Skip to content

An AI-powered task-management system you can drop into Cursor, Lovable, Windsurf, Roo, and others.

Adjusts the readmes and cursor rule.

Eyal Toledanoe11aba2fec0f
diff --git a/.cursor/rules/dev_workflow.mdc b/.cursor/rules/dev_workflow.mdc
index 229a7c9d..e5175c32 100644
--- a/.cursor/rules/dev_workflow.mdc
+++ b/.cursor/rules/dev_workflow.mdc
@@ -11,6 +11,7 @@ alwaysApply: true
- Select tasks based on dependencies (all marked 'done'), priority level, and ID order
- Clarify tasks by checking task files in tasks/ directory or asking for user input
- Break down complex tasks using `node scripts/dev.js expand --id=<id>` with appropriate flags
+ - Clear existing subtasks if needed using `node scripts/dev.js clear-subtasks --id=<id>` before regenerating
- Implement code following task details, dependencies, and project standards
- Verify tasks according to test strategies before marking as complete
- Mark completed tasks with `node scripts/dev.js set-status --id=<id> --status=done`
@@ -33,6 +34,7 @@ alwaysApply: true
- Use `--prompt="<context>"` to provide additional context when needed
- Review and adjust generated subtasks as necessary
- Use `--all` flag to expand multiple pending tasks at once
+ - If subtasks need regeneration, clear them first with `clear-subtasks` command
- **Implementation Drift Handling**
- When implementation differs significantly from planned approach
@@ -126,6 +128,21 @@ alwaysApply: true
- Example: `node scripts/dev.js analyze-complexity --research`
- Notes: Report includes complexity scores, recommended subtasks, and tailored prompts.
+- **Command Reference: clear-subtasks**
+ - Syntax: `node scripts/dev.js clear-subtasks --id=<id>`
+ - Description: Removes subtasks from specified tasks to allow regeneration
+ - Parameters:
+ - `--id=<id>`: ID or comma-separated IDs of tasks to clear subtasks from
+ - `--all`: Clear subtasks from all tasks
+ - Examples:
+ - `node scripts/dev.js clear-subtasks --id=3`
+ - `node scripts/dev.js clear-subtasks --id=1,2,3`
+ - `node scripts/dev.js clear-subtasks --all`
+ - Notes:
+ - Task files are automatically regenerated after clearing subtasks
+ - Can be combined with expand command to immediately generate new subtasks
+ - Works with both parent tasks and individual subtasks
+
- **Task Structure Fields**
- **id**: Unique identifier for the task (Example: `1`)
- **title**: Brief, descriptive title (Example: `"Initialize Repo"`)
diff --git a/README-task-master.md b/README-task-master.md
index 3ca327bf..2df22a78 100644
--- a/README-task-master.md
+++ b/README-task-master.md
@@ -300,6 +300,18 @@ or
npm run dev -- expand --all --research
```
+### Clear Subtasks
+```bash
+# Clear subtasks from a specific task
+npm run dev -- clear-subtasks --id=<id>
+
+# Clear subtasks from multiple tasks
+npm run dev -- clear-subtasks --id=1,2,3
+
+# Clear subtasks from all tasks
+npm run dev -- clear-subtasks --all
+```
+
## Task Structure
Tasks in tasks.json have the following structure:
@@ -348,6 +360,11 @@ What's the next task I should work on? Please consider dependencies and prioriti
I'd like to implement task 4. Can you help me understand what needs to be done and how to approach it?
```
+### Managing subtasks
+```
+I need to regenerate the subtasks for task 3 with a different approach. Can you help me clear and regenerate them?
+```
+
### Handling changes
```
We've decided to use MongoDB instead of PostgreSQL. Can you update all future tasks to reflect this change?
diff --git a/scripts/README.md b/scripts/README.md
index ebd8041e..08efa586 100644
--- a/scripts/README.md
+++ b/scripts/README.md
@@ -13,6 +13,7 @@ In an AI-driven development process—particularly with tools like [Cursor](http
5. **Set task status**—mark tasks as `done`, `pending`, or `deferred` based on progress.
6. **Expand** tasks with subtasks—break down complex tasks into smaller, more manageable subtasks.
7. **Research-backed subtask generation**—use Perplexity AI to generate more informed and contextually relevant subtasks.
+8. **Clear subtasks**—remove subtasks from specified tasks to allow regeneration or restructuring.
