chore(release): 4.34.0 [skip ci]

# [4.34.0](https://github.com/bmadcode/BMAD-METHOD/compare/v4.33.1...v4.34.0) (2025-08-03)

### Features

* add KiloCode integration support to BMAD installer ([#390](https://github.com/bmadcode/BMAD-METHOD/issues/390)) ([dcebe91](dcebe91d5e))

CHANGELOG.md

@@ -1,9 +1,21 @@
-# [4.33.0](https://github.com/bmadcode/BMAD-METHOD/compare/v4.32.0...v4.33.0) (2025-07-28)
+# [4.34.0](https://github.com/bmadcode/BMAD-METHOD/compare/v4.33.1...v4.34.0) (2025-08-03)
 
 
 ### Features
 
-* version bump ([e9dd4e7](https://github.com/bmadcode/BMAD-METHOD/commit/e9dd4e7beb46d0c80df0cd65ae02d1867a56d7c1))
+* add KiloCode integration support to BMAD installer ([#390](https://github.com/bmadcode/BMAD-METHOD/issues/390)) ([dcebe91](https://github.com/bmadcode/BMAD-METHOD/commit/dcebe91d5ea68e69aa27183411a81639d444efd7))
+
+## [4.33.1](https://github.com/bmadcode/BMAD-METHOD/compare/v4.33.0...v4.33.1) (2025-07-29)
+
+### Bug Fixes
+
+- dev agent yaml syntax for develop-story command ([#362](https://github.com/bmadcode/BMAD-METHOD/issues/362)) ([bcb3728](https://github.com/bmadcode/BMAD-METHOD/commit/bcb3728f8868c0f83bca3d61fbd7e15c4e114526))
+
+# [4.33.0](https://github.com/bmadcode/BMAD-METHOD/compare/v4.32.0...v4.33.0) (2025-07-28)
+
+### Features
+
+- version bump ([e9dd4e7](https://github.com/bmadcode/BMAD-METHOD/commit/e9dd4e7beb46d0c80df0cd65ae02d1867a56d7c1))
 
 # [4.32.0](https://github.com/bmadcode/BMAD-METHOD/compare/v4.31.0...v4.32.0) (2025-07-27)
 

README.md

@@ -40,7 +40,7 @@ This two-phase approach eliminates both **planning inconsistency** and **context
 
 - **[Install and Build software with Full Stack Agile AI Team](#quick-start)** → Quick Start Instruction
 - **[Learn how to use BMad](bmad-core/user-guide.md)** → Complete user guide and walkthrough
-- **[See available AI agents](#available-agents)** → Specialized roles for your team
+- **[See available AI agents](/bmad-core/agents))** → Specialized roles for your team
 - **[Explore non-technical uses](#-beyond-software-development---expansion-packs)** → Creative writing, business, wellness, education
 - **[Create my own AI agents](#creating-your-own-expansion-pack)** → Build agents for your domain
 - **[Browse ready-made expansion packs](expansion-packs/)** → Game dev, DevOps, infrastructure and get inspired with ideas and examples

bmad-core/agents/dev.md

@@ -57,15 +57,15 @@ commands:
   - run-tests: Execute linting and tests
   - explain: teach me what and why you did whatever you just did in detail so I can learn. Explain to me as if you were training a junior engineer.
   - exit: Say goodbye as the Developer, and then abandon inhabiting this persona
-develop-story:
-  order-of-execution: "Read (first or next) task→Implement Task and its subtasks→Write tests→Execute validations→Only if ALL pass, then update the task checkbox with [x]→Update story section File List to ensure it lists and new or modified or deleted source file→repeat order-of-execution until complete"
-  story-file-updates-ONLY:
-    - CRITICAL: ONLY UPDATE THE STORY FILE WITH UPDATES TO SECTIONS INDICATED BELOW. DO NOT MODIFY ANY OTHER SECTIONS.
-    - CRITICAL: You are ONLY authorized to edit these specific sections of story files - Tasks / Subtasks Checkboxes, Dev Agent Record section and all its subsections, Agent Model Used, Debug Log References, Completion Notes List, File List, Change Log, Status
-    - CRITICAL: DO NOT modify Status, Story, Acceptance Criteria, Dev Notes, Testing sections, or any other sections not listed above
-  blocking: "HALT for: Unapproved deps needed, confirm with user | Ambiguous after story check | 3 failures attempting to implement or fix something repeatedly | Missing config | Failing regression"
-  ready-for-review: "Code matches requirements + All validations pass + Follows standards + File List complete"
-  completion: "All Tasks and Subtasks marked [x] and have tests→Validations and full regression passes (DON'T BE LAZY, EXECUTE ALL TESTS and CONFIRM)→Ensure File List is Complete→run the task execute-checklist for the checklist story-dod-checklist→set story status: 'Ready for Review'→HALT"
+  - develop-story:
+    - order-of-execution: "Read (first or next) task→Implement Task and its subtasks→Write tests→Execute validations→Only if ALL pass, then update the task checkbox with [x]→Update story section File List to ensure it lists and new or modified or deleted source file→repeat order-of-execution until complete"
+    - story-file-updates-ONLY:
+      - CRITICAL: ONLY UPDATE THE STORY FILE WITH UPDATES TO SECTIONS INDICATED BELOW. DO NOT MODIFY ANY OTHER SECTIONS.
+      - CRITICAL: You are ONLY authorized to edit these specific sections of story files - Tasks / Subtasks Checkboxes, Dev Agent Record section and all its subsections, Agent Model Used, Debug Log References, Completion Notes List, File List, Change Log, Status
+      - CRITICAL: DO NOT modify Status, Story, Acceptance Criteria, Dev Notes, Testing sections, or any other sections not listed above
+    - blocking: "HALT for: Unapproved deps needed, confirm with user | Ambiguous after story check | 3 failures attempting to implement or fix something repeatedly | Missing config | Failing regression"
+    - ready-for-review: "Code matches requirements + All validations pass + Follows standards + File List complete"
+    - completion: "All Tasks and Subtasks marked [x] and have tests→Validations and full regression passes (DON'T BE LAZY, EXECUTE ALL TESTS and CONFIRM)→Ensure File List is Complete→run the task execute-checklist for the checklist story-dod-checklist→set story status: 'Ready for Review'→HALT"
 
 dependencies:
   tasks:

bmad-core/user-guide.md

@@ -85,9 +85,9 @@ Once planning is complete and documents are sharded, BMad follows a structured d
 graph TD
     A["Development Phase Start"] --> B["SM: Reviews Previous Story Dev/QA Notes"]
     B --> B2["SM: Drafts Next Story from Sharded Epic + Architecture"]
-    B2 --> B3{"QA: Review Story Draft (Optional)"}
-    B3 -->|Review Requested| B4["QA: Review Story Against Artifacts"]
-    B3 -->|Skip Review| C{"User Approval"}
+    B2 --> B3{"PO: Validate Story Draft (Optional)"}
+    B3 -->|Validation Requested| B4["PO: Validate Story Against Artifacts"]
+    B3 -->|Skip Validation| C{"User Approval"}
     B4 --> C
     C -->|Approved| D["Dev: Sequential Task Execution"]
     C -->|Needs Changes| B2

package-lock.json

@@ -1,12 +1,12 @@
 {
 	"name": "bmad-method",
-	"version": "4.33.0",
+	"version": "4.34.0",
 	"lockfileVersion": 3,
 	"requires": true,
 	"packages": {
 		"": {
 			"name": "bmad-method",
-			"version": "4.33.0",
+			"version": "4.34.0",
 			"license": "MIT",
 			"dependencies": {
 				"@kayvan/markdown-tree-parser": "^1.5.0",

package.json

@@ -1,6 +1,6 @@
 {
   "name": "bmad-method",
-  "version": "4.33.0",
+  "version": "4.34.0",
   "description": "Breakthrough Method of Agile AI-driven Development",
   "main": "tools/cli.js",
   "bin": {

