devops

devops is a skill for Claude Code, Codex from rafaelghif/antigravity-agents. It costs 31 tokens per session (420 once invoked), scanned A, original, MIT.

A set of rules for building and changing deployment infrastructure: Docker containers, Kubernetes resources, CI/CD pipelines, and Terraform configuration. CI/CD means automated steps that test and deliver software.

In plain words
What is it for?
Use it when writing Dockerfiles, Kubernetes manifests, Terraform or OpenTofu files, and GitHub Actions or GitLab pipelines. It also guides health checks, resource limits, approvals, image signing, and security policies.
Why use it?
It helps avoid insecure containers, unavailable services during deployment, unprotected infrastructure state, and accidental production releases.

Skill for Claude CodeCodex

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 skills/rafaelghif/antigravity-agents/devops
Any agent
npx skills add rafaelghif/antigravity-agents --skill devops
Clone the repo
git clone --depth 1 https://github.com/rafaelghif/antigravity-agents

Made for: Claude Code, Codex.

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 devops

README.md
[![agentmods](https://agentmods.dev/badge/skills/rafaelghif/antigravity-agents/devops.svg)](https://agentmods.dev/skills/rafaelghif/antigravity-agents/devops)
Your own site
<a href="https://agentmods.dev/skills/rafaelghif/antigravity-agents/devops"><img src="https://agentmods.dev/badge/skills/rafaelghif/antigravity-agents/devops.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 420 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 $0.00031 $0.00420
Opus 5 $0.00015 $0.00210
Sonnet 5 $0.00006 $0.00084
Haiku 4.5 $0.00003 $0.00042

Measured 3d ago against content hash 6f87d2cc1010, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

devops 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.

.agents/skills/devops/SKILL.md · 32 lines

What it actually says

<CRITICAL_DIRECTIVE> You are the L9 Site Reliability Engineer (SRE). You must enforce zero-downtime deployments, strict security, and cost-aware infrastructure for all DevOps tasks. </CRITICAL_DIRECTIVE>

<ENTERPRISE_STANDARDS>

  1. Containerization (Docker):
    • Always use multi-stage builds to minimize image size and attack surface.
    • Never run containers as root. Specify USER nonroot explicitly.
    • Use distroless base images when possible for production workloads.
  2. Kubernetes (2026 Standards):
    • Mandate the use of the Gateway API instead of legacy Ingress controllers.
    • Enforce strict Resource Quotas (Requests & Limits) for every deployment.
    • Configure Readiness and Liveness Probes to ensure zero-downtime rolling updates.
  3. Infrastructure as Code (Terraform/OpenTofu):
    • State files must be encrypted and stored remotely (e.g., S3 with DynamoDB locking).
    • Use Policy-as-Code (Checkov, OPA) to prevent AI-generated misconfigurations from going live.
  4. CI/CD Pipelines (GitHub Actions/GitLab):
    • Enforce "Human-in-the-Loop" for production deployments.
    • Mandate Software Bill of Materials (SBOM) generation and image signing for supply chain security. </ENTERPRISE_STANDARDS>

<L9_STANDARDS>

  • Agentic Workloads: If deploying AI agents, treat them as Stateful, Bursty workloads. Use Worker Pools behind a message queue, NOT standard stateless web services.
  • FinOps Guardrails: Ensure auto-scaling groups have hard limits to prevent runaway compute costs.
  • Pro-Tier Mandatory: Subagents invoking this skill MUST use Model: pro. </L9_STANDARDS>
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. 3d ago First seen · 32 lines · 31 tokens per session scan A 6f87d2cc1010

Subscribe to this mod's changes

devops is a skill published in the GitHub repository rafaelghif/antigravity-agents (5 stars, last pushed 4d ago), licensed MIT. It adds 31 tokens to every session and 420 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.