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 osouthgate/agent-plus-skills --skill coolify-remotegit clone --depth 1 https://github.com/osouthgate/agent-plus-skillsWrote 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/osouthgate/agent-plus-skills/coolify-remote)<a href="https://agentmods.dev/skills/osouthgate/agent-plus-skills/coolify-remote"><img src="https://agentmods.dev/badge/skills/osouthgate/agent-plus-skills/coolify-remote.svg" alt="Measured on agentmods" 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 | $0.00069 | $0.03348 |
| Opus 5 | $0.00034 | $0.01674 |
| Sonnet 5 | $0.00014 | $0.00670 |
| Haiku 4.5 | $0.00007 | $0.00335 |
Grade D, and why
coolify-remote scanned grade D with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
This replaces the hand-rolled `until [ "$(curl … | python3 -c …)" = "finished" ]` loops that used to fail on the Windows bash shim. Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Or globally in `~/.claude/settings.json`: Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
description: Manage a remote Coolify PaaS instance from the CLI — list apps, set env vars with post-write verification, flip domains, enable TLS, trigger deploys and wait for them to finish. Use whenever you need to muta How it starts
The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
coolify-remote
Stdlib-only Python 3 CLI wrapping Coolify's REST API. One file, no pip installs. Lives at ${CLAUDE_SKILL_DIR}/../../bin/coolify-remote; the plugin auto-adds bin/ to PATH.
When to reach for this
- User wants to change something on a Coolify app (env, domain, TLS, deploy).
- User asks about deploy status or wants to redeploy and confirm it worked.
- User says "the env var isn't showing up in the container" — see Env propagation gotcha below.
- User wants to sync a local
.envto a Coolify app.
Do NOT use for server provisioning — Coolify's server objects are already-bootstrapped hosts, not Hetzner VMs. For VM lifecycle use the (separate) hcloud CLI.
When NOT to use this — fall back to coolify CLI / Coolify API directly
This wrapper is deliberately narrow. It covers the mutations we do weekly (env, domain, TLS, deploy, exec) plus read-only listing of apps and servers. It does NOT wrap Coolify's full surface area. If the user wants to do something outside that scope, don't try to contort coolify-remote — hit the Coolify REST API directly with curl (auth with $COOLIFY_API_KEY) or use the Coolify web UI.
Specific cases where you should use raw curl/the Coolify API/the UI, not coolify-remote:
- Creating or deleting applications, services, or databases. The wrapper only manages apps that already exist. Use
POST /api/v1/applications/{public,private-github,dockerfile,...}or the UI's "New Resource" flow. - Managing projects, teams, environments, or servers (add, delete, validate, reconfigure). No wrapper commands exist —
coolify-remote server listis read-only. Use/api/v1/projects,/api/v1/teams,/api/v1/serversdirectly. - Database resources (Postgres, MySQL, Redis, Clickhouse, etc.). The wrapper's
appcommands only target application resources. Database resources have their own endpoints (/api/v1/databases/*). - Rolling back to a specific deployment, canceling an in-flight deploy, or streaming live build logs.
deploy --waitpolls to a terminal state but can't cancel, roll back, or tail. Use the UI or/api/v1/deployments/{uuid}endpoints. - Managing private keys, SSH keys, webhooks, or shared variables. Not wrapped — use the UI or
/api/v1/security/keys,/api/v1/shared-variables. - Anything else the wrapper doesn't expose. The commands listed below are the complete surface; if it's not there, it's not wrapped.
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.
- 7d ago First seen · 207 lines · 69 tokens per session scan D f05c0c70f86e
coolify-remote is a skill published in the GitHub repository osouthgate/agent-plus-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 69 tokens to every session and 3,348 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it D with 3 findings (downloads and executes remote code, reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
coolify
Operate a Coolify self-hosted PaaS through the @masonator/coolify-mcp server. Use this skill whenever the user asks Claude to inspect, deploy, restart, debug, or manage anything on Coolify — including applications, databases, services, servers, projects, environments, deployments, environment variables, private keys…
cloud-administration
Administers the cloud the company runs on rather than the one it sells — tenant and subscription structure, the SaaS estate and who owns each app, identity as the real perimeter, cloud spend that arrives as a surprise, and what the provider does not do for you. Use this to structure subscriptions or tenants, get…
network-administration
Designs and operates the corporate network — segmentation, remote access, wireless, DNS and addressing, and diagnosing network problems. Use this to segment a network, set up or fix remote access, diagnose intermittent connectivity, plan addressing or DNS, or assess whether the network's trust assumptions still hold.
telephony-and-conferencing
Runs voice and meeting infrastructure — phone systems and numbers, emergency calling obligations, conference rooms and their AV, call recording and its retention consequences, and the porting that makes provider changes go badly. Use this to replace a phone system, fix rooms nobody can start a meeting in, meet…
virtualization-operations
Runs the hypervisor layer beneath the servers — host capacity and consolidation ratios, VM sprawl, snapshot discipline, resilience and live migration, and licensing that counts cores rather than instances. Use this to size or expand a cluster, work out why VMs are slow when the hosts look idle, clean up sprawl, set…
business-continuity-and-resilience
Plans for operating through disruption — impact analysis, recovery objectives, continuity plans, and the exercises that prove they work. Use this to run a business impact analysis, set RTO and RPO, write or test a continuity plan, prepare for a supplier or site failure, or answer a customer's resilience questionnaire.