Agentrunpod cli
Skill SebastianBoehler/agent-cli-utils/skills/agentrunpod-cli
CLI utilities for AI agents - fast Go replacements for common Python tools
npx -y skills add SebastianBoehler/agent-cli-utils --skill agentrunpod-cliAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Use the local `agentrunpod` CLI to submit, inspect, and cancel RunPod serverless jobs with structured output. Prefer it when an agent needs an env-configurable wrapper around the RunPod HTTP API instead of ad hoc curl commands.
SKILL.md
1.4 KB, 290 tokens by cl100k_base, as published. Nobody here has run it
AgentRunPod CLI
Use agentrunpod when a workflow needs a small deterministic wrapper around RunPod endpoint execution.
Invoke the Tool
Prefer the installed binary when it exists:
agentrunpod submit -endpoint "$RUNPOD_ENDPOINT_ID" -input payload.json
If working inside this repository or the binary is not installed, run:
go run ./cmd/agentrunpod -- submit -endpoint "$RUNPOD_ENDPOINT_ID" -input payload.json
Choose Flags
- Use
submitfor new jobs. - Use
-syncto hit RunPod's synchronousrunsyncpath. - Use
-inputor-payloadto pass JSON or YAML input. - Use
-raw-bodyonly when the payload already contains the full RunPod request body. - Use
status,result, orcancelwith-request. - Set
RUNPOD_API_KEY,RUNPOD_ENDPOINT_ID, and optionallyRUNPOD_BASE_URLthrough the environment when possible. - Prefer
-format jsonor-format yamlfor downstream agent parsing.
Examples
Submit a job:
go run ./cmd/agentrunpod -- submit -payload '{"prompt":"hello"}'
Fetch job status:
go run ./cmd/agentrunpod -- status -request "$JOB_ID"
What ships with it: 1 file
219 B alongside SKILL.md
agents/
- openai.yaml219 B