bmad-method 6.3.1-next.1 → 6.3.1-next.3

package/package.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://json.schemastore.org/package.json",
   "name": "bmad-method",
-  "version": "6.3.1-next.1",
+  "version": "6.3.1-next.3",
   "description": "Breakthrough Method of Agile AI-driven Development",
   "keywords": [
     "agile",

package/src/bmm-skills/4-implementation/bmad-quick-dev/step-01-clarify-and-route.md

@@ -1,6 +1,7 @@
 ---
 deferred_work_file: '{implementation_artifacts}/deferred-work.md'
 spec_file: '' # set at runtime for both routes before leaving this step
+story_key: '' # set at runtime to the current story's full sprint-status key (e.g. 3-2-digest-delivery) when the intent is an epic story and sprint-status resolution succeeds
 ---
 
 # Step 1: Clarify and Route
@@ -20,7 +21,7 @@ Before listing artifacts or prompting the user, check whether you already know t
 
 1. Explicit argument
    Did the user pass a specific file path, spec name, or clear instruction this message?
-   - If it points to a file that matches the spec template (has `status` frontmatter with a recognized value: draft, ready-for-dev, in-progress, in-review, or done) → set `spec_file` and **EARLY EXIT** to the appropriate step (step-02 for draft, step-03 for ready/in-progress, step-04 for review). For `done`, ingest as context and proceed to INSTRUCTIONS — do not resume.
+   - If it points to a file that matches the spec template (has `status` frontmatter with a recognized value: draft, ready-for-dev, in-progress, in-review, or done) → set `spec_file`. Before exiting, run **Story-key resolution** (below). Then **EARLY EXIT** to the appropriate step (step-02 for draft, step-03 for ready/in-progress, step-04 for review). For `done`, ingest as context and proceed to INSTRUCTIONS — do not resume.
    - Anything else (intent files, external docs, plans, descriptions) → ingest it as starting intent and proceed to INSTRUCTIONS. Do not attempt to infer a workflow state from it.
 
 2. Recent conversation
@@ -29,13 +30,19 @@ Before listing artifacts or prompting the user, check whether you already know t
 
 3. Otherwise — scan artifacts and ask
    - Active specs (`draft`, `ready-for-dev`, `in-progress`, `in-review`) in `{implementation_artifacts}`? → List them and HALT. Ask user which to resume (or `[N]` for new).
-     - If `draft` selected: Set `spec_file`. **EARLY EXIT** → `./step-02-plan.md` (resume planning from the draft)
-     - If `ready-for-dev` or `in-progress` selected: Set `spec_file`. **EARLY EXIT** → `./step-03-implement.md`
-     - If `in-review` selected: Set `spec_file`. **EARLY EXIT** → `./step-04-review.md`
+     - If `draft` selected: Set `spec_file`. Run **Story-key resolution** (below). **EARLY EXIT** → `./step-02-plan.md` (resume planning from the draft)
+     - If `ready-for-dev` or `in-progress` selected: Set `spec_file`. Run **Story-key resolution** (below). **EARLY EXIT** → `./step-03-implement.md`
+     - If `in-review` selected: Set `spec_file`. Run **Story-key resolution** (below). **EARLY EXIT** → `./step-04-review.md`
    - Unformatted spec or intent file lacking `status` frontmatter? → Suggest treating its contents as the starting intent. Do NOT attempt to infer a state and resume it.
 
 Never ask extra questions if you already understand what the user intends.
 
+### Story-key resolution
+
+This runs on ALL paths (early-exit and INSTRUCTIONS) whenever `spec_file` is set. Determine whether the spec is an epic story — use the spec's filename, frontmatter, and any loaded epics file to identify `{epic_num}` and `{story_num}`. If the spec is not an epic story, skip silently and leave `{story_key}` unset.
+
+If the spec is an epic story and `{sprint_status}` exists: find the `development_status` key matching `{epic_num}-{story_num}` by exact numeric equality on the first two segments (so `1-1` never collides with `1-10`). Exactly one match → set `{story_key}` to that full key. Zero or multiple matches → leave `{story_key}` unset (warn on multiple).
+
 ## INSTRUCTIONS
 
 1. Load context.
@@ -45,7 +52,7 @@ Never ask extra questions if you already understand what the user intends.
 
      **A) Epic story path** — if the intent is clearly an epic story:
 
-     1. Identify the epic number and (if present) the story number. If you can't identify an epic number, use path B.
+     1. Identify the epic number `{epic_num}` and (if present) the story number `{story_num}`. If you can't identify an epic number, use path B.
 
