wnsrn3436/open-game-works-core
A harness that lets AI agents make server-client games of commercial quality on a prebuilt core
stack: TypeScript
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 wnsrn3436/open-game-works-core/agents ./rig-open-game-works-core/agents $ npx degit wnsrn3436/open-game-works-core/skills ./rig-open-game-works-core/skills
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.
$ npx degit wnsrn3436/open-game-works-core/skills/client-content .claude/skills/client-content $ npx degit wnsrn3436/open-game-works-core/skills/client-core .claude/skills/client-core $ npx degit wnsrn3436/open-game-works-core/skills/contract .claude/skills/contract $ npx degit wnsrn3436/open-game-works-core/skills/core .claude/skills/core $ npx degit wnsrn3436/open-game-works-core/skills/data .claude/skills/data $ npx degit wnsrn3436/open-game-works-core/skills/game-design .claude/skills/game-design $ npx degit wnsrn3436/open-game-works-core/skills/game-loop .claude/skills/game-loop $ npx degit wnsrn3436/open-game-works-core/skills/game-setup .claude/skills/game-setup $ npx degit wnsrn3436/open-game-works-core/skills/host-env .claude/skills/host-env $ npx degit wnsrn3436/open-game-works-core/skills/resource .claude/skills/resource $ npx degit wnsrn3436/open-game-works-core/skills/server-content .claude/skills/server-content $ npx degit wnsrn3436/open-game-works-core/skills/server-core .claude/skills/server-core
$ curl -fsSL --create-dirs -o .claude/agents/client-hardening.md https://raw.githubusercontent.com/wnsrn3436/open-game-works-core/main/agents/client-hardening.md $ curl -fsSL --create-dirs -o .claude/agents/content.md https://raw.githubusercontent.com/wnsrn3436/open-game-works-core/main/agents/content.md $ curl -fsSL --create-dirs -o .claude/agents/core.md https://raw.githubusercontent.com/wnsrn3436/open-game-works-core/main/agents/core.md $ curl -fsSL --create-dirs -o .claude/agents/judge.md https://raw.githubusercontent.com/wnsrn3436/open-game-works-core/main/agents/judge.md $ curl -fsSL --create-dirs -o .claude/agents/play.md https://raw.githubusercontent.com/wnsrn3436/open-game-works-core/main/agents/play.md $ curl -fsSL --create-dirs -o .claude/agents/resource.md https://raw.githubusercontent.com/wnsrn3436/open-game-works-core/main/agents/resource.md $ curl -fsSL --create-dirs -o .claude/agents/review.md https://raw.githubusercontent.com/wnsrn3436/open-game-works-core/main/agents/review.md $ curl -fsSL --create-dirs -o .claude/agents/server-hardening.md https://raw.githubusercontent.com/wnsrn3436/open-game-works-core/main/agents/server-hardening.md $ curl -fsSL --create-dirs -o .claude/agents/translation.md https://raw.githubusercontent.com/wnsrn3436/open-game-works-core/main/agents/translation.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (12)
client-contentclient-corecontractcoredatagame-designgame-loopgame-setuphost-envresourceserver-contentserver-core
Subagents (9)
| client-hardening | — |
| content | — |
| core | — |
| judge | — |
| play | — |
| resource | — |
| review | — |
| server-hardening | — |
| translation | — |
Similar rigs
AlmanacCode/codealmanac
A codebase wiki for AI coding agents. Captures what the code can't say: decisions, flows, invariants, gotchas.
Pragmatist 4.1k tok · · Q8
tony/claude-code-riper-5
Claude Code (Sub-agent, Custom Commands) for RIPER-5
Pragmatist 3.0k tok · · Q20
launch52-ai/flutter-template
Template for Flutter mobile applications.
Skill Collector 3.4k tok · · Q0
Ian-Lo/application-doc-toolkit
Fact-governance for LLM-written documents: claims trace to a verified source entry, a scripted lint gates every draft, reviewers hold no write access. Applied to resumes and cover letters.
Pragmatist 8.4k tok · · Q18