devops-warden

devops-warden is a skill for Claude Code, Codex from caravanglory/magehub. It costs 59 tokens per session (7,128 once invoked), scanned C, original, MIT.

A set of instructions for running Magento 2 development and maintenance commands inside Warden, a Docker-based local environment manager.

In plain words
What is it for?
Use it when working on Magento projects with Warden, including service checks, Magento commands, dependency work, cache or search operations, queues, and file synchronization.
Why use it?
It helps ensure PHP, Composer, Magento, database, cache, search, and queue commands run in the correct environment. It also guides safer checks before operational changes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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/caravanglory/magehub/devops-warden
Any agent
npx skills add caravanglory/magehub --skill devops-warden
Clone the repo
git clone --depth 1 https://github.com/caravanglory/magehub

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-warden

README.md
[![agentmods](https://agentmods.dev/badge/skills/caravanglory/magehub/devops-warden.svg)](https://agentmods.dev/skills/caravanglory/magehub/devops-warden)
Your own site
<a href="https://agentmods.dev/skills/caravanglory/magehub/devops-warden"><img src="https://agentmods.dev/badge/skills/caravanglory/magehub/devops-warden.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,128 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 5.1 $0.00059 $0.07128
Opus 5 $0.00030 $0.03564
Sonnet 5 $0.00012 $0.01426
Haiku 4.5 $0.00006 $0.00713

Measured 6d ago against content hash aec6658ef559, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

devops-warden scanned grade C with 2 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 6d ago.

The scan reads SKILL.md. This mod also ships 9 executable files (examples/db-import.sh, examples/env-lifecycle.sh, examples/file-sync.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

`warden env exec -T opensearch curl -s localhost:9200/_cluster/health | python3 -m json.tool`

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

`warden env exec -T opensearch curl -s localhost:9200/_cluster/health | python3 -m json.tool`
skills/devops/devops-warden/SKILL.md · 685 lines

How it starts

The opening of the file, as written. The whole thing — 685 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Warden Local Environment

Activation

Use When
  • The task needs Magento CLI, Composer, PHP, database, cache, search, queue, or filesystem-sync work inside a Warden-managed local environment.
  • The user mentions warden, Docker local stack, Redis/Valkey, Varnish, OpenSearch/Elasticsearch, RabbitMQ, Mutagen, or n98-magerun2.
Do Not Use When
  • The project uses DDEV, docker compose, Kubernetes, Adobe Cloud tooling, or another wrapper and no Warden files or commands are present.
  • The request is purely code editing and does not require running Magento/runtime commands.
Required Inputs
  • Project root containing the Warden .env file and the specific service or Magento command to operate.
  • Whether the operation is read-only, cache-clearing, data-changing, or destructive.

Workflow

  1. Start with read-only environment discovery from the project root: git status, Warden env name, service status, and relevant logs.
  2. Run PHP, Composer, bin/magento, and n98-magerun2 only through warden shell or the project wrapper.
  3. Prefer targeted service operations over broad restarts or full cache/storage resets.
  4. After any operational change, run the smallest command that proves the service or Magento state recovered.

Guardrails

  • Never run project PHP, Composer, or bin/magento directly on the host when a Warden environment is in use.
  • Ask before running warden env down -v, deleting search indices, purging RabbitMQ queues, flushing Redis/Valkey, or importing a database. (approval required)
  • Do not run destructive or data-changing commands against production or shared staging environments. (approval required)

Verification

  • For shell/Magento work, report the exact warden shell command or wrapper used and the command exit result.
  • For cache/search/queue changes, run a read-only status command afterward, such as cache:status, indexer:status, cluster health, or list_queues.
  • For sync issues, confirm warden sync list or warden sync monitor output before and after recovery.

Read the full file on GitHub · 685 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. 6d ago First seen · 685 lines · 59 tokens per session scan C aec6658ef559

Subscribe to this mod's changes

devops-warden is a skill published in the GitHub repository caravanglory/magehub (2 stars, last pushed 2mo ago), licensed MIT. It adds 59 tokens to every session and 7,128 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

deploy-docker-compose

Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…

omnigent-ai/omnigent · 84 tokens

compute-env-setup

Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup.

companion-inc/feynman · 45 tokens

securing-kubernetes-on-cloud

This skill covers hardening managed Kubernetes clusters on EKS, AKS, and GKE by implementing Pod Security Standards, network policies, workload identity, RBAC scoping, image admission controls, and runtime security monitoring. It addresses cloud-specific security features including IRSA for EKS, Workload Identity for…

xalgorix/xalgorix · 80 tokens

detecting-privilege-escalation-in-kubernetes-pods

Detect and prevent privilege escalation in Kubernetes pods by monitoring security contexts, capabilities, and syscall patterns with Falco and OPA policies.

xalgorix/xalgorix · 40 tokens

implementing-rbac-hardening-for-kubernetes

Harden Kubernetes Role-Based Access Control by implementing least-privilege policies, auditing role bindings, eliminating cluster-admin sprawl, and integrating external identity providers.

xalgorix/xalgorix · 41 tokens

docker-socket-mount

Docker / containerd socket mounted into a container → host RCE. Common in CI runners, GitOps controllers (ArgoCD, Flux), and 'Docker-in-Docker' setups. Single-command escape via docker run --rm --privileged -v /:/host alpine chroot /host.

PurpleAILAB/Decepticon · 67 tokens