      2. **Check for a valid cached epic context.** Look for `{implementation_artifacts}/epic-<N>-context.md` (where `<N>` is the epic number). A file is **valid** when it exists, is non-empty, starts with `# Epic <N> Context:` (with the correct epic number), and no file in `{planning_artifacts}` is newer.
         - **If valid:** load it as the primary planning context. Do not load raw planning docs (PRD, architecture, UX, etc.). Skip to step 5.
@@ -59,6 +66,8 @@ Never ask extra questions if you already understand what the user intends.
 
      5. **Previous story continuity.** Regardless of which context source succeeded above, scan `{implementation_artifacts}` for specs from the same epic with `status: done` and a lower story number. Load the most recent one (highest story number below current). Extract its **Code Map**, **Design Notes**, **Spec Change Log**, and **task list** as continuity context for step-02 planning. If no `done` spec is found but an `in-review` spec exists for the same epic with a lower story number, note it to the user and ask whether to load it.
 
+     6. **Resolve `{story_key}`.** If not already set by an earlier early-exit path, run **Story-key resolution** (above) now.
+
      **B) Freeform path** — if the intent is not an epic story:
      - Planning artifacts are the output of BMAD phases 1-3. Typical files include:
        - **PRD** (`*prd*`) — product requirements and success criteria

package/src/bmm-skills/4-implementation/bmad-quick-dev/step-03-implement.md

@@ -24,6 +24,8 @@ Capture `baseline_commit` (current HEAD, or `NO_VCS` if version control is unava
 
 Change `{spec_file}` status to `in-progress` in the frontmatter before starting implementation.
 
+Follow `./sync-sprint-status.md` with `{target_status}` = `in-progress`.
+
 If `{spec_file}` has a non-empty `context:` list in its frontmatter, load those files before implementation begins. When handing to a sub-agent, include them in the sub-agent prompt so it has access to the referenced context.
 
 Hand `{spec_file}` to a sub-agent/task and let it implement. If no sub-agents are available, implement directly.

package/src/bmm-skills/4-implementation/bmad-quick-dev/step-05-present.md

@@ -48,16 +48,25 @@ Format each stop as framing first, link on the next indented line:
 
 When there is only one concern, omit the bold label — just list the stops directly.
 
-### Commit and Present
+### Mark Spec Done
 
-1. Change `{spec_file}` status to `done` in the frontmatter.
-2. If version control is available and the tree is dirty, create a local commit with a conventional message derived from the spec title.
-3. Open the spec in the user's editor so they can click through the Suggested Review Order:
+Change `{spec_file}` status to `done` in the frontmatter.
+
+Follow `./sync-sprint-status.md` with `{target_status}` = `review`.
+
+### Commit and Open
+
+1. If version control is available and the tree is dirty, create a local commit with a conventional message derived from the spec title.
+2. Open the spec in the user's editor so they can click through the Suggested Review Order:
    - Resolve two absolute paths: (1) the repository root (`git rev-parse --show-toplevel` — returns the worktree root when in a worktree, project root otherwise; if this fails, fall back to the current working directory), (2) `{spec_file}`. Run `code -r "{absolute-root}" "{absolute-spec-file}"` — the root first so VS Code opens in the right context, then the spec file. Always double-quote paths to handle spaces and special characters.
    - If `code` is not available (command fails), skip gracefully and tell the user the spec file path instead.
-4. Display summary of your work to the user, including the commit hash if one was created. Any file paths shown in conversation/terminal output must use CWD-relative format (no leading `/`) with `:line` notation (e.g., `src/path/file.ts:42`) for terminal clickability — the goal is to make paths clickable in terminal emulators. Include:
-   - A note that the spec is open in their editor (or the file path if it couldn't be opened). Mention that `{spec_file}` now contains a Suggested Review Order.
-   - **Navigation tip:** "Ctrl+click (Cmd+click on macOS) the links in the Suggested Review Order to jump to each stop."
-   - Offer to push and/or create a pull request.
+
+### Display Summary
+
+Display summary of your work to the user, including the commit hash if one was created. Any file paths shown in conversation/terminal output must use CWD-relative format (no leading `/`) with `:line` notation (e.g., `src/path/file.ts:42`) for terminal clickability — the goal is to make paths clickable in terminal emulators. Include:
+
+- A note that the spec is open in their editor (or the file path if it couldn't be opened). Mention that `{spec_file}` now contains a Suggested Review Order.
+- **Navigation tip:** "Ctrl+click (Cmd+click on macOS) the links in the Suggested Review Order to jump to each stop."
+- Offer to push and/or create a pull request.
 
 Workflow complete.

package/src/bmm-skills/4-implementation/bmad-quick-dev/step-oneshot.md

@@ -13,6 +13,8 @@ deferred_work_file: '{implementation_artifacts}/deferred-work.md'
 
 ### Implement
 
+Follow `./sync-sprint-status.md` with `{target_status}` = `in-progress`.
+
 Implement the clarified intent directly.
 
