Task Execution Workflow

Collaborates with users to design structured development plans broken into testable commits, with research and clarification steps.

Load a written implementation plan, execute each task with verification checkpoints, and complete development using a structured workflow.

Create, list, and view GitHub issues using the gh CLI with guided workflows for gathering titles, descriptions, labels, and reproduction steps.

Executes a phased implementation plan by deploying subagents for implementation, verification, anti-pattern checks, code quality review, and committing.

Provides a repeatable, auditable workflow for large coding tasks by initializing repo-local task artifacts, installing subagent templates, and running a spec-freeze → build → evidence → verify → fix loop with fresh-session verification.

Delegates tasks to specialized AI agents running in parallel via the Box0 platform, enabling code review, security checks, research, and documentation.

Provides detailed guidance on Hermes Kanban worker lifecycle, including workspace handling, handoff patterns, retry diagnostics, and edge cases for dispatched workers.

Inspect and adjust the agent's runtime state, including model, context window, iteration limits, token usage, workspace configuration, subagent status, and request routing metadata.

Loads an implementation plan, executes tasks in batches with verification, and reports progress for review between batches.

Executes a written implementation plan in batches, pausing between batches for review and feedback.