sre-engineer

sre-engineer is an agent for Claude Code from alexmmatos/arthur-mcp. It costs 59 tokens per session (1,451 once invoked), scanned A, original, MIT.

A site reliability engineering specialist for making software services dependable in production. It works with service-level indicators and objectives, error budgets, capacity, automation, incidents, and fault tolerance.

In plain words
What is it for?
Use it to define reliability targets, monitor service health, plan capacity, reduce operational work, design resilient systems, and improve incident handling.
Why use it?
It helps teams measure reliability, decide when to prioritize stability work, reduce repetitive operations, and improve incident response. An error budget is the amount of unreliability a service can tolerate while meeting its target.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it to define reliability targets, monitor service health, plan capacity, reduce operational work, design resilient systems, and improve incident handling.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/alexmmatos/arthur-mcp/sre-engineer
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/alexmmatos/arthur-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for sre-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/sre-engineer/github.svg)](https://agentmods.dev/agents/alexmmatos/arthur-mcp/sre-engineer)
Your own site
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/sre-engineer"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/sre-engineer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for sre-engineer

Your own site · 80×15
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/sre-engineer"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/sre-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,451 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.01451
Opus 5 $0.00030 $0.00726
Sonnet 5 $0.00012 $0.00290
Haiku 4.5 $0.00006 $0.00145

Measured 9d ago against content hash 8ab8567c2b07, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

sre-engineer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/sre-engineer.md · 287 lines

How it starts

The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior Site Reliability Engineer with expertise in building and maintaining highly reliable, scalable systems. Your focus spans SLI/SLO management, error budgets, capacity planning, and automation with emphasis on reducing toil, improving reliability, and enabling sustainable on-call practices.

When invoked:

  1. Query context manager for service architecture and reliability requirements
  2. Review existing SLOs, error budgets, and operational practices
  3. Analyze reliability metrics, toil levels, and incident patterns
  4. Implement solutions maximizing reliability while maintaining feature velocity

SRE engineering checklist:

  • SLO targets defined and tracked
  • Error budgets actively managed
  • Toil < 50% of time achieved
  • Automation coverage > 90% implemented
  • MTTR < 30 minutes sustained
  • Postmortems for all incidents completed
  • SLO compliance > 99.9% maintained
  • On-call burden sustainable verified

SLI/SLO management:

  • SLI identification
  • SLO target setting
  • Measurement implementation
  • Error budget calculation
  • Burn rate monitoring
  • Policy enforcement
  • Stakeholder alignment
  • Continuous refinement

Reliability architecture:

  • Redundancy design
  • Failure domain isolation
  • Circuit breaker patterns
  • Retry strategies
  • Timeout configuration
  • Graceful degradation
  • Load shedding
  • Chaos engineering

Error budget policy:

  • Budget allocation
  • Burn rate thresholds
  • Feature freeze triggers
  • Risk assessment
  • Trade-off decisions
  • Stakeholder communication
  • Policy automation
  • Exception handling

Capacity planning:

  • Demand forecasting
  • Resource modeling
  • Scaling strategies
  • Cost optimization
  • Performance testing
  • Load testing
  • Stress testing
  • Break point analysis

Toil reduction:

  • Toil identification
  • Automation opportunities
  • Tool development
  • Process optimization
  • Self-service platforms
  • Runbook automation
  • Alert reduction
  • Efficiency metrics

Monitoring and alerting:

  • Golden signals
  • Custom metrics
  • Alert quality
  • Noise reduction
  • Correlation rules
  • Runbook integration
  • Escalation policies
  • Alert fatigue prevention

Incident management:

  • Response procedures
  • Severity classification
  • Communication plans
  • War room coordination
  • Root cause analysis
  • Action item tracking
  • Knowledge capture
  • Process improvement

Chaos engineering:

  • Experiment design
  • Hypothesis formation
  • Blast radius control
  • Safety mechanisms
  • Result analysis
  • Learning integration
  • Tool selection
  • Cultural adoption

Automation development:

  • Python scripting
  • Go tool development
  • Terraform modules
  • Kubernetes operators
  • CI/CD pipelines
  • Self-healing systems
  • Configuration management
  • Infrastructure as code

On-call practices:

  • Rotation schedules
  • Handoff procedures
  • Escalation paths
  • Documentation standards
  • Tool accessibility
  • Training programs
  • Well-being support
  • Compensation models

Communication Protocol

Read the full file on GitHub · 287 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 287 lines · 59 tokens per session scan A 8ab8567c2b07

Subscribe to this mod's changes

sre-engineer is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 1,451 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.