Vigil — Development agent for Claude Code
Observability & reliability engineer — SLOs, alerting, instrumentation, incident response.
How to install Vigil
Installs to ~/.claude/agents/tonone-ai-tonone-core-vigil.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/tonone-ai/tonone-core/HEAD/agents/vigil.md -o ~/.claude/agents/tonone-ai-tonone-core-vigil.md Restart Claude Code, or start a new session, for it to be picked up.
What Vigil does
name: vigil description: Observability & reliability engineer — SLOs, alerting, instrumentation, incident response. Writes configs and runbooks, doesn't produce roadmaps. model: sonnet
You are Vigil — observability and reliability engineer on the Engineering Team. Write instrumentation configs, alert rules, and runbooks. Do not produce observability roadmaps or 6-month plans.
Communication
Respond terse. All technical substance stays — only filler dies. Follow output-kit protocol:
Alternatives in Development
- Incident Runbook Templates — Production-ready templates for incident response runbooks covering detection, triage, mitigation, re 31.9k ★
- Lessons Learned — In this document we briefly collect what we have learned while developing and using Serena, what works well an 21.9k ★
- Instrumentation Reviewer 108 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
A13 Observability
A13 OBS — Owns SLOs, dashboards, alerting and incident declaration. Use to define SLOs for a service, compute
Sf SRE
Site Reliability Engineer (SRE) of the Software Factory cell. Use to set up observability (logs, metrics, trac
Agency SRE
Site reliability engineering, observability, and incident response
Engineering SRE
Expert site reliability engineer specializing in SLOs, error budgets, observability, chaos engineering, and to
Ops Site Reliability Engineer
Site reliability engineer who monitors system health, manages alerts, and handles incident response. Use this
Production Observability Auditor
Audits codebase for observability gaps — structured logging, request tracing, health endpoints, metrics, and a
Related Skills
Datadog
Set up and troubleshoot Datadog — Agent deployment on Kubernetes, APM instrumentation, Log Management, Monitor
DevOps Engineering
Routes DevOps and platform-engineering questions to specialist reference sheets (CI/CD, deployment, IaC, conta
Incident
Respond to an outage or write a blameless postmortem — severity, runbooks, action items