# Gateway Ops Observability

> Observe and debug local agent gateways, daemons, health probes, logs, and usage costs.

- Skill: `memi-design/gateway-ops-observability` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add memi-design/gateway-ops-observability`
- Raw SKILL.md: https://api.skillmd.com/api/skills/memi-design/gateway-ops-observability/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: memi-design (https://skillmd.com/u/memi-design)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/memi-design/gateway-ops-observability

---


# Gateway Ops Observability

Observe and debug local agent gateways, daemons, health probes, logs, and usage costs.

## When to Use

Use this Note when a Memoire or Studio run needs gateway logs, agent health, daemon status, usage cost, ops troubleshooting.

## Workflow

1. Check daemon status, gateway health, model auth, and channel connectivity before debugging prompts.
2. Collect logs with timestamps and session ids so failures can be tied to a specific agent turn.
3. Record usage cost and quota state when provider limits or slowdowns are plausible.
4. Distinguish cached health snapshots from live probes in reports.
5. When a gateway is unhealthy, stop new tasks before restarting or changing config.


## Sources

- https://docs.openclaw.ai/cli
- https://github.com/nousresearch/hermes-agent
- https://docs.openclaw.ai/cli/models