 ### Review
@@ -39,6 +41,8 @@ Write `{spec_file}` using `./spec-template.md`. Fill only these sections — del
 2. **Title and Intent** — `# {title}` heading and `## Intent` with **Problem** and **Approach** lines. Reuse the summary you already generated for the terminal.
 3. **Suggested Review Order** — append after Intent. Build using the same convention as `./step-05-present.md` § "Generate Suggested Review Order" (spec-file-relative links, concern-based ordering, ultra-concise framing).
 
+Follow `./sync-sprint-status.md` with `{target_status}` = `review`.
+
 ### Commit
 
 If version control is available and the tree is dirty, create a local commit with a conventional message derived from the intent. If VCS is unavailable, skip.

package/src/bmm-skills/4-implementation/bmad-quick-dev/sync-sprint-status.md

@@ -0,0 +1,19 @@
+# Sync Sprint Status
+
+Shared sub-step for updating `sprint-status.yaml` during quick-dev. Called from any route (plan-code-review, one-shot, future routes) with a `{target_status}` parameter.
+
+## Preconditions
+
+Skip this entire file (return to caller) if ANY of:
+- `{story_key}` is unset
+- `{sprint_status}` does not exist on disk
+
+## Instructions
+
+1. Load the FULL `{sprint_status}` file.
+2. Find the `development_status` entry matching `{story_key}`. If not found, warn the user once (`"{story_key} not found in sprint-status; skipping sprint sync"`) and return to caller.
+3. **Idempotency check.** If `development_status[{story_key}]` is already at `{target_status}` or a later state (`review` is later than `in-progress`; `done` is later than both), return to caller — no write needed. Never regress a story's status.
+4. Set `development_status[{story_key}]` to `{target_status}`.
+5. **Epic lift (only when `{target_status}` = `in-progress`).** Derive the parent epic key as `epic-{N}` from the leading numeric segment of `{story_key}` (e.g., `3-2-digest-delivery` → `epic-3`). If that entry exists and is `backlog`, set it to `in-progress`. Leave it alone otherwise. Skip this sub-step entirely when `{target_status}` is not `in-progress`.
+6. Refresh `last_updated` to the current date.
+7. Save the file, preserving ALL comments and structure including STATUS DEFINITIONS and WORKFLOW NOTES.

package/src/bmm-skills/4-implementation/bmad-quick-dev/workflow.md

@@ -65,6 +65,7 @@ Load and read full config from `{main_config}` and resolve:
 - `project_name`, `planning_artifacts`, `implementation_artifacts`, `user_name`
 - `communication_language`, `document_output_language`, `user_skill_level`
 - `date` as system-generated current datetime
+- `sprint_status` = `{implementation_artifacts}/sprint-status.yaml`
 - `project_context` = `**/project-context.md` (load if exists)
 - CLAUDE.md / memory files (load if exist)
 

package/tools/installer/ide/shared/agent-command-generator.js

@@ -1,180 +0,0 @@
-const path = require('node:path');
-const fs = require('fs-extra');
-const { toColonPath, toDashPath, customAgentColonName, customAgentDashName, BMAD_FOLDER_NAME } = require('./path-utils');
-
-/**
- * Generates launcher command files for each agent
- */
-class AgentCommandGenerator {
-  constructor(bmadFolderName = BMAD_FOLDER_NAME) {
-    this.templatePath = path.join(__dirname, '../templates/agent-command-template.md');
-    this.bmadFolderName = bmadFolderName;
-  }
-
-  /**
-   * Collect agent artifacts for IDE installation
-   * @param {string} bmadDir - BMAD installation directory
-   * @param {Array} selectedModules - Modules to include
-   * @returns {Object} Artifacts array with metadata
-   */
-  async collectAgentArtifacts(bmadDir, selectedModules = []) {
-    const { getAgentsFromBmad } = require('./bmad-artifacts');
-
-    // Get agents from INSTALLED bmad/ directory
-    const agents = await getAgentsFromBmad(bmadDir, selectedModules);
-
-    const artifacts = [];
-
-    for (const agent of agents) {
-      const launcherContent = await this.generateLauncherContent(agent);
-      // Use relativePath if available (for nested agents), otherwise just name with .md
-      const agentPathInModule = agent.relativePath || `${agent.name}.md`;
-      // Calculate the relative agent path (e.g., bmm/agents/pm.md)
-      let agentRelPath = agent.path || '';
-      // Normalize path separators for cross-platform compatibility
-      agentRelPath = agentRelPath.replaceAll('\\', '/');
-      // Remove _bmad/ prefix if present to get relative path from project root
-      // Handle both absolute paths (/path/to/_bmad/...) and relative paths (_bmad/...)
-      if (agentRelPath.includes('_bmad/')) {
-        const parts = agentRelPath.split(/_bmad\//);
-        if (parts.length > 1) {
-          agentRelPath = parts.slice(1).join('/');
-        }
-      }
-      artifacts.push({
-        type: 'agent-launcher',
-        name: agent.name,
-        description: agent.description || `${agent.name} agent`,
-        module: agent.module,
-        canonicalId: agent.canonicalId || '',
-        relativePath: path.join(agent.module, 'agents', agentPathInModule), // For command filename
-        agentPath: agentRelPath, // Relative path to actual agent file
-        content: launcherContent,
-        sourcePath: agent.path,
-      });
-    }
-
-    return {
-      artifacts,
-      counts: {
-        agents: agents.length,
-      },
-    };
-  }
-
-  /**
-   * Generate launcher content for an agent
-   * @param {Object} agent - Agent metadata
-   * @returns {string} Launcher file content
-   */
-  async generateLauncherContent(agent) {
-    // Load the template
-    const template = await fs.readFile(this.templatePath, 'utf8');
-
-    // Replace template variables
-    // Use relativePath if available (for nested agents), otherwise just name with .md
-    const agentPathInModule = agent.relativePath || `${agent.name}.md`;
-    return template
-      .replaceAll('{{name}}', agent.name)
-      .replaceAll('{{module}}', agent.module)
-      .replaceAll('{{path}}', agentPathInModule)
-      .replaceAll('{{description}}', agent.description || `${agent.name} agent`)
-      .replaceAll('_bmad', this.bmadFolderName)
-      .replaceAll('_bmad', '_bmad');
-  }
-
-  /**
-   * Write agent launcher artifacts to IDE commands directory
-   * @param {string} baseCommandsDir - Base commands directory for the IDE
-   * @param {Array} artifacts - Agent launcher artifacts
-   * @returns {number} Count of launchers written
-   */
-  async writeAgentLaunchers(baseCommandsDir, artifacts) {
-    let writtenCount = 0;
-
-    for (const artifact of artifacts) {
-      if (artifact.type === 'agent-launcher') {
-        const moduleAgentsDir = path.join(baseCommandsDir, artifact.module, 'agents');
-        await fs.ensureDir(moduleAgentsDir);
-
-        const launcherPath = path.join(moduleAgentsDir, `${artifact.name}.md`);
-        await fs.writeFile(launcherPath, artifact.content);
-        writtenCount++;
-      }
-    }
-
-    return writtenCount;
-  }
-
-  /**
-   * Write agent launcher artifacts using underscore format (Windows-compatible)
-   * Creates flat files like: bmad_bmm_pm.md
-   *
-   * @param {string} baseCommandsDir - Base commands directory for the IDE
-   * @param {Array} artifacts - Agent launcher artifacts
-   * @returns {number} Count of launchers written
-   */
-  async writeColonArtifacts(baseCommandsDir, artifacts) {
-    let writtenCount = 0;
-
-    for (const artifact of artifacts) {
-      if (artifact.type === 'agent-launcher') {
-        // Convert relativePath to underscore format: bmm/agents/pm.md → bmad_bmm_pm.md
-        const flatName = toColonPath(artifact.relativePath);
-        const launcherPath = path.join(baseCommandsDir, flatName);
-        await fs.ensureDir(path.dirname(launcherPath));
-        await fs.writeFile(launcherPath, artifact.content);
-        writtenCount++;
-      }
-    }
-
-    return writtenCount;
-  }
-
-  /**
-   * Write agent launcher artifacts using dash format (NEW STANDARD)
-   * Creates flat files like: bmad-agent-bmm-pm.md
-   *
-   * The bmad-agent- prefix distinguishes agents from workflows/tasks/tools.
-   *
-   * @param {string} baseCommandsDir - Base commands directory for the IDE
-   * @param {Array} artifacts - Agent launcher artifacts
-   * @returns {number} Count of launchers written
-   */
-  async writeDashArtifacts(baseCommandsDir, artifacts) {
-    let writtenCount = 0;
-
-    for (const artifact of artifacts) {
-      if (artifact.type === 'agent-launcher') {
-        // Convert relativePath to dash format: bmm/agents/pm.md → bmad-agent-bmm-pm.md
-        const flatName = toDashPath(artifact.relativePath);
-        const launcherPath = path.join(baseCommandsDir, flatName);
-        await fs.ensureDir(path.dirname(launcherPath));
-        await fs.writeFile(launcherPath, artifact.content);
-        writtenCount++;
-      }
-    }
-
-    return writtenCount;
-  }
-
-  /**
-   * Get the custom agent name in underscore format (Windows-compatible)
-   * @param {string} agentName - Custom agent name
-   * @returns {string} Underscore-formatted filename
-   */
-  getCustomAgentColonName(agentName) {
-    return customAgentColonName(agentName);
-  }
-
-  /**
-   * Get the custom agent name in underscore format (Windows-compatible)
-   * @param {string} agentName - Custom agent name
-   * @returns {string} Underscore-formatted filename
-   */
-  getCustomAgentDashName(agentName) {
-    return customAgentDashName(agentName);
-  }
-}
-
-module.exports = { AgentCommandGenerator };

