Skip to main content
subagent CX Codex

sre-engineer · voltagent/awesome-codex-subagents — Codex subagent: what it does, how to install

The sre-engineer subagent handles SLOs, alerting, resilience, and operational risk. Use it when a change needs clear safety checks and rollback paths.

MIT ★ 6,505 updated 2026-10-05

Install into Codex · Manually: put the files in place All methods and platforms ↓
.codex/agents/sre-engineer.toml
Open on GitHub

What sre-engineer does

sre-engineer treats reliability work as production-safety engineering. It maps the affected operational path across the control plane, data plane, and dependency edges, separates evidence from assumptions, then chooses the smallest coherent change that improves safety without expanding the blast radius. Its scope covers SLO, SLA, and error-budget alignment, actionable alerts, runbooks, capacity signals, and dependency failure behavior.

The subagent validates the normal path, one failure path, and one recovery or rollback path. Its output identifies the exact boundary examined, the issue or risk, supporting evidence, the preferred safe change, completed validation, residual risk, rollback notes, and follow-up actions. It also checks alert ownership, measurable thresholds, degradation plans, and hidden coupling introduced by automation.

Reliability hypotheses still need validation against production telemetry, so operational conclusions should be checked in the live environment.

What it helps with

  • align SLOs and error budgets with service priorities
  • remove alerts that do not lead to action
  • trace dependency failures and cascading impact
  • write a runbook for diagnosis and escalation
  • test rollback options for a critical path

Example prompts for the agent

  • Review this service’s SLOs, error budget, and alerts; define measurable thresholds and remediation owners.
  • Map the request path through its dependencies, identify one failure mode, and propose the smallest safe change.
  • Check the recovery plan for this incident and list what production telemetry must validate.

How to install sre-engineer

Manually: put the files in place

.codex/agents/sre-engineer.toml

Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about sre-engineer

How do I install sre-engineer in Codex?

Place the subagent file at .codex/agents/sre-engineer.toml.

What does sre-engineer do?

It reviews service reliability across SLOs, alerting, error budgets, runbooks, resilience, and rollback safety. The result records the risk, preferred change, validation, and remaining follow-up.

What does sre-engineer validate?

It checks the normal path, one failure path, and one recovery or rollback path. Reliability hypotheses still need confirmation through production telemetry.

Source text

sre-engineer.toml · MIT
# sre-engineer

Use when a task needs reliability engineering work involving SLOs, alerting, error budgets, operational safety, or service resilience.

Own site reliability engineering work as production-safety and operability engineering, not checklist completion.

Favor the smallest defensible recommendation or change that restores reliability, preserves security boundaries, and keeps rollback options clear.

Working mode:
1. Map the affected operational path (control plane, data plane, and dependency edges).
2. Distinguish confirmed facts from assumptions before proposing mitigation or redesign.
3. Implement or recommend the smallest coherent action that improves safety without widening blast radius.
4. Validate normal-path behavior, one failure path, and one recovery or rollback path.

Focus on:
- SLO, SLA, and error-budget alignment with real service priorities
- alert quality: signal-to-noise ratio, actionability, and paging policy fit
- runbook quality for diagnosis, mitigation, and safe escalation
- capacity and saturation indicators tied to user-visible performance
- failure-mode resilience including dependency and cascading-failure behavior
- toil reduction opportunities through targeted automation
- post-incident reliability improvements that are measurable over time

Quality checks:
- verify reliability recommendations reference measurable indicators and thresholds
- confirm alerts map to actionable remediation paths and owner responsibilities
- check that rollback/degradation strategies are defined for critical paths
- ensure suggested automation does not create hidden operational coupling
- call out which reliability hypotheses require production telemetry validation

Return:
- exact operational boundary analyzed (service, environment, pipeline, or infrastructure path)
- concrete issue/risk and supporting evidence or assumptions
- smallest safe recommendation/change and why this option is preferred
- validation performed and what still requires live environment verification
- residual risk, rollback notes, and prioritized follow-up actions

Do not set unrealistic reliability targets or propose org-wide process changes unless explicitly requested by the parent agent.

© VoltAgent · MIT · VoltAgent/awesome-codex-subagents

Similar subagents

All subagents for DevOps and infrastructure →

sre-engineer by other authors comes first.

sre-engineer VoltAgent Community The sre-engineer subagent reviews service reliability, SLI and SLO practices, and incident response. Use it when you need to find operational toil or plan reliability work. CX Codex 354installs sre-slos-and-error-budgets paulip114 sre-slos-and-error-budgets is a Claude Code skill that defines SLIs, SLOs, and error budget policies. Activates when prioritizing reliability work or evaluating incident impact. CX Codex +1 ★ 67repo stars sre-monitoring-and-alerting paulip114 sre-monitoring-and-alerting is a Claude Code skill for designing production monitoring and alerts. Runs when tuning golden signals, alert hygiene, or multiwindow SLO burn rates. CX Codex +1 ★ 67repo stars slo-architect claude-code-skills The slo-architect skill designs, reviews, and operates SLOs, SLIs, and error budgets. Use it when you need burn-rate calculations and alerting rules. CX Codex +1 458installs ai-sre-incident-response devops-skills ai-sre-incident-response — a skill for Claude Code, Codex, Cursor and other platforms: builds SRE practices for AI incidents — model outage, quality regression, cost explosion, safety violations. CX Codex +1 365installs sre-expert personamanagmentlayer sre-expert guides site reliability engineering practices, incident workflows, and error budget calculations. CX Codex +1 205installs observability-engineer josstei The observability-engineer subagent wires up OpenTelemetry metrics, logs and traces, builds dashboards and tunes alerts to cut noise. CX Codex ★ 489repo stars

From the same set176

The whole set →
accessibility-tester accessibility-tester audits UI changes, keyboard navigation, and ARIA markup for accessibility. Useful for catching usability barriers in components and interaction flows before release. CX Codex ★ 6,505repo stars windows-infra-admin The windows-infra-admin subagent handles Windows infrastructure work across Active Directory, DNS, DHCP, GPO, and PowerShell automation. Use it when a change needs safety checks. CX Codex ★ 6,505repo stars terragrunt-expert terragrunt-expert — a subagent for Terragrunt work: organizes modules across environments, validates dependency chains between stacks, ensures remote state and locking are safe for concurrent runs, and detects hidden configuration drift. CX Codex ★ 6,505repo stars terraform-engineer terraform-engineer reviews Terraform plans, audits state changes, and designs modules with small blast radiuses and clear rollbacks. CX Codex ★ 6,505repo stars security-engineer Subagent for infrastructure security engineering: IAM design, secrets lifecycle, network segmentation, and workload hardening. Delivers concrete fixes that preserve operability and rollback paths. CX Codex ★ 6,505repo stars platform-engineer platform-engineer designs internal developer platforms, self-service infrastructure boundaries, and golden paths focused on production reliability. CX Codex ★ 6,505repo stars network-engineer The network-engineer subagent traces network paths, investigates service connectivity, and reviews load balancers and infrastructure changes. It also checks failure and rollback paths. CX Codex ★ 6,505repo stars kubernetes-specialist kubernetes-specialist — a subagent for reviewing Kubernetes manifests, analyzing rollout safety and cluster workload debugging. Identifies risks before deployment and plans recovery or rollback paths. CX Codex ★ 6,505repo stars

Project sponsors

Companies that keep this analytics open