growthxai/output
The open-source TypeScript framework for building AI workflows and agents. Designed for Claude Code describe what you want, Claude builds it, with all the best practices already in place.
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 growthxai/output/.claude ./rig-output # 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.
$ npx degit growthxai/output/.claude/skills/llm-output-schema-constraints .claude/skills/llm-output-schema-constraints $ npx degit growthxai/output/.claude/skills/prompt-file-provider-options .claude/skills/prompt-file-provider-options $ npx degit growthxai/output/.claude/skills/validate .claude/skills/validate $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-build-workflow .claude/skills/output-build-workflow $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-credentials-edit .claude/skills/output-credentials-edit $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-credentials-env-vars .claude/skills/output-credentials-env-vars $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-credentials-init .claude/skills/output-credentials-init $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-debug-workflow .claude/skills/output-debug-workflow $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-dev-agent-class .claude/skills/output-dev-agent-class $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-dev-code-style .claude/skills/output-dev-code-style $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-dev-cost-hooks .claude/skills/output-dev-cost-hooks $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-dev-create-skeleton .claude/skills/output-dev-create-skeleton $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-dev-credentials .claude/skills/output-dev-credentials $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-dev-eval-testing .claude/skills/output-dev-eval-testing $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-dev-evaluator-function .claude/skills/output-dev-evaluator-function $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-dev-folder-structure .claude/skills/output-dev-folder-structure $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-dev-http-client-create .claude/skills/output-dev-http-client-create $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-dev-llm-streaming .claude/skills/output-dev-llm-streaming $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-dev-model-selection .claude/skills/output-dev-model-selection $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-dev-prompt-file .claude/skills/output-dev-prompt-file $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-dev-scenario-file .claude/skills/output-dev-scenario-file $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-dev-skill-file .claude/skills/output-dev-skill-file $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-dev-step-function .claude/skills/output-dev-step-function $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-dev-types-file .claude/skills/output-dev-types-file $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-dev-upgrade-prompt-models .claude/skills/output-dev-upgrade-prompt-models $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-dev-workflow-cost .claude/skills/output-dev-workflow-cost $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-dev-workflow-function .claude/skills/output-dev-workflow-function $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-error-direct-io .claude/skills/output-error-direct-io $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-error-http-client .claude/skills/output-error-http-client $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-error-missing-schemas .claude/skills/output-error-missing-schemas $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-error-nondeterminism .claude/skills/output-error-nondeterminism $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-error-try-catch .claude/skills/output-error-try-catch $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-error-zod-import .claude/skills/output-error-zod-import $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-eval-audit .claude/skills/output-eval-audit $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-eval-dataset-design .claude/skills/output-eval-dataset-design $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-eval-error-analysis .claude/skills/output-eval-error-analysis $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-eval-judge-prompt .claude/skills/output-eval-judge-prompt $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-eval-validate-judge .claude/skills/output-eval-validate-judge $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-meta-post-flight .claude/skills/output-meta-post-flight $ npx degit growthxai/output/coding_assistants/claude/plugins/outputai/skills/output-meta-pre-flight .claude/skills/output-meta-pre-flight
