denghongcai/Operon / skills/operon-sdk-protocol
operon-sdk-protocol
VerifiedUse when an agent needs to integrate Operon from application code, the TypeScript SDK, generated gRPC clients, or the documented runtime protocol instead of shelling out to the CLI.
Operon SDK And Protocol
Use the CLI first for operational tasks. Use the TypeScript SDK when writing application code, and use direct gRPC only for custom clients that cannot use the SDK.
Start by reading local protocol and SDK docs:
PROTOCOL.mdfor direct gRPC connection rules.proto/operon/runtime.protofor service and message definitions.packages/sdk-jsfor the TypeScript SDK.
Use CLI help to confirm behavior before mirroring it in code:
operon config explain --help
operon fs read --help
operon exec logs --help
operon exec session --help
operon service forward --help
Integration guidance:
- Read config with the same assumptions as
operon config explain. - Use bearer auth only from configured token sources; do not log token values.
- Prefer streaming APIs for large file reads, file writes, exec stdin, exec logs, and PTY-backed exec sessions.
- Preserve and reuse opaque filesystem
versionvalues when a workflow needs stale-write protection; sendexpected_versionrather than parsing version tokens. - Preserve audit and trace context when running execution graphs.
- Respect pagination fields on list APIs.
- Use
OpenExecSession/ SDKopenExecSessionfor interactive terminal workflows, including explicit resize events when the client owns a TTY; useRunExec/runExecfor non-interactive commands. - Treat service forwarding as an explicit user operation, not an automatic background side effect.
After implementing a client workflow, compare it against equivalent CLI behavior and verify with audit or trace output.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 468k | Updated | Claude CodeCodex | Verified | Install |
| 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: 321k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |
| 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 available | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |