  // System Reminders section
+  newLines.push('### System Reminders');
+  newLines.push('');
+  newLines.push('Text for large system reminders.');
+  newLines.push('');
+  newLines.push('> [!NOTE]');
+  newLines.push('> Note that we\'re planning to add a **system reminder creator/editor** to [tweakcc](https://github.com/Piebald-AI/tweakcc); :+1: [this issue](https://github.com/Piebald-AI/tweakcc/issues/113) if you\'re interested in that idea.');
+  newLines.push('');
+  newLines.push(...categories['System Reminders']['main']);
+  newLines.push('');
+
+  // Builtin Tool Descriptions section
+  newLines.push('### Builtin Tool Descriptions');
+  newLines.push('');
+  newLines.push(...categories['Builtin Tool Descriptions']['main']);
+  newLines.push('');
+  newLines.push('**Additional notes for some Tool Desscriptions**');
+  newLines.push('');
+  newLines.push(...categories['Builtin Tool Descriptions']['Additional notes for some Tool Descriptions']);
+  newLines.push('');
+
+  // Write updated README
+  writeFileSync(README_PATH, newLines.join('\n'));
+}
+
+// Main execution
+const args = process.argv.slice(2);
+if (args.length === 0) {
+  console.error('Usage: node updatePrompts.js <path-to-prompts.json>');
+  console.error('Example: node updatePrompts.js /path/to/tweakcc/data/prompts/prompts-2.0.44.json');
+  process.exit(1);
+}
+
+const jsonPath = args[0];
+await updateFromJSON(jsonPath);

system-prompts/agent-prompt-claudemd-creation.md

@@ -1,8 +1,6 @@
 <!--
 name: 'Agent Prompt: CLAUDE.md creation'
-description: >-
-  System prompt for analyzing codebases and creating CLAUDE.md documentation
-  files
+description: System prompt for analyzing codebases and creating CLAUDE.md documentation files
 ccVersion: 2.0.14
 -->
 Please analyze this codebase and create a CLAUDE.md file, which will be given to future instances of Claude Code to operate in this repository.

system-prompts/agent-prompt-prompt-hook-execution.md

@@ -1,8 +1,6 @@
 <!--
 name: 'Agent Prompt: Prompt Hook execution'
-description: >-
-  Prompt given to Claude when acting evaluating whether to pass or fail a prompt
-  hook.
+description: Prompt given to Claude when acting evaluating whether to pass or fail a prompt hook.
 ccVersion: 2.0.41
 -->
 You are evaluating a hook in Claude Code.

system-prompts/agent-prompt-security-review-slash.md

@@ -1,8 +1,6 @@
 <!--
 name: 'Agent Prompt: /security-review slash'
-description: >-
-  Comprehensive security review prompt for analyzing code changes with focus on
-  exploitable vulnerabilities
+description: Comprehensive security review prompt for analyzing code changes with focus on exploitable vulnerabilities
 ccVersion: 2.0.14
 -->
 ---

system-prompts/agent-prompt-status-line-setup.md

@@ -1,8 +1,6 @@
 <!--
 name: 'Agent Prompt: Status line setup'
-description: >-
-  System prompt for the statusline-setup agent that configures status line
-  display
+description: System prompt for the statusline-setup agent that configures status line display
 ccVersion: 2.0.14
 -->
 You are a status line setup agent for Claude Code. Your job is to create or update the statusLine command in the user's Claude Code settings.

system-prompts/agent-prompt-webfetch-summarizer.md

@@ -1,8 +1,6 @@
 <!--
 name: 'Agent Prompt: WebFetch summarizer'
-description: >-
-  Prompt for agent that summarizes verbose output from WebFetch for the main
-  model
+description: Prompt for agent that summarizes verbose output from WebFetch for the main model
 ccVersion: 2.0.14
 variables:
   - WEB_CONTENT

system-prompts/data-github-actions-workflow-for-@claude-mentions.md

@@ -1,8 +1,6 @@
 <!--
 name: 'Data: GitHub Actions workflow for @claude mentions'
-description: >-
-  GitHub Actions workflow template for triggering Claude Code via @claude
-  mentions
+description: GitHub Actions workflow template for triggering Claude Code via @claude mentions
 ccVersion: 2.0.14
 -->
 name: Claude Code

system-prompts/data-github-actions-workflow-for-automated-code-review-beta.md

@@ -1,8 +1,6 @@
 <!--
 name: 'Data: GitHub Actions workflow for automated code review (beta)'
-description: >-
-  GitHub Actions workflow template for automated Claude Code reviews using
-  direct_prompt
+description: GitHub Actions workflow template for automated Claude Code reviews using direct_prompt
 ccVersion: 2.0.14
 -->
 name: Claude Code Review

system-prompts/system-prompt-learning-mode.md

@@ -1,8 +1,6 @@
 <!--
 name: 'System Prompt: Learning mode'
-description: >-
-  System Prompt: Main system prompt for learning mode with human collaboration
-  instructions
+description: System Prompt: Main system prompt for learning mode with human collaboration instructions
 ccVersion: 2.0.14
 variables:
   - ICONS_OBJECT

system-prompts/system-prompt-main-system-prompt.md

@@ -1,8 +1,6 @@
 <!--
 name: 'System Prompt: Main system prompt'
-description: >-
-  Core system prompt for Claude Code defining behavior, tone, and tool usage
-  policies
+description: Core system prompt for Claude Code defining behavior, tone, and tool usage policies
 ccVersion: 2.0.43
 variables:
   - OUTPUT_STYLE_CONFIG

system-prompts/tool-description-bash.md

@@ -1,6 +1,6 @@
 <!--
 name: 'Tool Description: Bash'
-description: 'Description for the Bash tool, which allows Claude to run shell commands'
+description: Description for the Bash tool, which allows Claude to run shell commands
 ccVersion: 2.0.25
 variables:
   - CUSTOM_TIMEOUT_MS

system-prompts/tool-description-exitplanmode-v2.md

@@ -1,8 +1,6 @@
 <!--
 name: 'Tool Description: ExitPlanMode v2'
-description: >-
-  V2 description for the ExitPlanMode tool, which presents a plan dialog for the
-  user to approve
+description: V2 description for the ExitPlanMode tool, which presents a plan dialog for the user to approve
 ccVersion: 2.0.43
 variables:
   - ASK_USER_QUESTION_TOOL_NAME

system-prompts/tool-description-exitplanmode.md

@@ -1,8 +1,6 @@
 <!--
 name: 'Tool Description: ExitPlanMode'
-description: >-
-  Description for the ExitPlanMode tool, which presents a plan dialog for the
-  user to approve
+description: Description for the ExitPlanMode tool, which presents a plan dialog for the user to approve
 ccVersion: 2.0.30
 variables:
   - ASK_USER_QUESTION_TOOL

system-prompts/tool-description-task.md

@@ -7,6 +7,7 @@ variables:
   - AGENT_TYPE_REGISTRY_STRING
   - READ_TOOL
   - GLOB_TOOL
+  - TASK_TOOL
   - WRITE_TOOL
 -->
 Launch a new agent to handle complex, multi-step tasks autonomously.