sumo91/godot-ai-workflow-templates
用Ai工具开发Godot游戏辅助Agent包Reusable multi-agent workflow templates for Godot development across Claude Code, Codex, Cursor, and Trae.
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code
$ npx degit sumo91/godot-ai-workflow-templates/templates/claude-godot-project/.claude ./rig-godot-ai-workflow-templates # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ curl -fsSL --create-dirs -o .claude/agents/godot-asset-integration-agent.md https://raw.githubusercontent.com/sumo91/godot-ai-workflow-templates/main/templates/claude-godot-project/.claude/agents/godot-asset-integration-agent.md $ curl -fsSL --create-dirs -o .claude/agents/godot-design-agent.md https://raw.githubusercontent.com/sumo91/godot-ai-workflow-templates/main/templates/claude-godot-project/.claude/agents/godot-design-agent.md $ curl -fsSL --create-dirs -o .claude/agents/godot-implementation-agent.md https://raw.githubusercontent.com/sumo91/godot-ai-workflow-templates/main/templates/claude-godot-project/.claude/agents/godot-implementation-agent.md $ curl -fsSL --create-dirs -o .claude/agents/godot-planning-agent.md https://raw.githubusercontent.com/sumo91/godot-ai-workflow-templates/main/templates/claude-godot-project/.claude/agents/godot-planning-agent.md $ curl -fsSL --create-dirs -o .claude/agents/godot-review-agent.md https://raw.githubusercontent.com/sumo91/godot-ai-workflow-templates/main/templates/claude-godot-project/.claude/agents/godot-review-agent.md $ curl -fsSL --create-dirs -o .claude/agents/godot-validation-agent.md https://raw.githubusercontent.com/sumo91/godot-ai-workflow-templates/main/templates/claude-godot-project/.claude/agents/godot-validation-agent.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Subagents (6)
| godot-asset-integration-agent | Use PROACTIVELY when a Godot task mainly involves wiring art, audio, animation, UI assets, or resource references without changing gameplay logic. |
| godot-design-agent | Use PROACTIVELY for new Godot features, behavior changes, and unclear requests before coding. Focus on player-visible behavior, scene impact, state rules, and acceptance criteria. |
| godot-implementation-agent | Use PROACTIVELY for narrow, file-bounded Godot implementation tasks after planning is complete. Must stay within assigned files and report concise verification results. |
| godot-planning-agent | Use PROACTIVELY once a Godot design is approved and work needs to be split into small, low-conflict task packets with file ownership and validation steps. |
| godot-review-agent | Use PROACTIVELY after a Godot task or feature is implemented, and before final completion, to review spec compliance, file ownership violations, maintainability risks, and missing validation. |
| godot-validation-agent | Use PROACTIVELY after Godot implementation work to validate scene loading, script health, resource references, and behavior against acceptance criteria. |
Slash commands (13)
/asset-wire/bugfix/feature/godot-brainstorm/godot-debug/godot-execute/godot-plan/godot-review/godot-ship/plan-feature/review-feature/ship-check/validate-feature
Cursor rules (6)
00-core-workflow · always10-godot-risk · always20-auto-agent-selection · always30-nightly-automation40-session-threading · always50-completion-gate · always
Similar rigs
rtk-ai/rtk
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
Orchestrator 2.6k tok ·
Yeachan-Heo/oh-my-claudecode
Teams-first Multi-agent orchestration for Claude Code
Orchestrator 14.5k tok ·
alirezarezvani/claude-skills
380 Claude Code skills & agent skills & plugins (30+ Agents, 70+ custom commands, 380+ skills, customizable references, scripts)for Claude Code, Codex, Gemini CLI, Cursor, and 8 more coding agents — engineering, marketing, product, complian
Orchestrator 48.5k tok ·
czlonkowski/n8n-mcp
A MCP for Claude Desktop / Claude Code / Windsurf / Cursor to build n8n workflows for you
Orchestrator 3.8k tok ·