package/tools/installer/ide/shared/bmad-artifacts.js

@@ -1,208 +0,0 @@
-const path = require('node:path');
-const fs = require('fs-extra');
-const { loadSkillManifest, getCanonicalId } = require('./skill-manifest');
-
-/**
- * Helpers for gathering BMAD agents/tasks from the installed tree.
- * Shared by installers that need Claude-style exports.
- *
- * TODO: Dead code cleanup — compiled XML agents are retired.
- *
- * All agents now use the SKILL.md directory format with bmad-skill-manifest.yaml
- * (type: agent). The legacy pipeline below only discovers compiled .md files
- * containing <agent> XML tags, which no longer exist. The following are dead:
- *
- *   - getAgentsFromBmad()      — scans {module}/agents/ for .md files with <agent> tags
- *   - getAgentsFromDir()       — recursive helper for the above
- *   - AgentCommandGenerator    — (agent-command-generator.js) generates launcher .md files
- *                                 that tell the LLM to load a compiled agent .md file
- *   - agent-command-template.md — (templates/) the launcher template with hardcoded
- *                                 {module}/agents/{{path}} reference
- *
- * Agent metadata for agent-manifest.csv is now handled entirely by
- * ManifestGenerator.getAgentsFromDirRecursive() in manifest-generator.js,
- * which walks the full module tree and finds type:agent directories.
- *
- * IDE installation of agents is handled by the native skill pipeline —
- * each agent's SKILL.md directory is installed directly to the IDE's
- * skills path, so no launcher intermediary is needed.
- *
- * Cleanup: remove getAgentsFromBmad, getAgentsFromDir, their exports,
- * AgentCommandGenerator, agent-command-template.md, and all call sites
- * in IDE installers that invoke collectAgentArtifacts / writeAgentLaunchers /
- * writeColonArtifacts / writeDashArtifacts.
- * getTasksFromBmad and getTasksFromDir may still be live — verify before removing.
- */
-async function getAgentsFromBmad(bmadDir, selectedModules = []) {
-  const agents = [];
-
-  // Get core agents
-  if (await fs.pathExists(path.join(bmadDir, 'core', 'agents'))) {
-    const coreAgents = await getAgentsFromDir(path.join(bmadDir, 'core', 'agents'), 'core');
-    agents.push(...coreAgents);
-  }
-
-  // Get module agents
-  for (const moduleName of selectedModules) {
-    const agentsPath = path.join(bmadDir, moduleName, 'agents');
-
-    if (await fs.pathExists(agentsPath)) {
-      const moduleAgents = await getAgentsFromDir(agentsPath, moduleName);
-      agents.push(...moduleAgents);
-    }
-  }
-
-  // Get standalone agents from bmad/agents/ directory
-  const standaloneAgentsDir = path.join(bmadDir, 'agents');
-  if (await fs.pathExists(standaloneAgentsDir)) {
-    const agentDirs = await fs.readdir(standaloneAgentsDir, { withFileTypes: true });
-
-    for (const agentDir of agentDirs) {
-      if (!agentDir.isDirectory()) continue;
-
-      const agentDirPath = path.join(standaloneAgentsDir, agentDir.name);
-      const agentFiles = await fs.readdir(agentDirPath);
-      const skillManifest = await loadSkillManifest(agentDirPath);
-
-      for (const file of agentFiles) {
-        if (!file.endsWith('.md')) continue;
-        if (file.includes('.customize.')) continue;
-
-        const filePath = path.join(agentDirPath, file);
-        const content = await fs.readFile(filePath, 'utf8');
-
-        if (content.includes('localskip="true"')) continue;
-
-        agents.push({
-          path: filePath,
-          name: file.replace('.md', ''),
-          module: 'standalone', // Mark as standalone agent
-          canonicalId: getCanonicalId(skillManifest, file),
-        });
-      }
-    }
-  }
-
-  return agents;
-}
-
-async function getTasksFromBmad(bmadDir, selectedModules = []) {
-  const tasks = [];
-
-  if (await fs.pathExists(path.join(bmadDir, 'core', 'tasks'))) {
-    const coreTasks = await getTasksFromDir(path.join(bmadDir, 'core', 'tasks'), 'core');
-    tasks.push(...coreTasks);
-  }
-
-  for (const moduleName of selectedModules) {
-    const tasksPath = path.join(bmadDir, moduleName, 'tasks');
-
-    if (await fs.pathExists(tasksPath)) {
-      const moduleTasks = await getTasksFromDir(tasksPath, moduleName);
-      tasks.push(...moduleTasks);
-    }
-  }
-
-  return tasks;
-}
-
-async function getAgentsFromDir(dirPath, moduleName, relativePath = '') {
-  const agents = [];
-
-  if (!(await fs.pathExists(dirPath))) {
-    return agents;
-  }
-
-  const entries = await fs.readdir(dirPath, { withFileTypes: true });
-  const skillManifest = await loadSkillManifest(dirPath);
-
-  for (const entry of entries) {
-    // Skip if entry.name is undefined or not a string
-    if (!entry.name || typeof entry.name !== 'string') {
-      continue;
-    }
-
-    const fullPath = path.join(dirPath, entry.name);
-    const newRelativePath = relativePath ? `${relativePath}/${entry.name}` : entry.name;
-
-    if (entry.isDirectory()) {
-      // Recurse into subdirectories
-      const subDirAgents = await getAgentsFromDir(fullPath, moduleName, newRelativePath);
-      agents.push(...subDirAgents);
-    } else if (entry.name.endsWith('.md')) {
-      // Skip README files and other non-agent files
-      if (entry.name.toLowerCase() === 'readme.md' || entry.name.toLowerCase().startsWith('readme-')) {
-        continue;
-      }
-
-      if (entry.name.includes('.customize.')) {
-        continue;
-      }
-
-      const content = await fs.readFile(fullPath, 'utf8');
-
-      if (content.includes('localskip="true"')) {
-        continue;
-      }
-
-      // Only include files that have agent-specific content (compiled agents have <agent> tag)
-      if (!content.includes('<agent')) {
-        continue;
-      }
-
-      agents.push({
-        path: fullPath,
-        name: entry.name.replace('.md', ''),
-        module: moduleName,
-        relativePath: newRelativePath, // Keep the .md extension for the full path
-        canonicalId: getCanonicalId(skillManifest, entry.name),
-      });
-    }
-  }
-
-  return agents;
-}
-
-async function getTasksFromDir(dirPath, moduleName) {
-  const tasks = [];
-
-  if (!(await fs.pathExists(dirPath))) {
-    return tasks;
-  }
-
-  const files = await fs.readdir(dirPath);
-  const skillManifest = await loadSkillManifest(dirPath);
-
-  for (const file of files) {
-    // Include both .md and .xml task files
-    if (!file.endsWith('.md') && !file.endsWith('.xml')) {
-      continue;
-    }
-
-    const filePath = path.join(dirPath, file);
-    const content = await fs.readFile(filePath, 'utf8');
-
-    // Skip internal/engine files (not user-facing tasks)
-    if (content.includes('internal="true"')) {
-      continue;
-    }
-
-    // Remove extension to get task name
-    const ext = file.endsWith('.xml') ? '.xml' : '.md';
-    tasks.push({
-      path: filePath,
-      name: file.replace(ext, ''),
-      module: moduleName,
-      canonicalId: getCanonicalId(skillManifest, file),
-    });
-  }
-
-  return tasks;
-}
-
-module.exports = {
-  getAgentsFromBmad,
-  getTasksFromBmad,
-  getAgentsFromDir,
-  getTasksFromDir,
-};

