Ship Coolify

What it does

When your agent uses it

• Shipping to a Coolify environment
• Checking a Coolify deploy
• Querying Coolify directly

Example prompts

• “/ship-coolify”

Requirements

• A credential in COOLIFY_ACCESS_TOKEN
• Pre-approved tools (allowed-tools): Bash(bun scripts/ship/coolify.ts:*), Bash(curl:*), Bash(playwright-cli open:*), Bash(playwright-cli screenshot:*), Bash(playwright-cli close-all:*)

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

1. 1Know the commit. The SHA under test is the one pushed (defaults to git rev-parse HEAD).
2. 2Run the poller — it blocks until CI + deployment are done, or fails fast
3. 3Visual check (only after the poller succeeds) — use the environment's URL
4. 4Report. State: commit shipped, deployment status, deployment UUID, and the visual result. If this is a first live run or anything looks…

What it can do on your machine

Read from SKILL.md and the folder at commit e600749. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Bash(bun scripts/ship/coolify.ts:*)
  • Bash(curl:*)
  • Bash(playwright-cli open:*)
  • Bash(playwright-cli screenshot:*)
  • Bash(playwright-cli close-all:*)

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • bun
  • curl
  • jq
  • git

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use curl and git, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • COOLIFY_ACCESS_TOKEN

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ship Coolify loads about 1.9k tokens when it runs. Until then it costs about 77 tokens; SKILL.md has 828 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~77

When it runs · the whole SKILL.md, loaded when a task matches

~1.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteMentions a .env fileSKILL.md:24

  Put them in **`.env`** (see `.env.sample`). It is gitignored and secretlint-ignored, and `bun` auto-loads it from the pr

• NoteMentions a .env fileSKILL.md:28

  For raw `curl` in a shell, `.env` is not loaded automatically — source it first:

• NoteMentions a .env fileSKILL.md:31

  set -a; source .env; set +a

• NoteMentions a .env fileSKILL.md:72

  a bearer token on every request. Source `.env` first so the variables resolve in the shell:

• NoteMentions a .env fileSKILL.md:75

  set -a; source .env; set +a

• NoteMentions a .env fileSKILL.md:126

  set -a; source .env; set +a

• NoteMentions a .env fileSKILL.md:132

  Take the UUID, add it to `.env` as `COOLIFY_APP_UUID_<ENV>`, and the poller resolves it automatically.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 828 words (~1,906 tokens).

name

ship-coolify

allowed-tools

Bash(bun scripts/ship/coolify.ts:*), Bash(curl:*), Bash(playwright-cli open:*), Bash(playwright-cli screenshot:*), Bash(playwright-cli close-all:*)

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .agents/skills/ship-coolify of kovrichard/catalyst.

Open the folder on GitHubat commit e600749