Sf SRE — Development agent for Claude Code
Site Reliability Engineer (SRE) of the Software Factory cell.
How to install Sf SRE
Installs to ~/.claude/agents/kemquiros-anvil-sf-sre.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/Kemquiros/anvil/HEAD/.claude/agents/sf-sre.md -o ~/.claude/agents/kemquiros-anvil-sf-sre.md Restart Claude Code, or start a new session, for it to be picked up.
What Sf SRE does
name: sf-sre description: Site Reliability Engineer (SRE) of the Software Factory cell. Use to set up observability (logs, metrics, traces), define alerts and runbooks, and lead triage during a production incident. tools: Read, Write, Edit, Bash, Grep, Glob, Skill
Role: SRE / Observability
Objective
Make production behavior visible and actionable: know when something is wrong before the user reports it, and have a runbook ready when it happens.
Context to read first
SLO.md
Alternatives in Development
- Incident Response — Orchestrate multi-agent incident response with modern SRE practices for rapid resolution and learnin 31.9k ★
- Product Owner Proxy — Define business intent as user stories with clear acceptance criteria and measurable outcomes 108 ★
- Observability Engineer — OpenTelemetry, distributed tracing, structured logging, metrics specialist — Grafana, Datadog, Prometheus 104 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Agency SRE
Site reliability engineering, observability, and incident response
Sf Tech Lead
Tech Lead of the Software Factory cell. Use to define ALL functional contracts and interfaces a feature will b
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
Vigil
Observability & reliability engineer — SLOs, alerting, instrumentation, incident response. Writes configs and
Sf Code Reviewer
Independent Code Reviewer of the Software Factory cell. Use after a module's implementation and its own tests
Related Skills
Incident Triage Agent
An AI-powered agent built with AWS Bedrock, Claude, and Strands Agents SDK that monitors system alerts, connec
Docs Observability
Open ArchiPy OpenTelemetry guidance (traces, metrics, logs)
Incident
Respond to an outage or write a blameless postmortem — severity, runbooks, action items