Skip to content

denghongcai/Operon / skills/operon-core

operon-core

Verified

Use when an agent needs to understand what Operon is, inspect config.yaml, choose the right Operon surface, or safely start any Operon task.

Operon Core

Operon is a capability runtime over an already reachable private network. It is not a VPN, relay, mesh router, or global routing layer. Use the CLI as the default agent surface, use the TypeScript SDK for application code, and use the gRPC protocol directly only when a custom client is needed.

Start every task by identifying the config path:

  • Default: $HOME/.operon/config.yaml.
  • Override: operon --config <path> ....

Before operating on nodes, run:

operon --config <path> config explain

Use operon --config <path> --json config explain when a script or agent needs structured daemon, client, auth, policy, service, and secrets information without reading raw YAML.

Use operon <command> --help for exact syntax. Skills explain scenarios and command choice; CLI help is the source of truth for flags and arguments.

Core workflow:

  1. Explain config.
  2. Inspect nodes with operon node list, operon node resolve, or operon node ping.
  3. Inspect allowed capabilities with operon capability list <node>.
  4. Choose the narrowest command family: fs, exec, service, audit, trace, or run.
  5. Confirm destructive or externally visible operations before running them.
  6. Verify mutating work with operon audit show <node> and, for graphs, operon trace show <trace.json>.

Policy is authoritative. Do not bypass denied capabilities, do not infer full trust from network reachability, and do not ask users to expose daemon ports outside their intended private network.

reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 469kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 321kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 321kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 321kUpdated Claude CodeCodexVerifiedInstall