devops-guard

An infrastructure safety guide for CI/CD pipelines, Docker containers, Terraform configuration, Kubernetes, and deployment files. It requires a written, approved plan before infrastructure changes.

In plain words
What is it for?
Use it when reviewing or changing GitHub Actions, GitLab CI, Kubernetes manifests, Helm charts, Docker Compose files, Terraform, or deployment scripts.
Why use it?
It helps prevent accidental production changes, destructive commands, exposed secrets, unsafe container settings, and unpinned software versions.

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/mtvrkan/senior-dev-kit/devops-guard
Clone the repo
git clone --depth 1 https://github.com/mtvrkan/senior-dev-kit
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 1,026 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 $0.00059 $0.01026
Opus 5 $0.00030 $0.00513
Sonnet 5 $0.00012 $0.00205
Haiku 4.5 $0.00006 $0.00103

Measured 2d ago against content hash 6fd3c50c26d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

devops-guard 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-guard.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reference docs (lazy-load when needed)

agent_docs/dep-check-guide.md — library/framework preference table, alternatives table, audit commands by runtime (for dependency CVE review before a release, via the security-scan skill) agent_docs/env-audit-guide.md — grep commands by language, .env.example format (for environment variable audits) agent_docs/devops-security-guide.md — rollback strategies by change type (Dockerfile/Actions/IaC/SBOM detail lives in rules/600-devops.md, which auto-loads when you read any Dockerfile/CI/IaC file)


HARD CONSTRAINTS — read first, apply always

Never execute infrastructure changes without an explicit written plan approved by the user. Never generate Terraform apply, kubectl apply, or deployment commands without showing the plan first. Never add long-lived cloud credentials to any CI/CD system — always use OIDC/Workload Identity. Never trust a mutable container tag (:latest, :main) — always pin to digest or specific version. Never store secrets in environment variables committed to code — always use secret manager references. Never write a Dockerfile that runs as root in the final stage. Never pin GitHub Actions with version tags — always use full commit SHA.

If the user's request would violate any constraint above: stop, explain why, propose a safe alternative.


Core principles

Immutable infrastructure over mutable configuration. Infrastructure drift is invisible until it causes an outage. Everything that exists should be declarative, versioned, and reproducible from code. If you can SSH in and change it manually, it will drift. Design so that changes flow through CI/CD only.

Read the full file on GitHub · 90 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 · 90 lines · 0 tokens per session scan A 6fd3c50c26d9

Subscribe to this mod's changes

devops-guard is an agent published in the GitHub repository mtvrkan/senior-dev-kit (5 stars, last pushed 12d ago), licensed MIT. It adds 59 tokens to every session and 1,026 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 2026-08-31.