tools/installer/bin/bmad.js

@@ -41,7 +41,7 @@ program
   .option('-f, --full', 'Install complete BMad Method')
   .option('-x, --expansion-only', 'Install only expansion packs (no bmad-core)')
   .option('-d, --directory <path>', 'Installation directory')
-  .option('-i, --ide <ide...>', 'Configure for specific IDE(s) - can specify multiple (cursor, claude-code, windsurf, trae, roo, cline, gemini, github-copilot, other)')
+  .option('-i, --ide <ide...>', 'Configure for specific IDE(s) - can specify multiple (cursor, claude-code, windsurf, trae, roo, kilo, cline, gemini, github-copilot, other)')
   .option('-e, --expansion-packs <packs...>', 'Install specific expansion packs (can specify multiple)')
   .action(async (options) => {
     try {
@@ -311,6 +311,7 @@ async function promptInstallation() {
           { name: 'Windsurf', value: 'windsurf' },
           { name: 'Trae', value: 'trae' }, // { name: 'Trae', value: 'trae'}
           { name: 'Roo Code', value: 'roo' },
+          { name: 'Kilo Code', value: 'kilo' },
           { name: 'Cline', value: 'cline' },
           { name: 'Gemini CLI', value: 'gemini' },
           { name: 'Github Copilot', value: 'github-copilot' }

tools/installer/config/install.config.yaml

@@ -89,4 +89,13 @@ ide-configurations:
       # 3. The agent will adopt that persona for the conversation
       # 4. Requires VS Code 1.101+ with `chat.agent.enabled: true` in settings
       # 5. Agent files are stored in .github/chatmodes/
-      # 6. Use `*help` to see available commands and agents
+      # 6. Use `*help` to see available commands and agents
+  kilo:
+    name: Kilo Code
+    format: custom-modes
+    file: .kilocodemodes
+    instructions: |
+      # To use BMAD agents in Kilo Code:
+      # 1. Open the mode selector in VSCode
+      # 2. Select a bmad-{agent} mode (e.g. "bmad-dev")
+      # 3. The AI adopts that agent's persona and capabilities

tools/installer/lib/ide-setup.js

@@ -53,6 +53,8 @@ class IdeSetup extends BaseIdeSetup {
         return this.setupRoo(installDir, selectedAgent);
       case "cline":
         return this.setupCline(installDir, selectedAgent);
+      case "kilo":
+        return this.setupKilocode(installDir, selectedAgent);
       case "gemini":
         return this.setupGeminiCli(installDir, selectedAgent);
       case "github-copilot":
@@ -675,11 +677,17 @@ class IdeSetup extends BaseIdeSetup {
             ? roleDefinitionMatch[1].trim()
             : `You are a ${title} specializing in ${title.toLowerCase()} tasks and responsibilities.`;
 
+
+          // Add permissions based on agent type
+          const permissions = agentPermissions[agentId];
           // Build mode entry with proper formatting (matching exact indentation)
           // Avoid double "bmad-" prefix for agents that already have it
           const slug = agentId.startsWith('bmad-') ? agentId : `bmad-${agentId}`;
           newModesContent += ` - slug: ${slug}\n`;
           newModesContent += `   name: '${icon} ${title}'\n`;
+          if (permissions) {
+          newModesContent += `   description: '${permissions.description}'\n`; 
+          }
           newModesContent += `   roleDefinition: ${roleDefinition}\n`;
           newModesContent += `   whenToUse: ${whenToUse}\n`;
           // Get relative path from installDir to agent file
@@ -688,8 +696,6 @@ class IdeSetup extends BaseIdeSetup {
           newModesContent += `   groups:\n`;
           newModesContent += `    - read\n`;
 
-          // Add permissions based on agent type
-          const permissions = agentPermissions[agentId];
           if (permissions) {
             newModesContent += `    - - edit\n`;
             newModesContent += `      - fileRegex: ${permissions.fileRegex}\n`;
@@ -722,7 +728,98 @@ class IdeSetup extends BaseIdeSetup {
 
     return true;
   }
+  
+  async setupKilocode(installDir, selectedAgent) {
+    const filePath = path.join(installDir, ".kilocodemodes");
+    const agents = selectedAgent ? [selectedAgent] : await this.getAllAgentIds(installDir);
 