## Configuration
@@ -56,6 +57,7 @@ The script can be configured through environment variables in a `.env` file at t
- `generate`: Create individual task files
- `set-status`: Change a task's status
- `expand`: Add subtasks to a task or all tasks
+ - `clear-subtasks`: Remove subtasks from specified tasks
Run `node scripts/dev.js` without arguments to see detailed usage information.
@@ -148,12 +150,26 @@ node scripts/dev.js expand --id=3 --research
node scripts/dev.js expand --all --research
```
+## Clearing Subtasks
+
+The `clear-subtasks` command allows you to remove subtasks from specified tasks:
+
+```bash
+# Clear subtasks from a specific task
+node scripts/dev.js clear-subtasks --id=3
+
+# Clear subtasks from multiple tasks
+node scripts/dev.js clear-subtasks --id=1,2,3
+
+# Clear subtasks from all tasks
+node scripts/dev.js clear-subtasks --all
+```
+
Notes:
-- Tasks marked as 'done' or 'completed' are always skipped
-- By default, tasks that already have subtasks are skipped unless `--force` is used
-- Subtasks include title, description, dependencies, and acceptance criteria
-- The `--research` flag uses Perplexity AI to generate more informed and contextually relevant subtasks
-- If Perplexity API is unavailable, the script will fall back to using Anthropic's Claude
+- After clearing subtasks, task files are automatically regenerated
+- This is useful when you want to regenerate subtasks with a different approach
+- Can be combined with the `expand` command to immediately generate new subtasks
+- Works with both parent tasks and individual subtasks
## AI Integration
diff --git a/templates/README-task-master.md b/templates/README-task-master.md
index 3ca327bf..2df22a78 100644
--- a/templates/README-task-master.md
+++ b/templates/README-task-master.md
@@ -300,6 +300,18 @@ or
npm run dev -- expand --all --research
```
+### Clear Subtasks
+```bash
+# Clear subtasks from a specific task
+npm run dev -- clear-subtasks --id=<id>
+
+# Clear subtasks from multiple tasks
+npm run dev -- clear-subtasks --id=1,2,3
+
+# Clear subtasks from all tasks
+npm run dev -- clear-subtasks --all
+```
+
## Task Structure
Tasks in tasks.json have the following structure:
@@ -348,6 +360,11 @@ What's the next task I should work on? Please consider dependencies and prioriti
I'd like to implement task 4. Can you help me understand what needs to be done and how to approach it?
```
+### Managing subtasks
+```
+I need to regenerate the subtasks for task 3 with a different approach. Can you help me clear and regenerate them?
+```
+
### Handling changes
```
We've decided to use MongoDB instead of PostgreSQL. Can you update all future tasks to reflect this change?
diff --git a/templates/dev.js b/templates/dev.js
index 8a64d91b..a3f4d7c9 100755
--- a/templates/dev.js
+++ b/templates/dev.js
@@ -19,7 +19,7 @@
* 4) set-status --id=4 --status=done
* -> Updates a single task's status to done (or pending, deferred, in-progress, etc.).
* -> Supports comma-separated IDs for updating multiple tasks: --id=1,2,3,1.1,1.2
- *
+ * -> If you set the status of a parent task to done, all its subtasks will be set to done.
* 5) list
* -> Lists tasks in a brief console view (ID, title, status).
