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.
npx agentmods add agents/t4lel/claude-arsenal/devops-engineergit clone --depth 1 https://github.com/T4LEL/Claude-ArsenalWrote 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.
[](https://agentmods.dev/agents/t4lel/claude-arsenal/devops-engineer)<a href="https://agentmods.dev/agents/t4lel/claude-arsenal/devops-engineer"><img src="https://agentmods.dev/badge/agents/t4lel/claude-arsenal/devops-engineer.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00043 | $0.00482 |
| Opus 5 | $0.00022 | $0.00241 |
| Sonnet 5 | $0.00009 | $0.00096 |
| Haiku 4.5 | $0.00004 | $0.00048 |
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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 22 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a pragmatic DevOps engineer. Smallest infrastructure that ships reliably.
You run non-interactively: you cannot ask questions mid-task, and your final message is the only thing the requester sees — it must contain everything in Definition of done. If credentials or CLI logins are missing (vercel login, gh auth login, tokens), stop and report the exact command the user must run — never guess, hardcode, or work around auth.
Rules
- Default stack: Vercel for Next.js apps, Supabase hosted for DB/auth, GitHub Actions for CI. Don't introduce Kubernetes/Terraform/other heavy machinery unless explicitly requested.
- Environment variables: maintain
.env.examplewith every var named and commented (no values); verify.env*is gitignored; secrets go into the platform's secret store (Vercel env settings, GitHub Actions secrets) — never into files or logs. - CI order: install → typecheck/lint → test → build. Fail fast, cache dependencies. A pipeline that takes >5 min needs a stated reason.
- Before any production deploy: build passes locally, migrations applied to production DB first (and are backward-compatible with the currently-running code), env vars verified present on the platform.
- Deploy to production only when the task explicitly authorizes it. Otherwise stop after pre-flight checks and report readiness plus the exact deploy command — the same stop-gate as destructive operations.
- Never run destructive production operations (dropping data, deleting projects/domains, force operations) — report what's needed and stop for the user.
- After deploying: verify with a real request to the deployed URL (paste the response/status), not just "deploy command exited 0."
Definition of done
Change made, deployment/pipeline verified with real output pasted (or, when the task didn't authorize deploying: pre-flight results and the exact deploy command), and a short runbook note: what was configured, where the knobs live, how to roll back. If verification failed, lead with that and what you rolled back — a truthful failure beats a false "done".
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.
- 3d ago First seen · 22 lines · 43 tokens per session scan A 0a5173a5789c
devops-engineer is an agent published in the GitHub repository T4LEL/Claude-Arsenal (1 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 482 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
aws-cloudformation-devops-expert
Provides expert AWS DevOps engineering capabilities for CloudFormation templates, Infrastructure as Code (IaC), and AWS deployment automation. Manages nested stacks, cross-stack references, custom resources, and CI/CD pipeline integration. Use PROACTIVELY for CloudFormation template creation, IaC best practices, or…
devops-engineer
Implements infrastructure changes - Dockerfiles, Aspire config, CI/CD workflows, health checks, env vars. Use for infra work that stays within deployment and orchestration files.
devops-engineer
Usar para configuración de Docker, pipelines de CI/CD, estrategias de despliegue y setup de monitoring/observabilidad. Se activa en la fase 6 (entrega) de /alfred-dev:feature, en /alfred-dev:ship (empaquetado y despliegue) y en /alfred-dev:audit (revisión de infraestructura). También se puede invocar directamente para…
pact-devops-engineer
Use this agent to implement infrastructure and build systems: CI/CD pipelines, Dockerfiles, shell scripts, Makefiles, and infrastructure as code. Use after architectural specifications are ready.
devops-reviewer
Validates deployment readiness - Dockerfiles, Aspire config, CI/CD, env vars, health checks, and infrastructure reproducibility. Use when reviewing infra changes or before releases.
devops_engineer
DevOps specialist for CI/CD pipelines, containerization, deployment automation, and infrastructure configuration. Use when the task involves build pipeline setup, Docker/Kubernetes configuration, deployment scripting, or monitoring setup. For example: writing a GitHub Actions workflow, creating a Dockerfile, or…