rqd6f4g6zn-bit/OneCommand
Build complete, production-ready software systems from a single prompt. Developed by USC Software UG.
stack: Python
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 rqd6f4g6zn-bit/OneCommand/agents ./rig-onecommand/agents $ npx degit rqd6f4g6zn-bit/OneCommand/commands ./rig-onecommand/commands $ npx degit rqd6f4g6zn-bit/OneCommand/skills ./rig-onecommand/skills $ npx degit rqd6f4g6zn-bit/OneCommand/hooks ./rig-onecommand/hooks
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 rqd6f4g6zn-bit/OneCommand/.codex-plugin/skills/onecommand .claude/skills/onecommand $ npx degit rqd6f4g6zn-bit/OneCommand/skills/21st-components .claude/skills/21st-components $ npx degit rqd6f4g6zn-bit/OneCommand/skills/acceptance-tester .claude/skills/acceptance-tester $ npx degit rqd6f4g6zn-bit/OneCommand/skills/app-icon-generator .claude/skills/app-icon-generator $ npx degit rqd6f4g6zn-bit/OneCommand/skills/asset-generator .claude/skills/asset-generator $ npx degit rqd6f4g6zn-bit/OneCommand/skills/auto-clear .claude/skills/auto-clear $ npx degit rqd6f4g6zn-bit/OneCommand/skills/automation-installer .claude/skills/automation-installer $ npx degit rqd6f4g6zn-bit/OneCommand/skills/brain-core .claude/skills/brain-core $ npx degit rqd6f4g6zn-bit/OneCommand/skills/codex-setup .claude/skills/codex-setup $ npx degit rqd6f4g6zn-bit/OneCommand/skills/collab-protocol .claude/skills/collab-protocol $ npx degit rqd6f4g6zn-bit/OneCommand/skills/context-manager .claude/skills/context-manager $ npx degit rqd6f4g6zn-bit/OneCommand/skills/cross-agent-sync .claude/skills/cross-agent-sync $ npx degit rqd6f4g6zn-bit/OneCommand/skills/delivery-reporter .claude/skills/delivery-reporter $ npx degit rqd6f4g6zn-bit/OneCommand/skills/demo-cleaner .claude/skills/demo-cleaner $ npx degit rqd6f4g6zn-bit/OneCommand/skills/domain-blueprints .claude/skills/domain-blueprints $ npx degit rqd6f4g6zn-bit/OneCommand/skills/emil .claude/skills/emil $ npx degit rqd6f4g6zn-bit/OneCommand/skills/exceed-expectations .claude/skills/exceed-expectations $ npx degit rqd6f4g6zn-bit/OneCommand/skills/game-engine-selector .claude/skills/game-engine-selector $ npx degit rqd6f4g6zn-bit/OneCommand/skills/godot-builder .claude/skills/godot-builder $ npx degit rqd6f4g6zn-bit/OneCommand/skills/live-integrations .claude/skills/live-integrations $ npx degit rqd6f4g6zn-bit/OneCommand/skills/ml-builder .claude/skills/ml-builder $ npx degit rqd6f4g6zn-bit/OneCommand/skills/oc-frontend-design .claude/skills/oc-frontend-design $ npx degit rqd6f4g6zn-bit/OneCommand/skills/oc-marketing .claude/skills/oc-marketing $ npx degit rqd6f4g6zn-bit/OneCommand/skills/oc-ui-ux .claude/skills/oc-ui-ux $ npx degit rqd6f4g6zn-bit/OneCommand/skills/os-builder .claude/skills/os-builder $ npx degit rqd6f4g6zn-bit/OneCommand/skills/phaser-builder .claude/skills/phaser-builder $ npx degit rqd6f4g6zn-bit/OneCommand/skills/self-healer .claude/skills/self-healer $ npx degit rqd6f4g6zn-bit/OneCommand/skills/spec-analyzer .claude/skills/spec-analyzer $ npx degit rqd6f4g6zn-bit/OneCommand/skills/stack-detector .claude/skills/stack-detector $ npx degit rqd6f4g6zn-bit/OneCommand/skills/store-readiness-checker .claude/skills/store-readiness-checker $ npx degit rqd6f4g6zn-bit/OneCommand/skills/threejs-builder .claude/skills/threejs-builder $ npx degit rqd6f4g6zn-bit/OneCommand/skills/video-producer .claude/skills/video-producer $ npx degit rqd6f4g6zn-bit/OneCommand/skills/voice-agent .claude/skills/voice-agent $ npx degit rqd6f4g6zn-bit/OneCommand/skills/wordpress-builder .claude/skills/wordpress-builder
$ curl -fsSL --create-dirs -o .claude/agents/backend-agent.md https://raw.githubusercontent.com/rqd6f4g6zn-bit/OneCommand/main/agents/backend-agent.md $ curl -fsSL --create-dirs -o .claude/agents/brain-agent.md https://raw.githubusercontent.com/rqd6f4g6zn-bit/OneCommand/main/agents/brain-agent.md $ curl -fsSL --create-dirs -o .claude/agents/frontend-agent.md https://raw.githubusercontent.com/rqd6f4g6zn-bit/OneCommand/main/agents/frontend-agent.md $ curl -fsSL --create-dirs -o .claude/agents/game-agent.md https://raw.githubusercontent.com/rqd6f4g6zn-bit/OneCommand/main/agents/game-agent.md $ curl -fsSL --create-dirs -o .claude/agents/marketing-agent.md https://raw.githubusercontent.com/rqd6f4g6zn-bit/OneCommand/main/agents/marketing-agent.md $ curl -fsSL --create-dirs -o .claude/agents/ml-agent.md https://raw.githubusercontent.com/rqd6f4g6zn-bit/OneCommand/main/agents/ml-agent.md $ curl -fsSL --create-dirs -o .claude/agents/mobile-agent.md https://raw.githubusercontent.com/rqd6f4g6zn-bit/OneCommand/main/agents/mobile-agent.md $ curl -fsSL --create-dirs -o .claude/agents/os-agent.md https://raw.githubusercontent.com/rqd6f4g6zn-bit/OneCommand/main/agents/os-agent.md $ curl -fsSL --create-dirs -o .claude/agents/security-agent.md https://raw.githubusercontent.com/rqd6f4g6zn-bit/OneCommand/main/agents/security-agent.md $ curl -fsSL --create-dirs -o .claude/agents/self-improve-agent.md https://raw.githubusercontent.com/rqd6f4g6zn-bit/OneCommand/main/agents/self-improve-agent.md $ curl -fsSL --create-dirs -o .claude/agents/test-agent.md https://raw.githubusercontent.com/rqd6f4g6zn-bit/OneCommand/main/agents/test-agent.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 (34)
onecommand21st-componentsacceptance-testerapp-icon-generatorasset-generatorauto-clearautomation-installerbrain-corecodex-setupcollab-protocolcontext-managercross-agent-syncdelivery-reporterdemo-cleanerdomain-blueprintsemilexceed-expectationsgame-engine-selectorgodot-builderlive-integrationsml-builderoc-frontend-designoc-marketingoc-ui-uxos-builderphaser-builderself-healerspec-analyzerstack-detectorstore-readiness-checkerthreejs-buildervideo-producervoice-agentwordpress-builder
Subagents (11)
| backend-agent model: sonnet | Generates complete backend code (API routes, auth, DB schema, migrations, seed data) by delegating bulk code generation to Codex. Reads .onecommand-spec.json for requirements. |
| brain-agent model: opus | OneCommand's intelligence orchestrator. Runs at build start (READ memories, detect similar projects), after each phase (CHECKPOINT + pattern update), and at build end (REFLECT, update episodic memory, |
| frontend-agent model: sonnet | Generates complete frontend code (all pages, components, styling) by applying the bundled oc-frontend-design and oc-ui-ux skills (plus the user's design skills from the skill plan). Reads .onecommand- |
| game-agent model: sonnet | Orchestrates generation of a complete 2D/3D game. Selects the optimal engine (Godot 4, Three.js, Phaser 3), generates all game code, worlds, characters, assets, and export configuration. Delivers a pl |
| marketing-agent model: sonnet | Generates landing page copy, README.md, and CHANGELOG.md using marketing-skills. Runs in parallel with the backend-agent during Phase 3. |
| ml-agent model: sonnet | Builds a complete AI/ML training project (data pipeline, training, evaluation, model card, FastAPI inference) from the spec's "ml" section, following the ml-builder skill. Verifies with hooks/ml-gate. |
| mobile-agent model: sonnet | Generates a complete, store-ready Flutter app (iOS + Android) from the project spec. Covers all screens, state management, API integration, auth, push notifications, app icons, splash screens, and all |
| os-agent model: sonnet | Orchestrates generation of a complete custom Linux-based operating system. Reads the spec, invokes os-builder skill, optionally runs a Docker-based build test, and delivers a complete buildable OS pro |
| security-agent model: opus | Performs an OWASP-based security audit on the generated codebase and fixes all critical and high-severity issues. Part of the Exceed-Expectations phase. |
| self-improve-agent model: opus | After each OneCommand run, extracts successful patterns, recurring errors, and proven stack combinations into ~/.onecommand/memory/. Future runs load this memory to make faster, more accurate decision |
| test-agent model: sonnet | Quality gate of OneCommand. Runs hooks/quality-gate.sh (install, API contract, typecheck, lint, build, unit tests), turns the spec's acceptance criteria into Playwright tests and verifies them against |
Slash commands (8)
/emil/oc-doctor/oc-resume/oc-save/oc-skills/oc-update/onecommand-status/onecommand
Similar rigs
jbeat30/claude-subagent-workflow
A Claude code plugin for sub-agent workflows led by the project manager, from planning and implementation to independent QA. Become a small one-person business
Orchestrator 2.4k tok · · Q3
wpank/ai
A curated collection of 115 skills, 16 agents, and 48 commands for Claude Code and Cursor.
Orchestrator 1.5k tok · · Q0
jmckinley/claude-code-resources
Complete guide and automation for Claude Code
Pragmatist 68 tok · · Q0
quboqin/template-agenticide-vibecoding
🤖 Claude Code定制化研发流程系统 - 基于Spec-Driven和Test-Driven的AI智能体团队协作框架。构建AI优先的软件开发新范式,让AI智能体团队替代传统人类开发团队。
Orchestrator 1.6k tok · · Q0