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 skills add Abilityai/abilities --skill safe-deploygit clone --depth 1 https://github.com/Abilityai/abilitiesWrote 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/skills/abilityai/abilities/safe-deploy)<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.
<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>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 5.1 | $0.00058 | $0.02271 |
| Opus 5.5 | $0.00023 | $0.00908 |
| Sonnet 5.5 | $0.00012 | $0.00454 |
| Haiku 4.5 | $0.00006 | $0.00227 |
Grade C, and why
safe-deploy scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
SSH_KEY=<path to key, default: ~/.ssh/id_rsa> Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
STATUS=$($RUN "curl -s -o /dev/null -w '%{http_code}' http://localhost:$BACKEND_PORT/health 2>/dev/null || echo 'unreachable'") 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.changelogabove — 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)'"
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.
- 1mo ago First seen · 321 lines · 58 tokens per session scan C 6d630f8ef017
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.
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…
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…
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…
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.
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.
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.