Load Task — Productivity skill for Claude Code
You're preparing to work on the task ("T123") or subtask ("T123/1.2").
How to install Load Task
Installs to ~/.claude/commands/davidlee-claude-code-starter-load-task.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/davidlee/claude-code-starter/HEAD/.claude/commands/load-task.md -o ~/.claude/commands/davidlee-claude-code-starter-load-task.md Restart Claude Code, or start a new session, for it to be picked up.
What Load Task does
You're preparing to work on the task ("T123") or subtask ("T123/1.2"): $ARGUMENTS.
- Find, read and understand the task card in
kanban/(usuallykanban/backlogorkanban/in-progress). - If given a specific subtask ("1.2"), run a pre-flight check:
- Read the execution plan critically, understand it, and consider any referenced files relevant to its completion. Ask any questions necessary to refine the plan and ensure the plan (and overall task context) is clear.
- If a subta
Alternatives in Productivity
- Configure Claude HUD — FIRST: Use the Read tool to load ~/.claude/plugins/claude-hud/config.json if it exists 10.9k ★
- Ticket Workflow — Work on ticket: $ARGUMENTS 5.8k ★
- Skill Context Detection — Auto-detect work context (Dev vs Knowledge) — use to tailor workflows based on current task type 2.8k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Subtask.Prompt
Delegate a bounded child task to a specialist agent and get a structured result back — use for isolated, well-
Task Start
Claim task and load full context to begin work
Load Cursor Rules
Load relevant coding rules for the current task
Find Context
Find relevant context files by topic. Use when you need to load files for a topic without a slash command, or
Context Load
Load project structure, stack, architecture, conventions, and key files for task context.
Harness Load
Load the layered harness for a project and task — assembles kernel, protocol, skills, project context, and the
Related Agents
Ren Reviewer
Adversarial reviewer for the execution doctrine's review gate. Spawn after every completed subtask, before cha
Task Plan Architect
Uses the smartest available Claude model to expand one broad GitHub issue into a bounded set of implementation
Subtask Verifier
Use this agent to verify that a finished implementation matches the subtask spec in docs/roadmap/{NNNN}-{miles