package/tools/installer/ide/templates/agent-command-template.md

@@ -1,14 +0,0 @@
----
-name: '{{name}}'
-description: '{{description}}'
----
-
-You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
-
-<agent-activation CRITICAL="TRUE">
-1. LOAD the FULL agent file from {project-root}/_bmad/{{module}}/agents/{{path}}
-2. READ its entire contents - this contains the complete agent persona, menu, and instructions
-3. Execute ALL activation steps exactly as written in the agent file
-4. Follow the agent's persona and menu system precisely
-5. Stay in character throughout the session
-</agent-activation>

package/tools/installer/ide/templates/combined/antigravity.md

@@ -1,8 +0,0 @@
----
-name: '{{name}}'
-description: '{{description}}'
----
-
-Read the entire workflow file at: {project-root}/_bmad/{{workflow_path}}
-
-Follow all instructions in the workflow file exactly as written.

package/tools/installer/ide/templates/combined/default-agent.md

@@ -1,15 +0,0 @@
----
-name: '{{name}}'
-description: '{{description}}'
----
-
-You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
-
-<agent-activation CRITICAL="TRUE">
-1. LOAD the FULL agent file from {project-root}/_bmad/{{path}}
-2. READ its entire contents - this contains the complete agent persona, menu, and instructions
-3. FOLLOW every step in the <activation> section precisely
-4. DISPLAY the welcome/greeting as instructed
-5. PRESENT the numbered menu
-6. WAIT for user input before proceeding
-</agent-activation>

package/tools/installer/ide/templates/combined/default-task.md

@@ -1,10 +0,0 @@
----
-name: '{{name}}'
-description: '{{description}}'
----
-
-# {{name}}
-
-Read the entire task file at: {project-root}/{{bmadFolderName}}/{{path}}
-
-Follow all instructions in the task file exactly as written.

