Scherzo Cloud CLI — Productivity skill for Claude Code
Run Claude Code, Codex, Pi, and commands as one durable workflow locally, on-prem, or in the cloud.
How to install Scherzo Cloud CLI
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open scherzo-systems/scherzo-cloud-cli and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Scherzo Cloud CLI does
Run Claude Code, Codex, Pi, and commands as one durable workflow locally, on-prem, or in the cloud.
Alternatives in Productivity
- Performance Optimization Skill — Systematic performance analysis and optimization for RTK CLI tool, focusing on startup time (<10ms), memory us 11.9k ★
- Agentlas Cloud — Staff a task only from the signed-in owner's Agent Cloud agents 1.1k ★
- Chief — CLI that wraps Claude Code in a loop 396 ★
README
Scherzo Cloud CLI
Scherzo Cloud CLI turns repeatable engineering work into explicit, durable workflows. Define commands and coding agents in one repository-owned YAML file, connect typed outputs to downstream steps, run independent work concurrently, and retain a result you can inspect instead of reconstructing what happened from terminal scrollback.
The CLI is the open-source command-line and runner executable for Scherzo Cloud. It can run workflows locally with Pi, Claude Code, and Codex, or serve them from an enrolled outbound runner. The project is early, but the local workflow engine and its authoring, execution, and inspection tools are available today.
Why Scherzo
Coding-agent automation often begins as a loose sequence of shell commands, prompts, and copy-and-paste handoffs. That approach becomes difficult to repeat, supervise, and recover once work spans several tools or agents. Scherzo gives the work a runtime:
- One graph for commands and agents. Express control flow and typed data flow in a workflow dependency graph instead of coordinating scripts and model sessions by hand.
- Parallel work with explicit handoffs. Let independent steps run concurrently, pass text, schema-validated JSON, and files to downstream work, and export Git branch results when a workflow changes a repository.
- Durable execution. Follow progress in the terminal, inspect retained runs later, recover bounded step failures, and retry eligible runs explicitly.
- Repository-owned automation. Version workflows, prompts, attachments, and result schemas beside the code they operate on.
- Validate before you spend. Resolve the complete workflow bundle and check its graph, references, types, files, and policy offline before starting commands or consuming model tokens.
What you can build
Use Scherzo to:
- run tests, linters, builds, and several independent code reviews in parallel, then combine their findings in one final artifact/PR;
- h
Related Skills
Open Axis
Local control plane that routes engineering tasks across Claude Code, OpenCode, and Codex with real fallback,
Heddlework
A native, harness-neutral workspace for agent sessions, task graphs, diffs, and durable work — Pi first, Codex
Agentface32
Animated ESP32 desk display for Claude Code and Codex. Multi-agent status, expressive faces, task timers, hook
Local Scheduler
Schedule a Claude Code command locally via launchd (Mac) or Task Scheduler (Windows). For remote agents, use t
Thingiverse Web Skill
Add your Thingiverse stats to your own website and keep them updated on a schedule by your coding agent — desi
Agent CLI Runtime
Unified TypeScript runtime for Codex CLI, Claude Code, and OpenCode with typed events, lifecycle control, perm
Related Agents
Tosca Automation Engineer
Use for end-to-end Tricentis Tosca test automation on either Tosca Commander (on-prem / Server) or Tosca Cloud
Bench Runner
Executes a11y skill benchmarks across hosted and local model families. Runs cloud/Codex/Ollama benchmark scrip
Go Expert
Use this agent when you need to write, refactor, analyze, or optimize any Go code. This includes creating new