SwiftlyS2 plugin development toolkit for VS Code Copilot (agents, prompts, skills)
Agent
Fast execution agent for the SwiftlyS2 / SW2 plugin ecosystem. It is intended for small to medium SwiftlyS2 C#/.NET modification tasks with clear goals and straightforward validation. It must first load the workspace rules and the SwiftlyS2-Toolkit, and it should maximize safe parallel subagent usage to improve…
Agent
Development agent for the SwiftlyS2 / SW2 plugin ecosystem. When creating, modifying, auditing, planning, or refactoring SwiftlyS2 C#/.NET plugins, it must first load the workspace rules and the SwiftlyS2-Toolkit, and for non-trivial tasks it must invoke the review subagent for cross-checking until approval is reached…
Agent
SwiftlyS2 planning subagent focused on file / method-level landing, implementation order, thread boundaries, lifecycle cleanup, and the smallest correct change surface. It independently generates a method-level plan from the input and keeps cross-discussing with the other planning viewpoints in later rounds until…
Agent
SwiftlyS2 planning subagent focused on player-visible semantics, historical behavior alignment, architecture selection, and lifecycle closure. It independently generates a method-level plan from the input and, in later rounds, raises objections to or agrees with other plans.
Agent
SwiftlyS2 planning subagent focused on TDD, validation matrices, regression paths, and requirement-to-evidence alignment. It independently produces a plan from the input and then reviews whether other plans are truly verifiable and sufficient for completing an execution-and-validation loop within a single conversation.
Agent
Pure planning agent for the SwiftlyS2 / SW2 plugin ecosystem. It only loads the workspace rules and the SwiftlyS2-Toolkit, orchestrates three plan subagents to generate and converge a method-level plan, does not directly edit code or implement fixes, and only outputs a final TDD-based plan. It generates a prompt plan…
Agent
Review subagent for SwiftlyS2 / SW2 plugin tasks. It reviews the main agent’s plans, audit conclusions, or code modification proposals, specifically looking for omissions, architectural drift, lifecycle gaps, threading risks, and unnecessary bridge / shared / intermediate layers, until it can issue an explicit pass or…