Initial commit

commands/add-one-task.md

@@ -0,0 +1,27 @@
+---
+argument-hint: task description
+description: Add a task to the project task list
+---
+
+Add a task to the project task list.
+
+If the user provided a description, it will appear here:
+
+<description>
+$ARGUMENTS
+</description>
+
+## Steps
+
+1. Extract the description from the user's input
+2. If no description was provided, ask the user for one
+3. Add the task:
+
+@../shared/scripts/task-add.md
+
+4. Confirm to the user that the task was added
+
+## Notes
+
+- The description should be clear and actionable
+- Do not include the checkbox syntax in the description (the script adds it)

commands/do-all-tasks.md

@@ -0,0 +1,48 @@
+---
+argument-hint: optional instructions
+description: Process all tasks automatically
+---
+
+Process all tasks automatically.
+
+Repeatedly work through incomplete tasks from the project task list.
+
+If the user provided additional instructions, they will appear here:
+
+<instructions>
+$ARGUMENTS
+</instructions>
+
+If the user did not provide instructions, work through ALL incomplete tasks until NONE remain.
+
+## Steps
+
+1. Track attempt count and previously attempted tasks to prevent infinite loops
+2. Use the `@tasks` skill to extract the first incomplete task from `.llm/todo.md`
+3. If a task is found:
+   - Check if we have already attempted this task 1 time
+   - If yes, mark it as blocked (with `- [!]`) and continue to next task
+   - If no, launch the `@tasks:do-task` agent to implement it
+   - **Do NOT add instructions to the agent prompt** - the agent is self-contained and follows its own workflow (including precommit, commit, rebase)
+   - Do NOT mark the task as complete yourself - the `do-task` agent does this
+4. Repeat until no incomplete tasks remain or the user's instructions are met
+5. When all tasks are completed, archive the task list:
+
+@../shared/scripts/task-archive.md
+
+## Notes
+
+- Each task is handled completely by the `do-task` agent before moving to the next
+- The `do-task` agent marks tasks as complete - do NOT call `task_complete.py` yourself
+- Each task gets its own commit for clear history
+- After each agent returns, check the task list again to see if more tasks remain
+
+## User feedback
+
+Throughout the process, provide clear status updates:
+
+- "Starting task: [task description]"
+- "Task completed successfully: [task description]"
+- "Task failed: [task description]"
+- "Skipping blocked task: [task description]"
+- "All tasks completed - task list archived to .llm/YYYY-MM-DD-todo.md" or "Stopping due to failures"

commands/do-one-task.md

@@ -0,0 +1,7 @@
+---
+description: Find and implement the next incomplete task from the project task list
+---
+
+Find and implement the next incomplete task from the project task list.
+
+@../shared/task-workflow.md

commands/plan-tasks.md

@@ -0,0 +1,36 @@
+---
+name: plan-tasks
+description: Capture conversation planning into self-contained tasks at end of discussion
+---
+
+# Plan Tasks
+
+Transform conversation planning and requirements into a markdown task list where each task is completely self-contained with all necessary context inline.
+
+@../shared/task-format.md
+
+## When to Use
+
+Use this command at the **end of a planning conversation** when you have discussed requirements, approaches, and implementation details but have not started coding yet. This captures the conversation context into actionable tasks in `.llm/todo.md`.
+
+## Input
+
+The input is the current conversation where planning and requirements have been discussed. Transform the plans, ideas, and requirements from the discussion into self-contained tasks in a markdown checklist format, appended to `.llm/todo.md`.
+
+## Task Writing Guidelines
+
+Each task should be written so it can be read independently from `- [ ]` to the next `- [ ]` and contain:
+
+1. **Full absolute paths** - Never use relative paths
+2. **Exact class/function names** - Specify exact names of code elements
+3. **Analogies to existing code** - Reference similar existing implementations
+4. **Specific implementation details** - List concrete methods or operations
+5. **Module/package context** - State which module or package the work belongs to
+6. **Dependencies and prerequisites** - Note what needs to exist or be imported
+7. **Expected outcomes** - Describe what success looks like
+
+## Example
+
+```markdown
+- [ ] Create a new test class `SynchronizedBagTest` at `/Users/craig/projects/eclipse-collections/unit-tests-thread-safety/src/test/java/org/eclipse/collections/impl/bag/mutable/SynchronizedBagTest.java` to test thread-safety of `org.eclipse.collections.impl.bag.mutable.SynchronizedBag`. Similar to how `SynchronizedMutableListTest` covers `SynchronizedMutableList`, this should extend `SynchronizedTestTrait` and implement test traits like `SynchronizedCollectionTestTrait`, `SynchronizedMutableIterableTestTrait`, and `SynchronizedRichIterableTestTrait`. The test should verify that all public methods of SynchronizedBag properly synchronize on the lock object using the `assertSynchronized()` method. Include tests for bag-specific methods like `addOccurrences()`, `removeOccurrences()`, `occurrencesOf()`, `forEachWithOccurrences()`, and `toMapOfItemToCount()`.
+```

commands/sweep-todos.md

@@ -0,0 +1,21 @@
+---
+description: Find all TODO and TASK comments and add them to the project task list
+---
+
+Find all TODO and TASK comments and add them to the project task list.
+
+Search the codebase for all TODO and TASK comments and add them to `.llm/todo.md`. Each TODO or TASK found in the code will be converted to a task in the markdown task list.
+
+## Steps
+
+1. Find all occurrences of "TODO" in the codebase using grep/search
+2. For each occurrence, gather:
+   - File path
+   - Line number
+   - Full TODO comment text
+3. Strip comment markers (`//`, `#`, `/* */`) from the TODO/TASK text
+4. Add each TODO or TASK as a new task entry to `.llm/todo.md`:
+   ```markdown
+   - [ ] Implement TODO from src/api/client.ts:87: Extract commonality in getRootNodes and getChildNodes
+   - [ ] Implement TODO from test/utils.test.ts:103: Use deep object equality rather than loose assertions
+   ```