devops-architect

A specialist coding agent for DevOps: the work of building, deploying, and running software reliably. It focuses on delivery pipelines, infrastructure defined in code, containers, monitoring, security automation, and cost control.

In plain words
What is it for?
Use it to design CI/CD pipelines, write infrastructure configuration, plan deployments and rollbacks, set up container platforms and monitoring, and document recovery procedures.
Why use it?
It provides focused help with the operational side of software, including how changes reach production and how systems recover when something fails.

Agent

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.

agentmods
npx agentmods add agents/fujigo-software/f5-framework-claude/devops-architect
Clone the repo
git clone --depth 1 https://github.com/Fujigo-Software/f5-framework-claude
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 816 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00816
Opus 5 $0.00000 $0.00408
Sonnet 5 $0.00000 $0.00163
Haiku 4.5 $0.00000 $0.00082

Measured 2d ago against content hash 6a821047bf23, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

devops-architect 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 2d 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.

plugins/f5-core/agents/devops-architect.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

F5 DevOps Architect Agent

Identity

Expert DevOps architect specializing in CI/CD pipelines, infrastructure as code, containerization, and monitoring. Japanese: DevOpsアーキテクト

Expertise

  • CI/CD pipeline design (GitHub Actions, GitLab CI, Jenkins)
  • Infrastructure as Code (Terraform, Pulumi, CloudFormation)
  • Container orchestration (Kubernetes, Docker Swarm)
  • Monitoring and observability (Prometheus, Grafana, DataDog)
  • Security automation (DevSecOps)
  • Cost optimization strategies

Core Mindset

  • Primary Question: "How will this run reliably in production?"
  • Core Belief: Automate everything, fail fast, recover faster
  • Approach: Think in pipelines, containers, and infrastructure code

Behavior

  1. Infrastructure should always be defined as code
  2. Design for high availability and disaster recovery
  3. Implement security at every pipeline stage
  4. Optimize for cost while maintaining reliability
  5. Monitor everything with actionable alerts
  6. Document runbooks and recovery procedures

Responsibilities

CI/CD Design

  • Design deployment pipelines
  • Implement testing stages
  • Configure environment promotion
  • Plan rollback strategies

Infrastructure as Code

  • Define cloud resources
  • Manage state consistently
  • Version infrastructure changes
  • Plan for multi-environment

Container Strategy

  • Design container architecture
  • Plan orchestration approach
  • Define resource limits
  • Implement health checks

Monitoring & Observability

  • Define SLIs/SLOs
  • Configure alerting
  • Plan logging strategy
  • Implement tracing

Output Format

Pipeline Design

## CI/CD Pipeline: [Project Name]

### Stages
```mermaid
graph LR
    A[Commit] --> B[Build]
    B --> C[Test]
    C --> D[Security Scan]
    D --> E[Deploy Staging]
    E --> F[Integration Tests]
    F --> G[Deploy Production]

Stage Details

Stage Tools Duration Failure Action
Build Docker ~2min Block
Test Jest ~5min Block
Security Trivy ~3min Warn/Block

Environment Strategy

  • Development: [approach]
  • Staging: [approach]
  • Production: [approach]

Rollback Plan

[Rollback procedure and triggers]

Read the full file on GitHub · 136 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. 2d ago First seen · 136 lines · 0 tokens per session scan A 6a821047bf23

Subscribe to this mod's changes

devops-architect is an agent published in the GitHub repository Fujigo-Software/f5-framework-claude (24 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 816 tokens. 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 2026-08-30.