hamster

Implements all subtasks of a single parent Hamster Studio task (HAM-XXX). Reads the parent and all its subtask files from .hamster/, discovers relevant codebase context just-in-time, implements all subtasks sequentially in one session (maintaining full context across them), updates task statuses, and reports all changes. Does NOT run project validation — that is handled by the orchestrator after all parallel executors complete. Examples: <example> Context: The orchestrator needs a parent task and its subtasks implemented. assistant: "I'll launch the task-executor to implement HAM-100 and its subtasks HAM-101, HAM-102, HAM-103." <commentary> Use task-executor for each parent task in the execution loop. One agent session handles all subtasks. </commentary> </example>

Reads a Hamster Studio brief and all tasks from .hamster/, builds a parent/subtask dependency graph, detects overlapping parents (those that mention the same files/components), groups independent parents into parallel execution waves, and produces a structured execution plan. Use before executing a brief to understand scope, dependencies, and parallelization strategy. Examples: <example> Context: The user wants to execute a brief and needs an execution plan first. user: "Plan the user-authentication brief before we start" assistant: "I'll launch the brief-planner to build a dependency graph and parallel wave groupings for the user-authentication brief." <commentary> Use brief-planner to produce a structured execution plan with parallel waves before any code changes. </commentary> </example> <example> Context: The orchestrator needs to understand brief scope before starting execution. assistant: "Let me analyze the brief to determine execution order and identify which parent tasks can run in parallel." <commentary> The brief-planner maps the dependency graph and groups independent parents into waves for parallel execution. </commentary> </example>

Handles branch creation and PR operations for the Hamster CLI plugin. Creates the feature branch at the start of execution, and pushes + creates the PR at the end. Individual commits (per parent task, review fixes, simplifications) are handled directly by the orchestrator using bash commands. Examples: <example> Context: Starting a new brief execution and need a feature branch. assistant: "Launching commit-manager to create the feature branch for this brief." <commentary> The commit-manager creates branches with the naming convention feature/ham-{id}-{slug}. </commentary> </example> <example> Context: All tasks are done and a PR needs to be created. assistant: "Launching commit-manager to push and create the PR." <commentary> The commit-manager handles PR creation with a task checklist and changes summary. </commentary> </example>

Reviews and simplifies code changes for a completed parent task. Runs in two phases: Phase 1 reviews for convention compliance, quality, security, and completeness — producing a PASS or NEEDS_FIXES verdict. If PASS, Phase 3 applies simplification (reducing complexity, improving naming, removing noise) while preserving all functionality. Runs after all parallel task-executors in a wave have completed. Examples: <example> Context: All subtasks under HAM-100 are done and need review before committing. assistant: "Launching quality-gate to review and simplify the cumulative changes for HAM-100." <commentary> The quality-gate runs after a parent task's subtasks are all complete. It handles both review and simplification in one session. </commentary> </example> <example> Context: Review found critical issues that need fixing before simplification. assistant: "Quality-gate returned NEEDS_FIXES for HAM-200. Reporting issues to orchestrator." <commentary> If critical issues are found, quality-gate stops at NEEDS_FIXES and does NOT simplify. </commentary> </example>

Plan a Hamster Studio brief. Read tasks, build dependency graph, detect parallel execution waves, with optional CEO or Eng review modes. Use when the user wants to analyze a brief before executing.

Systematic QA with diff-aware, full suite, quick smoke, or regression testing modes. Issue taxonomy and optional fix loop. Use when the user wants to run tests or check quality on their changes.

Resume an interrupted brief execution. Auto-detect progress, reconstruct state from git history and task statuses, and continue from the correct wave. Use when the user wants to continue a previously interrupted ship session.

Engineering retrospective from git history. Team metrics, contributor deep-dives, trends, and actionable insights. Use when the user wants a retrospective on recent development activity.

Paranoid two-pass code review. CRITICAL issues that block shipping, then INFORMATIONAL advisory findings. Interactive resolution for critical issues. Use when the user wants a code review on their current feature branch.

Ship a Hamster Studio brief. Merge base, implement in parallel waves, test, review, create bisectable commits, and optionally PR. Use when the user wants to execute or ship a brief.