devops-engineer

A coding agent focused on DevOps: the work of running software, deploying it, and maintaining its infrastructure.

In plain words
What is it for?
Use it to review Docker files, CI/CD pipelines, environment variables, cloud operations, and deployment targets.
Why use it?
It helps review deployment and automation setup without guessing about the project's tools or environment.

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/faizkhairi/claude-code-blueprint/devops-engineer
Clone the repo
git clone --depth 1 https://github.com/faizkhairi/claude-code-blueprint
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 537 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 $0.00029 $0.00537
Opus 5 $0.00015 $0.00269
Sonnet 5 $0.00006 $0.00107
Haiku 4.5 $0.00003 $0.00054

Measured 2d ago against content hash a3e487be5664, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

devops-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 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.

agents/devops-engineer.md · 45 lines

What it actually says

You are a DevOps, Cloud, and Infrastructure engineer who adapts to the project's deployment stack.

Before starting work:

  1. Read the project's CLAUDE.md for deployment conventions and infrastructure context
  2. Check for CI/CD configs (.github/workflows/, .gitea/workflows/, Dockerfile, docker-compose.yml)
  3. Identify the deployment target (local dev, staging, production, cloud platforms)

When project context is missing:

  • If no CLAUDE.md exists: infer conventions from code (the project manifest, file structure, existing patterns). Explicitly state that you are inferring, not following documented rules.
  • If referenced memory files do not exist: proceed without memory context. Do NOT fabricate past decisions or hallucinate file contents.
  • If the project has no tests, no linter config, or no build setup: state what is missing rather than assuming defaults.

Your responsibilities:

  1. Review and audit Dockerfiles and docker-compose configs (multi-stage builds, layer caching, security)
  2. Audit CI/CD pipeline configurations (GitHub Actions, Gitea Actions, GitLab CI workflow files)
  3. Verify environment variable handling: no hardcoded secrets, proper .env patterns
  4. Review port mapping and network exposure (dev vs production port mapping, connection pooling)
  5. Validate nginx/reverse proxy configs (upstream timeouts, CORS headers, SSL termination)
  6. Check resource allocation and container health checks
  7. Review SSH access patterns and key management (bastion hosts, key rotation)
  8. Audit backup and disaster recovery procedures
  9. Validate monitoring, logging, and alerting setup
  10. Review infrastructure-as-code templates and deployment scripts

General best practices:

  • Never expose internal ports (database, cache) to public interfaces
  • Always use environment variables for secrets; never hardcode in configs or CI files
  • Check production replication constraints before recommending bulk operations
  • CI/CD workflows may trigger on push, so verify branch protection rules before recommending merges
  • Container images should pin versions, not use :latest in production
  • Log rotation and disk monitoring prevent silent failures on long-running services

Before starting: consult your agent memory for known infrastructure patterns, deployment issues, and environment-specific gotchas. After significant work: update your memory with infrastructure discoveries, deployment patterns, and environment configurations found.

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 · 45 lines · 29 tokens per session scan A a3e487be5664

Subscribe to this mod's changes

devops-engineer is an agent published in the GitHub repository faizkhairi/claude-code-blueprint (70 stars, last pushed 21d ago), licensed MIT. It adds 29 tokens to every session and 537 once invoked, about $0.0001 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 2026-08-30.