package/tools/installer/ide/templates/combined/default-tool.md

@@ -1,10 +0,0 @@
----
-name: '{{name}}'
-description: '{{description}}'
----
-
-# {{name}}
-
-Read the entire tool file at: {project-root}/{{bmadFolderName}}/{{path}}
-
-Follow all instructions in the tool file exactly as written.

package/tools/installer/ide/templates/combined/default-workflow.md

@@ -1,6 +0,0 @@
----
-name: '{{name}}'
-description: '{{description}}'
----
-
-IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL {project-root}/{{bmadFolderName}}/{{path}}, READ its entire contents and follow its directions exactly!

package/tools/installer/ide/templates/combined/gemini-agent.toml

@@ -1,14 +0,0 @@
-description = "Activates the {{name}} agent from the BMad Method."
-prompt = """
-CRITICAL: You are now the BMad '{{name}}' agent.
-
-PRE-FLIGHT CHECKLIST:
-1.  [ ] IMMEDIATE ACTION: Load and parse {project-root}/{{bmadFolderName}}/{{module}}/config.yaml - store ALL config values in memory for use throughout the session.
-2.  [ ] IMMEDIATE ACTION: Read and internalize the full agent definition at {project-root}/{{bmadFolderName}}/{{path}}.
-3.  [ ] CONFIRM: The user's name from config is {user_name}.
-
-Only after all checks are complete, greet the user by name and display the menu.
-Acknowledge this checklist is complete in your first response.
-
-AGENT DEFINITION: {project-root}/{{bmadFolderName}}/{{path}}
-"""

package/tools/installer/ide/templates/combined/gemini-task.toml

@@ -1,11 +0,0 @@
-description = "Executes the {{name}} task from the BMAD Method."
-prompt = """
-Execute the BMAD '{{name}}' task.
-
-TASK INSTRUCTIONS:
-1. LOAD the task file from {project-root}/{{bmadFolderName}}/{{path}}
-2. READ its entire contents
-3. FOLLOW every instruction precisely as specified
-
-TASK FILE: {project-root}/{{bmadFolderName}}/{{path}}
-"""

package/tools/installer/ide/templates/combined/gemini-tool.toml

@@ -1,11 +0,0 @@
-description = "Executes the {{name}} tool from the BMAD Method."
-prompt = """
-Execute the BMAD '{{name}}' tool.
-
-TOOL INSTRUCTIONS:
-1. LOAD the tool file from {project-root}/{{bmadFolderName}}/{{path}}
-2. READ its entire contents
-3. FOLLOW every instruction precisely as specified
-
-TOOL FILE: {project-root}/{{bmadFolderName}}/{{path}}
-"""

package/tools/installer/ide/templates/combined/gemini-workflow-yaml.toml

@@ -1,16 +0,0 @@
-description = '{{description}}'
-prompt = """
-Execute the BMAD '{{name}}' workflow.
-
-CRITICAL: This is a structured YAML workflow. Follow these steps precisely:
-
-1. LOAD the workflow definition from {project-root}/{{bmadFolderName}}/{{workflow_path}}
-2. PARSE the YAML structure to understand:
-   - Workflow phases and steps
-   - Required inputs and outputs
-   - Dependencies between steps
-3. EXECUTE each step in order
-4. VALIDATE outputs before proceeding to next step
-
-WORKFLOW FILE: {project-root}/{{bmadFolderName}}/{{workflow_path}}
-"""

package/tools/installer/ide/templates/combined/gemini-workflow.toml

@@ -1,14 +0,0 @@
-description = '{{description}}'
-prompt = """
-Execute the BMAD '{{name}}' workflow.
-
-CRITICAL: You must load and follow the workflow definition exactly.
-
-WORKFLOW INSTRUCTIONS:
-1. LOAD the workflow file from {project-root}/{{bmadFolderName}}/{{workflow_path}}
-2. READ its entire contents
-3. FOLLOW every step precisely as specified
-4. DO NOT skip or modify any steps
-
-WORKFLOW FILE: {project-root}/{{bmadFolderName}}/{{workflow_path}}
-"""

package/tools/installer/ide/templates/combined/kiro-agent.md

@@ -1,16 +0,0 @@
----
-inclusion: manual
----
-
-# {{name}}
-
-You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
-
-<agent-activation CRITICAL="TRUE">
-1. LOAD the FULL agent file from #[[file:{{bmadFolderName}}/{{path}}]]
-2. READ its entire contents - this contains the complete agent persona, menu, and instructions
-3. FOLLOW every step in the <activation> section precisely
-4. DISPLAY the welcome/greeting as instructed
-5. PRESENT the numbered menu
-6. WAIT for user input before proceeding
-</agent-activation>

package/tools/installer/ide/templates/combined/kiro-task.md

@@ -1,9 +0,0 @@
----
-inclusion: manual
----
-
-# {{name}}
-
-Read the entire task file at: #[[file:{{bmadFolderName}}/{{path}}]]
-
-Follow all instructions in the task file exactly as written.

