safe-deploy

safe-deploy is a skill for Claude Code from Abilityai/abilities. It costs 58 tokens per session (2,271 once invoked), scanned C, original, MIT.

A deployment workflow for Docker Compose services that can be reached over SSH, a secure way to run commands on another computer.

In plain words
What is it for?
It helps back up, pull, rebuild, restart, validate, roll back, restore a database, and diagnose deployment health.
Why use it?
It reduces the risk of losing data or leaving a service unhealthy during updates and rollbacks.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; positional $N argument.

Part of the utilities plugin — 7 skills shipped together

Good fit It helps back up, pull, rebuild, restart, validate, roll back, restore a database, and diagnose deployment health.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/abilityai/abilities/safe-deploy
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.

Any agent
npx skills add Abilityai/abilities --skill safe-deploy
Clone the repo
git clone --depth 1 https://github.com/Abilityai/abilities

Made for: Claude Code.

Or install utilities, the plugin that ships this one along with the rest of its 7 skills.

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 safe-deploy

README.md
[![agentmods](https://agentmods.dev/badge/skills/abilityai/abilities/safe-deploy/github.svg)](https://agentmods.dev/skills/abilityai/abilities/safe-deploy)
Your own site
<a href="https://agentmods.dev/skills/abilityai/abilities/safe-deploy"><img src="https://agentmods.dev/badge/skills/abilityai/abilities/safe-deploy/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for safe-deploy

Your own site · 80×15
<a href="https://agentmods.dev/skills/abilityai/abilities/safe-deploy"><img src="https://agentmods.dev/badge/skills/abilityai/abilities/safe-deploy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,271 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00058 $0.02271
Opus 5.5 $0.00023 $0.00908
Sonnet 5.5 $0.00012 $0.00454
Haiku 4.5 $0.00006 $0.00227

Measured 1mo ago against content hash 6d630f8ef017, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

safe-deploy 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 1mo 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.

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

SSH_KEY=<path to key, default: ~/.ssh/id_rsa>

Makes network callslowCapability

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

STATUS=$($RUN "curl -s -o /dev/null -w '%{http_code}' http://localhost:$BACKEND_PORT/health 2>/dev/null || echo 'unreachable'")
plugins/utilities/skills/safe-deploy/SKILL.md · 321 lines

How it starts

The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Safe Deploy

ℹ️ First, set expectations: before anything else, print one short line with this skill's version and its most recent change — the top entry of metadata.changelog above — e.g. safe-deploy vX.Y — recent: <summary>. Then proceed.

Safe deployment operations for docker-compose-based services over SSH. Three subcommands covering the full deploy lifecycle.


Prerequisites

Configure via environment variables or a local .env file:

SSH_HOST=<ip or hostname>
SSH_USER=<username, default: ubuntu>
SSH_KEY=<path to key, default: ~/.ssh/id_rsa>
APP_PATH=<remote app directory, default: ~/app>
COMPOSE_FILE=<compose file, default: docker-compose.yml>
BACKUP_DIR=<backup directory on remote, default: ~/backups>
DB_PATH=<path to database file, default: ~/app/app.db>

Connection setup (used in all subcommands):

source .env 2>/dev/null || true
SSH_HOST=${SSH_HOST:-""}
SSH_USER=${SSH_USER:-"ubuntu"}
SSH_KEY=${SSH_KEY:-"~/.ssh/id_rsa"}
APP_PATH=${APP_PATH:-"~/app"}
COMPOSE=${COMPOSE_FILE:-"docker-compose.yml"}
BACKUP_DIR=${BACKUP_DIR:-"~/backups"}
DB_PATH=${DB_PATH:-"$APP_PATH/app.db"}
RUN="ssh -i $SSH_KEY $SSH_USER@$SSH_HOST"

If SSH_HOST is empty, check for a scripts/run.sh wrapper.


Subcommand: update

Full deployment: backup → pull → rebuild → restart → validate.

Step U1: Pre-deploy Check

Check for running long-lived processes before proceeding:

$RUN "cd $APP_PATH && docker compose -f $COMPOSE ps --format json 2>/dev/null | grep -c running || docker compose -f $COMPOSE ps | grep -c Up"

Warn the user if active processes are running. Ask: "Proceed with deployment? Active processes may be interrupted."

Check disk space before proceeding:

$RUN "df -h $APP_PATH | tail -1 | awk '{print \$5}'"

If disk usage >85%, warn the user.

Step U2: Backup Database

Create a timestamped backup before any changes:

BACKUP_TS=$(date +%Y-%m-%d-%H%M%S)
$RUN "mkdir -p $BACKUP_DIR && cp $DB_PATH $BACKUP_DIR/app-${BACKUP_TS}.db 2>/dev/null && echo 'backup: ok' || echo 'backup: skipped (no DB found)'"

Read the full file on GitHub · 321 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. 1mo ago First seen · 321 lines · 58 tokens per session scan C 6d630f8ef017

Subscribe to this mod's changes

safe-deploy is a skill published in the GitHub repository Abilityai/abilities (12 stars, last pushed 3d ago), licensed MIT. It adds 58 tokens to every session and 2,271 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 2 findings (reaches for credential files, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-07.

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

bdd-container-update

Update the BDD test container image when its dependencies or runtime change. Determines version bump (major vs minor vs patch), rebuilds the Docker image, pushes to GitLab registry, and updates the image tag in starttest.sh. Test source (tests/, features/, scripts/, data/, conftest.py) is bind-mounted from the host…

NVIDIA-AI-Blueprints/video-search-and-summarization · 117 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

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

managing-astro-local-env

Manage local Airflow environment with Astro CLI (Docker and standalone modes). Use when the user wants to start, stop, or restart Airflow, view logs, query the Airflow API, troubleshoot, or fix environment issues. For project setup, see setting-up-astro-project.

astronomer/agents · 63 tokens