$ curl -fsSL --create-dirs -o .claude/agents/api-expert.md https://raw.githubusercontent.com/growthxai/output/main/.claude/agents/api-expert.md $ curl -fsSL --create-dirs -o .claude/agents/docker-expert.md https://raw.githubusercontent.com/growthxai/output/main/.claude/agents/docker-expert.md $ curl -fsSL --create-dirs -o .claude/agents/llm-expert.md https://raw.githubusercontent.com/growthxai/output/main/.claude/agents/llm-expert.md $ curl -fsSL --create-dirs -o .claude/agents/nodejs-expert.md https://raw.githubusercontent.com/growthxai/output/main/.claude/agents/nodejs-expert.md $ curl -fsSL --create-dirs -o .claude/agents/temporal-expert.md https://raw.githubusercontent.com/growthxai/output/main/.claude/agents/temporal-expert.md $ curl -fsSL --create-dirs -o .claude/agents/testing-expert.md https://raw.githubusercontent.com/growthxai/output/main/.claude/agents/testing-expert.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 *)"
]
}
} Skills (54)
llm-output-schema-constraintsprompt-file-provider-optionsvalidateoutput-build-workflowoutput-credentials-editoutput-credentials-env-varsoutput-credentials-initoutput-debug-workflowoutput-dev-agent-classoutput-dev-code-styleoutput-dev-cost-hooksoutput-dev-create-skeletonoutput-dev-credentialsoutput-dev-eval-testingoutput-dev-evaluator-functionoutput-dev-folder-structureoutput-dev-http-client-createoutput-dev-llm-streamingoutput-dev-model-selectionoutput-dev-prompt-fileoutput-dev-scenario-fileoutput-dev-skill-fileoutput-dev-step-functionoutput-dev-types-fileoutput-dev-upgrade-prompt-modelsoutput-dev-workflow-costoutput-dev-workflow-functionoutput-error-direct-iooutput-error-http-clientoutput-error-missing-schemasoutput-error-nondeterminismoutput-error-try-catchoutput-error-zod-importoutput-eval-auditoutput-eval-dataset-designoutput-eval-error-analysisoutput-eval-judge-promptoutput-eval-validate-judgeoutput-meta-post-flightoutput-meta-pre-flightoutput-meta-project-contextoutput-migrateoutput-plan-workflowoutput-services-checkoutput-workflow-listoutput-workflow-resetoutput-workflow-resultoutput-workflow-runoutput-workflow-runs-listoutput-workflow-startoutput-workflow-statusoutput-workflow-stopoutput-workflow-trace-fileoutput-workflow-trace
Subagents (6)
| api-expert | Use this agent for Output.ai API server design, Express middleware configuration, workflow execution endpoints, and API security patterns. Specializes in workflow integration via REST APIs. |
| docker-expert | Use this agent for Output.ai containerization including Docker Compose configuration, Node.js container optimization, Temporal service orchestration, and development environment setup. Specializes in |
| llm-expert | Use this agent for AI SDK integration, LLM provider configuration, prompt template management, error handling for AI APIs, and optimizing LLM workflow patterns within Output. Specializes in Anthropic |
| nodejs-expert | Use this agent for Node.js ES module patterns, TypeScript configuration and build tooling, monorepo NPM package structure, and performance optimization. Specializes in Output.ai package architecture w |
| temporal-expert | Use this agent for Output.ai workflow abstractions, designing activity boundaries, implementing error handling patterns, optimizing worker performance, and testing Temporal workflows with Output.ai pa |
| testing-expert | Use this agent for Output.ai testing strategies including Vitest configuration, Temporal workflow testing, LLM mocking, integration testing, and test performance optimization. Specializes in JavaScrip |
Slash commands (1)
/pr-review
Plugins (2)
outputai@outputaioutputai@outputai
Similar rigs
claude-dev-suite/claude-dev-suite
Point it at a repo and it configures your AI coding assistant for that stack: agents, framework skills, MCP servers, path-scoped rules. One install, seven assistants - Claude Code, Copilot, Cursor, Gemini CLI, Codex CLI, Cline, Kimi Code. M
Orchestrator 9.3k tok ·
scaccogatto/okf-skills
The OKF toolkit for Claude Code — author, maintain, validate & visualize Open Knowledge Format bundles. Plugin, agent skills, and a GitHub Action.
Pragmatist 2.5k tok ·
bpenwell/claude-config
Portable Claude Code setup: settings, hooks, skills, and templated MCP servers with a one-command installer
Pragmatist 290 tok ·
melagiri/code-insights
Turn your AI coding sessions into knowledge.
Orchestrator 3.0k tok ·