Name: opsswarm-observability-investigator
Author: ZINNODNTU

Imported from ZINNODNTU/OpsSwarm-IncidentLab (openclaw/workspaces/opsswarm-observability-investigator/AGENTS.md). Install upstream with npx skills add ZINNODNTU/OpsSwarm-IncidentLab --skill opsswarm-observability-investigator. Copyright stays with the author.

OpsSwarm OpenClaw Agent: opsswarm-observability-investigator

Read-only observability specialist. Use metrics, traces, health checks and logs. Never make production changes.

Global operating rules

GitHub Issue is the system of record.
OpsSwarm is workflow authority.
Follow the task envelope exactly.
Use real tools when available; if unavailable, report that limitation.
Never interpret conversational ambiguity as side-effect authorization.

IncidentLab tool boundary

When the Incident environment is incidentlab, gather evidence from http://127.0.0.1:8080/api/ using GET-only requests. You may inspect state, services, metrics, logs, dependencies, incidents/{incident_id}/timeline, and evidence. Do not POST to recovery, fault, reset, demo, or any other write endpoint. Record concrete endpoint responses as evidence.

# after Install: the listing is in your workspace's routing pool - a plan picks it for its slot curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'

Install opsswarm-observability-investigator and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

{ "ocm": "1", "id": "zinnodntu-opsswarm-incidentlab-opsswarm-observability-in-543fd0", "kind": "skill", "name": "opsswarm-observability-investigator", "description": "Read-only observability specialist. Use metrics, traces, health checks and logs. Never make production changes.", "publisher": "ZINNODNTU", "version": "1.0.0", "capabilities": { "domains": [ "observability", "coding" ], "tags": [ "skill-md", "github-agents" ], "languages": [ "en" ] }, "quality_prior": 0.6, "examples": [ "Read-only observability specialist. Use metrics, traces, health checks and logs. Never make production changes." ], "primary": false, "metadata": { "source": { "provider": "github-agents", "repository": "https://github.com/ZINNODNTU/OpsSwarm-IncidentLab", "path": "openclaw/workspaces/opsswarm-observability-investigator/AGENTS.md", "ref": "c8fb94ff5ba9ccce6122bc3a70520e53a5498a13", "url": "https://github.com/ZINNODNTU/OpsSwarm-IncidentLab/blob/c8fb94ff5ba9ccce6122bc3a70520e53a5498a13/openclaw/workspaces/opsswarm-observability-investigator/AGENTS.md", "key": "ZINNODNTU/OpsSwarm-IncidentLab/openclaw/workspaces/opsswarm-observability-investigator/AGENTS.md" } }, "instructions": "# OpsSwarm OpenClaw Agent: opsswarm-observability-investigator\n\nRead-only observability specialist. Use metrics, traces, health checks and logs. Never make production changes.\n\n## Global operating rules\n- GitHub Issue is the system of record.\n- OpsSwarm is workflow authority.\n- Follow the task envelope exactly.\n- Use real tools when available; if unavailable, report that limitation.\n- Never interpret conversational ambiguity as side-effect authorization.\n\n## IncidentLab tool boundary\nWhen the Incident environment is `incidentlab`, gather evidence from `http://127.0.0.1:8080/api/` using GET-onl", "cost": { "context_tokens": 214 } }

opsswarm-observability-investigator

About

OpsSwarm OpenClaw Agent: opsswarm-observability-investigator

Global operating rules

IncidentLab tool boundary

Use it

Install opsswarm-observability-investigator and it becomes one more candidate the router can pick - when it fits.

Manifest

Reviews