*
@@ -52,6 +52,11 @@
* --file, -f <path>: Use alternative tasks.json file instead of default
* --research, -r: Use Perplexity AI for research-backed complexity analysis
*
+ * 8) clear-subtasks
+ * -> Clears subtasks from specified tasks
+ * -> Supports comma-separated IDs for clearing multiple tasks: --id=1,2,3,1.1,1.2
+ * -> Use --all to clear subtasks from all tasks
+ *
* Usage examples:
* node dev.js parse-prd --input=sample-prd.txt
* node dev.js parse-prd --input=sample-prd.txt --tasks=10
@@ -67,6 +72,7 @@
* node dev.js analyze-complexity --output=custom-report.json
* node dev.js analyze-complexity --threshold=6 --model=claude-3.7-sonnet
* node dev.js analyze-complexity --research
+ * node dev.js clear-subtasks --id=1,2,3 --all
*/
import fs from 'fs';
@@ -527,6 +533,11 @@ async function updateTasks(tasksPath, fromId, prompt) {
writeJSON(tasksPath, data);
log('info', "Tasks updated successfully.");
+
+ // Add call to generate task files
+ log('info', "Regenerating task files...");
+ await generateTaskFiles(tasksPath, path.dirname(tasksPath));
+
} catch (parseError) {
log('error', "Failed to parse Claude's response as JSON:", parseError);
log('debug', "Response content:", fullResponse);
@@ -665,6 +676,10 @@ function setTaskStatus(tasksPath, taskIdInput, newStatus) {
writeJSON(tasksPath, data);
log('info', `Updated subtask ${parentId}.${subtaskId} status from '${oldStatus}' to '${newStatus}'`);
+ // Add call to generate task files
+ log('info', "Regenerating task files...");
+ generateTaskFiles(tasksPath, path.dirname(tasksPath));
+
return;
}
@@ -700,6 +715,10 @@ function setTaskStatus(tasksPath, taskIdInput, newStatus) {
// Save the changes
writeJSON(tasksPath, data);
log('info', `Updated task ${taskId} status from '${oldStatus}' to '${newStatus}'`);
+
+ // Add call to generate task files
+ log('info', "Regenerating task files...");
+ generateTaskFiles(tasksPath, path.dirname(tasksPath));
}
//
@@ -1711,6 +1730,36 @@ async function main() {
await analyzeTaskComplexity(options);
});
+ program
+ .command('clear-subtasks')
+ .description('Clear subtasks from specified tasks')
+ .option('-f, --file <file>', 'Path to the tasks file', 'tasks/tasks.json')
+ .option('-i, --id <ids>', 'Task IDs (comma-separated) to clear subtasks from')
+ .option('--all', 'Clear subtasks from all tasks')
+ .action(async (options) => {
+ const tasksPath = options.file;
+ const taskIds = options.id;
+ const all = options.all;
+
+ if (!taskIds && !all) {
+ console.error(chalk.red('Error: Please specify task IDs with --id=<ids> or use --all to clear all tasks'));
+ process.exit(1);
+ }
+
+ if (all) {
+ // If --all is specified, get all task IDs
+ const data = readJSON(tasksPath);
+ if (!data || !data.tasks) {
+ console.error(chalk.red('Error: No valid tasks found'));
+ process.exit(1);
+ }
+ const allIds = data.tasks.map(t => t.id).join(',');
+ clearSubtasks(tasksPath, allIds);
+ } else {
+ clearSubtasks(tasksPath, taskIds);
+ }
+ });
+
await program.parseAsync(process.argv);
}
@@ -2321,6 +2370,57 @@ function findTaskInComplexityReport(report, taskId) {
return report.complexityAnalysis.find(task => task.taskId === taskId);
}
+//
+// Clear subtasks from tasks
+//
+function clearSubtasks(tasksPath, taskIds) {
+ log('info', `Reading tasks from ${tasksPath}...`);
+ const data = readJSON(tasksPath);
+ if (!data || !data.tasks) {
+ log('error', "No valid tasks found.");
+ process.exit(1);
+ }
+
+ // Handle multiple task IDs (comma-separated)
+ const taskIdArray = taskIds.split(',').map(id => id.trim());
+ let clearedCount = 0;
+
+ taskIdArray.forEach(taskId => {
+ const id = parseInt(taskId, 10);
+ if (isNaN(id)) {
+ log('error', `Invalid task ID: ${taskId}`);
+ return;
+ }
+
+ const task = data.tasks.find(t => t.id === id);
+ if (!task) {
+ log('error', `Task ${id} not found`);
+ return;
+ }
+
+ if (!task.subtasks || task.subtasks.length === 0) {
+ log('info', `Task ${id} has no subtasks to clear`);
+ return;
+ }
+
+ const subtaskCount = task.subtasks.length;
+ task.subtasks = [];
+ clearedCount++;
+ log('info', `Cleared ${subtaskCount} subtasks from task ${id}`);
+ });
+
+ if (clearedCount > 0) {
+ writeJSON(tasksPath, data);
+ log('info', `Successfully cleared subtasks from ${clearedCount} task(s)`);
+
+ // Regenerate task files to reflect changes
+ log('info', "Regenerating task files...");
+ generateTaskFiles(tasksPath, path.dirname(tasksPath));
+ } else {
+ log('info', "No subtasks were cleared");
+ }
+}
+
main().catch(err => {
log('error', err);
process.exit(1);
diff --git a/templates/dev_workflow.mdc b/templates/dev_workflow.mdc
index 229a7c9d..e5175c32 100644
--- a/templates/dev_workflow.mdc
+++ b/templates/dev_workflow.mdc
@@ -11,6 +11,7 @@ alwaysApply: true
- Select tasks based on dependencies (all marked 'done'), priority level, and ID order
- Clarify tasks by checking task files in tasks/ directory or asking for user input
- Break down complex tasks using `node scripts/dev.js expand --id=<id>` with appropriate flags
+ - Clear existing subtasks if needed using `node scripts/dev.js clear-subtasks --id=<id>` before regenerating
- Implement code following task details, dependencies, and project standards
- Verify tasks according to test strategies before marking as complete
- Mark completed tasks with `node scripts/dev.js set-status --id=<id> --status=done`
@@ -33,6 +34,7 @@ alwaysApply: true
- Use `--prompt="<context>"` to provide additional context when needed
- Review and adjust generated subtasks as necessary
- Use `--all` flag to expand multiple pending tasks at once
+ - If subtasks need regeneration, clear them first with `clear-subtasks` command
- **Implementation Drift Handling**
- When implementation differs significantly from planned approach
@@ -126,6 +128,21 @@ alwaysApply: true
- Example: `node scripts/dev.js analyze-complexity --research`
- Notes: Report includes complexity scores, recommended subtasks, and tailored prompts.