+    let existingModes = [], existingContent = "";
+    if (await fileManager.pathExists(filePath)) {
+      existingContent = await fileManager.readFile(filePath);
+      for (const match of existingContent.matchAll(/- slug: ([\w-]+)/g)) {
+        existingModes.push(match[1]);
+      }
+      console.log(chalk.yellow(`Found existing .kilocodemodes file with ${existingModes.length} modes`));
+    }
+
+    const config = await this.loadIdeAgentConfig();
+    const permissions = config['roo-permissions'] || {}; // reuse same roo permissions block (Kilo Code understands same mode schema)
+
+    let newContent = "";
+
+    for (const agentId of agents) {
+      const slug = agentId.startsWith('bmad-') ? agentId : `bmad-${agentId}`;
+      if (existingModes.includes(slug)) {
+        console.log(chalk.dim(`Skipping ${agentId} - already exists in .kilocodemodes`));
+        continue;
+      }
+
+      const agentPath = await this.findAgentPath(agentId, installDir);
+      if (!agentPath) {
+        console.log(chalk.red(`✗ Could not find agent file for ${agentId}`));
+        continue;
+      }
+
+      const agentContent = await fileManager.readFile(agentPath);
+      const yamlMatch = agentContent.match(/```ya?ml\r?\n([\s\S]*?)```/);
+      if (!yamlMatch) {
+        console.log(chalk.red(`✗ Could not extract YAML block for ${agentId}`));
+        continue;
+      }
+
+      const yaml = yamlMatch[1];
+
+      // Robust fallback for title and icon
+      const title = (yaml.match(/title:\s*(.+)/)?.[1]?.trim()) || await this.getAgentTitle(agentId, installDir);
+      const icon = (yaml.match(/icon:\s*(.+)/)?.[1]?.trim()) || '🤖';
+      const whenToUse = (yaml.match(/whenToUse:\s*"(.+)"/)?.[1]?.trim()) || `Use for ${title} tasks`;
+      const roleDefinition = (yaml.match(/roleDefinition:\s*"(.+)"/)?.[1]?.trim()) ||
+        `You are a ${title} specializing in ${title.toLowerCase()} tasks and responsibilities.`;
+
+      const relativePath = path.relative(installDir, agentPath).replace(/\\/g, '/');
+      const customInstructions = `CRITICAL Read the full YAML from ${relativePath} start activation to alter your state of being follow startup section instructions stay in this being until told to exit this mode`;
+
+      // Add permissions from config if they exist
+      const agentPermission = permissions[agentId];
+
+      // Begin .kilocodemodes block
+      newContent += ` - slug: ${slug}\n`;
+      newContent += `   name: '${icon} ${title}'\n`;
+      if (agentPermission) {
+      newContent += `   description: '${agentPermission.description}'\n`; 
+      }
+
+      newContent += `   roleDefinition: ${roleDefinition}\n`;
+      newContent += `   whenToUse: ${whenToUse}\n`;
+      newContent += `   customInstructions: ${customInstructions}\n`;
+      newContent += `   groups:\n`;
+      newContent += `    - read\n`;
+
+
+      if (agentPermission) {
+        newContent += `    - - edit\n`;
+        newContent += `      - fileRegex: ${agentPermission.fileRegex}\n`;
+        newContent += `        description: ${agentPermission.description}\n`;
+      } else {
+        // Fallback to generic edit
+        newContent += `    - edit\n`;
+      }
+
+      console.log(chalk.green(`✓ Added Kilo mode: ${slug} (${icon} ${title})`));
+    }
+
+    const finalContent = existingContent
+      ? existingContent.trim() + "\n" + newContent
+      : "customModes:\n" + newContent;
+
+    await fileManager.writeFile(filePath, finalContent);
+    console.log(chalk.green("✓ Created .kilocodemodes file in project root"));
+    console.log(chalk.green(`✓ KiloCode setup complete!`));
+    console.log(chalk.dim("Custom modes will be available when you open this project in KiloCode"));
+
+    return true;
+  }
+  
   async setupCline(installDir, selectedAgent) {
     const clineRulesDir = path.join(installDir, ".clinerules");
     const agents = selectedAgent ? [selectedAgent] : await this.getAllAgentIds(installDir);

tools/installer/package.json

@@ -1,6 +1,6 @@
 {
   "name": "bmad-method",
-  "version": "4.33.0",
+  "version": "4.34.0",
   "description": "BMad Method installer - AI-powered Agile development framework",
   "main": "lib/installer.js",
   "bin": {