Hook Claude Code
Runs when a session starts on startup and resume, executing session-start.py and web_hook.py via python3 with --source-app and --event-type (2 commands). From tettethu/VibeGame.
Hook Claude Code
Runs when you submit a prompt, before the agent sees it, executing goal-capture.py and web_hook.py via python3 with --source-app and --event-type (2 commands). From tettethu/VibeGame.
Hook Claude Code
Runs when a session ends, executing web_hook.py via python3 with --source-app and --event-type. From tettethu/VibeGame.
Hook Claude Code
Runs before the agent uses a tool for Agent tool calls, executing web_hook.py, enforce-team-setup.py and enforce-team-mode.py via python3 with --source-app and --event-type (3 commands). From tettethu/VibeGame.
Hook Claude Code
Runs when the agent asks permission for an action, executing web_hook.py via python3 with --source-app and --event-type. From tettethu/VibeGame.
Hook Claude Code
Runs when the agent finishes a response, executing agent-team-stop.py via python3 with --source-app. From tettethu/VibeGame.
Hook Claude Code
Runs when a subagent starts, executing web_hook.py via python3 with --source-app and --event-type. From tettethu/VibeGame.
Hook Claude Code
Runs when a subagent finishes, executing web_hook.py via python3 with --source-app and --event-type. From tettethu/VibeGame.
Hook Claude Code
Runs after a tool call finishes for SendMessage tool calls, executing teammate-message-touch.py via python3. From tettethu/VibeGame.
Settings file Claude Code
Agent settings declaring 9 hook events (SessionStart, UserPromptSubmit, SessionEnd, PreToolUse).
Agent
Technical architect for one code task. Owns deep technical research, task-level implementation planning, and per-task context configuration.
Agent
Game artist. Generates and processes visual assets, registers them in manifest.json.
Agent
Static quality auditor for one code task. Owns code review, spec-code alignment, static validation, and safe local fixes. Does not run the game.
Agent
Game designer agent. Use for design tasks: creating or updating GDD.md sections, designing new game mechanics, systems, or content.
Agent
Runtime verification teammate for one code task. Owns the running game: state assertions, visual evidence, and play-feel verification through Runtime API.
Agent
Programmer for one approved code task. Owns code changes for the approved task contract and validates them before handoff.
Agent
VibeGame build final quality gate. Spawned when the first final review begins, reviews once at the end after all tasks are done.
Skill Claude CodeCodex
Distill stable art-generation patterns from a completed project, so future projects produce comparable assets without re-discovering the prompts. Lead-dispatched only — orchestrator invokes this skill from its self-evolve flow with a game-slug message; do not self-trigger.
Skill Claude CodeCodex
Capture reusable patterns from a finished project and lift them into framework-level priors (contracts, modules, skeletons) that future projects inherit. Run only when the user explicitly requests self-evolution; the orchestrator executes the workflow.
Skill Claude CodeCodex
Run VibeGame's standard end-to-end game development workflow with reviewer gates. Use when the user wants to create a game from zero or evolve an existing game across multiple stages.
Skill Claude CodeCodex
Iterate broadly on an existing game, on top of vibegame-build. Use when the user asks to change an existing game's art style, genre, or core rules. Not for local tuning such as numbers or game feel. Orchestrator only.
Skill Claude CodeCodex
Resume a VibeGame orchestrator session after vibegame start. Use at the beginning of a Claude or Codex session to inspect team runtime state, repair missing persistent members, load goal and GDD context, inspect tasks, and ask the user what to do next.