+- **Command Reference: clear-subtasks**
+ - Syntax: `node scripts/dev.js clear-subtasks --id=<id>`
+ - Description: Removes subtasks from specified tasks to allow regeneration
+ - Parameters:
+ - `--id=<id>`: ID or comma-separated IDs of tasks to clear subtasks from
+ - `--all`: Clear subtasks from all tasks
+ - Examples:
+ - `node scripts/dev.js clear-subtasks --id=3`
+ - `node scripts/dev.js clear-subtasks --id=1,2,3`
+ - `node scripts/dev.js clear-subtasks --all`
+ - Notes:
+ - Task files are automatically regenerated after clearing subtasks
+ - Can be combined with expand command to immediately generate new subtasks
+ - Works with both parent tasks and individual subtasks
+
- **Task Structure Fields**
- **id**: Unique identifier for the task (Example: `1`)
- **title**: Brief, descriptive title (Example: `"Initialize Repo"`)
diff --git a/templates/scripts_README.md b/templates/scripts_README.md
index ebd8041e..08efa586 100644
--- a/templates/scripts_README.md
+++ b/templates/scripts_README.md
@@ -13,6 +13,7 @@ In an AI-driven development process—particularly with tools like [Cursor](http
5. **Set task status**—mark tasks as `done`, `pending`, or `deferred` based on progress.
6. **Expand** tasks with subtasks—break down complex tasks into smaller, more manageable subtasks.
7. **Research-backed subtask generation**—use Perplexity AI to generate more informed and contextually relevant subtasks.
+8. **Clear subtasks**—remove subtasks from specified tasks to allow regeneration or restructuring.
## Configuration
@@ -56,6 +57,7 @@ The script can be configured through environment variables in a `.env` file at t
- `generate`: Create individual task files
- `set-status`: Change a task's status
- `expand`: Add subtasks to a task or all tasks
+ - `clear-subtasks`: Remove subtasks from specified tasks
Run `node scripts/dev.js` without arguments to see detailed usage information.
@@ -148,12 +150,26 @@ node scripts/dev.js expand --id=3 --research
node scripts/dev.js expand --all --research
```
+## Clearing Subtasks
+
+The `clear-subtasks` command allows you to remove subtasks from specified tasks:
+
+```bash
+# Clear subtasks from a specific task
+node scripts/dev.js clear-subtasks --id=3
+
+# Clear subtasks from multiple tasks
+node scripts/dev.js clear-subtasks --id=1,2,3
+
+# Clear subtasks from all tasks
+node scripts/dev.js clear-subtasks --all
+```
+
Notes:
-- Tasks marked as 'done' or 'completed' are always skipped
-- By default, tasks that already have subtasks are skipped unless `--force` is used
-- Subtasks include title, description, dependencies, and acceptance criteria
-- The `--research` flag uses Perplexity AI to generate more informed and contextually relevant subtasks
-- If Perplexity API is unavailable, the script will fall back to using Anthropic's Claude
+- After clearing subtasks, task files are automatically regenerated
+- This is useful when you want to regenerate subtasks with a different approach
+- Can be combined with the `expand` command to immediately generate new subtasks
+- Works with both parent tasks and individual subtasks
## AI Integration