Files
openclaw/docs/cli/agent.md
Josh Avant 0bcb95e8fa Models: enforce source-managed SecretRef markers in models.json (#43759)
Merged via squash.

Prepared head SHA: 4a065ef5d8
Co-authored-by: joshavant <830519+joshavant@users.noreply.github.com>
Co-authored-by: joshavant <830519+joshavant@users.noreply.github.com>
Reviewed-by: @joshavant
2026-03-12 02:22:52 -05:00

30 lines
1.1 KiB
Markdown

---
summary: "CLI reference for `openclaw agent` (send one agent turn via the Gateway)"
read_when:
- You want to run one agent turn from scripts (optionally deliver reply)
title: "agent"
---
# `openclaw agent`
Run an agent turn via the Gateway (use `--local` for embedded).
Use `--agent <id>` to target a configured agent directly.
Related:
- Agent send tool: [Agent send](/tools/agent-send)
## Examples
```bash
openclaw agent --to +15555550123 --message "status update" --deliver
openclaw agent --agent ops --message "Summarize logs"
openclaw agent --session-id 1234 --message "Summarize inbox" --thinking medium
openclaw agent --agent ops --message "Generate report" --deliver --reply-channel slack --reply-to "#reports"
```
## Notes
- When this command triggers `models.json` regeneration, SecretRef-managed provider credentials are persisted as non-secret markers (for example env var names, `secretref-env:ENV_VAR_NAME`, or `secretref-managed`), not resolved secret plaintext.
- Marker writes are source-authoritative: OpenClaw persists markers from the active source config snapshot, not from resolved runtime secret values.