package/tools/installer/ide/templates/combined/kiro-tool.md

@@ -1,9 +0,0 @@
----
-inclusion: manual
----
-
-# {{name}}
-
-Read the entire tool file at: #[[file:{{bmadFolderName}}/{{path}}]]
-
-Follow all instructions in the tool file exactly as written.

package/tools/installer/ide/templates/combined/kiro-workflow.md

@@ -1,7 +0,0 @@
----
-inclusion: manual
----
-
-# {{name}}
-
-IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL #[[file:{{bmadFolderName}}/{{path}}]], READ its entire contents and follow its directions exactly!

package/tools/installer/ide/templates/combined/opencode-agent.md

@@ -1,15 +0,0 @@
----
-mode: all
-description: '{{description}}'
----
-
-You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
-
-<agent-activation CRITICAL="TRUE">
-1. LOAD the FULL agent file from {project-root}/{{bmadFolderName}}/{{path}}
-2. READ its entire contents - this contains the complete agent persona, menu, and instructions
-3. FOLLOW every step in the <activation> section precisely
-4. DISPLAY the welcome/greeting as instructed
-5. PRESENT the numbered menu
-6. WAIT for user input before proceeding
-</agent-activation>

package/tools/installer/ide/templates/combined/opencode-task.md

@@ -1,13 +0,0 @@
----
-description: '{{description}}'
----
-
-Execute the BMAD '{{name}}' task.
-
-TASK INSTRUCTIONS:
-
-1. LOAD the task file from {project-root}/{{bmadFolderName}}/{{path}}
-2. READ its entire contents
-3. FOLLOW every instruction precisely as specified
-
-TASK FILE: {project-root}/{{bmadFolderName}}/{{path}}

package/tools/installer/ide/templates/combined/opencode-tool.md

@@ -1,13 +0,0 @@
----
-description: '{{description}}'
----
-
-Execute the BMAD '{{name}}' tool.
-
-TOOL INSTRUCTIONS:
-
-1. LOAD the tool file from {project-root}/{{bmadFolderName}}/{{path}}
-2. READ its entire contents
-3. FOLLOW every instruction precisely as specified
-
-TOOL FILE: {project-root}/{{bmadFolderName}}/{{path}}

package/tools/installer/ide/templates/combined/opencode-workflow-yaml.md

@@ -1,16 +0,0 @@
----
-description: '{{description}}'
----
-
-Execute the BMAD '{{name}}' workflow.
-
-CRITICAL: You must load and follow the workflow definition exactly.
-
-WORKFLOW INSTRUCTIONS:
-
-1. LOAD the workflow file from {project-root}/{{bmadFolderName}}/{{path}}
-2. READ its entire contents
-3. FOLLOW every step precisely as specified
-4. DO NOT skip or modify any steps
-
-WORKFLOW FILE: {project-root}/{{bmadFolderName}}/{{path}}

package/tools/installer/ide/templates/combined/opencode-workflow.md

@@ -1,16 +0,0 @@
----
-description: '{{description}}'
----
-
-Execute the BMAD '{{name}}' workflow.
-
-CRITICAL: You must load and follow the workflow definition exactly.
-
-WORKFLOW INSTRUCTIONS:
-
-1. LOAD the workflow file from {project-root}/{{bmadFolderName}}/{{path}}
-2. READ its entire contents
-3. FOLLOW every step precisely as specified
-4. DO NOT skip or modify any steps
-
-WORKFLOW FILE: {project-root}/{{bmadFolderName}}/{{path}}

package/tools/installer/ide/templates/combined/rovodev.md

@@ -1,9 +0,0 @@
-# {{name}}
-
-{{description}}
-
----
-
-Read the entire workflow file at: {project-root}/_bmad/{{workflow_path}}
-
-Follow all instructions in the workflow file exactly as written.

package/tools/installer/ide/templates/combined/trae.md

@@ -1,9 +0,0 @@
-# {{name}}
-
-{{description}}
-
-## Instructions
-
-Read the entire workflow file at: {project-root}/_bmad/{{workflow_path}}
-
-Follow all instructions in the workflow file exactly as written.

package/tools/installer/ide/templates/combined/windsurf-workflow.md

@@ -1,10 +0,0 @@
----
-description: '{{description}}'
-auto_execution_mode: "iterate"
----
-
-# {{name}}
-
-Read the entire workflow file at {project-root}/_bmad/{{workflow_path}}
-
-Follow all instructions in the workflow file exactly as written.