thebrownproject-space-agents

Plugin thebrownproject-space-agents from marketplace cascade-ai-ml-agents-misc-1 in joshuarweaver/cascade-ai-ml-agents-misc-1. Commands read from the repo's manifest — 1 month ago.

Skills (16)

• capcom

  Check mission status and progress via fresh subagent. Queries Beads for features, tasks, bugs, and recent work activity. Keeps HOUSTON context lean.

• exploration-brainstorm

  Explore ideas through conversation. HOUSTON asks questions, has opinions, and suggests background agents when investigation would help.

• exploration-debug

  Interactive debugging through conversation. HOUSTON guides through 4 phases, asks questions, and suggests agents for investigation.

• exploration-plan

  Structure work into plans and Beads. Three modes: plan from brainstorm, plan from scratch, or create Beads from existing plan.

• exploration-review

  Interactive code review through conversation. HOUSTON guides review, spawns specialized agents, and helps create Beads for issues found.

• exploration-write-spec

  Produce structured spec.md from brainstorm conversations. Creates a consistent format that feeds cleanly into the planning phase.

• exploration

  Select mode, delegate to analysis skill.

• install

  Use to install Space-Agents in a project. Creates .space-agents/ directory and initializes Beads for issue tracking. Run once per project.

• land

  End session. Reconciles exploration folders, appends context to CAPCOM, syncs Beads, displays session stats.

• launch

  Start a Space-Agents session. Displays welcome screen with project status.

• mission-airlock

  Run test and lint validation gate. Use after implementation to verify code quality.

• mission-orchestrated

  HOUSTON spawns Pathfinder, Builder, Inspector per task. Best for medium features (4-10 tasks).

• mission-pod

  Execute a single task with Pathfinder/Builder/Inspector crew. Self-fetches work from Beads.

• mission-ralph

  Launch ralph.sh in background. Lightweight mode (default) or full Pod crew (--pod). Best for large features (10+ tasks).

• mission-solo

  HOUSTON executes feature tasks directly. No agents. Best for small features (1-3 tasks).

• mission

  Select feature, select mode, delegate to execution skill.

Subagents (14)

• brainstorm-architecture

  Propose architectural approaches with trade-offs during brainstorming

• brainstorm-research

  Explore codebase for relevant patterns, constraints, and context during brainstorming

• brainstorm-risk

  Identify risks, failure modes, and effort estimates during brainstorming

• debug

  Trace code paths, gather evidence, and investigate issues during debugging sessions

• mission-builder

  Writes code for tasks using Pathfinder findings and TDD approach

• mission-inspector

  Reviews implementation for requirements and code quality (two-pass)

• mission-pathfinder

  Explores codebase and provides implementation context for tasks

• plan-implementer

  Create detailed TDD task breakdown for tasks

• plan-sequencer

  Analyze dependencies and sequence tasks during planning

• plan-task-planner

  Break a feature into tasks during planning

• review-code-simplifier

  Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.

• review-performance

  Review code for performance issues and optimization opportunities

• review-quality

  Review code for quality, readability, and maintainability issues

• review-security

  Review code for security vulnerabilities and risks

Similar plugins