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 agentmods add skills/clezcoding/awesome-coolify/coolify-deploynpx skills add clezcoding/awesome-coolify --skill coolify-deploygit clone --depth 1 https://github.com/clezcoding/awesome-coolifyWhat 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 | $0.00025 | $0.00673 |
| Opus 5 | $0.00013 | $0.00336 |
| Sonnet 5 | $0.00005 | $0.00135 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
coolify-deploy scanned grade A with 0 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 yesterday.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coolify Deploy
Install this skill pack (Cursor, Claude Code, Codex):
npx skills add clezcoding/awesome-coolify -a cursor -a claude-code -a codex
MCP prompt analog: deploy (src/mcp/prompts.ts)
Related skills: coolify-setup · coolify-diagnose · coolify-incident
Deploy workflow
-
Resolve UUID — from args,
.coolify/manifest.json, or ask the user. -
Trigger deployment — capture
deployment_uuidwithwait: false:application({ action: "deploy", uuid: "<uuid>", wait: false }) -
Monitor with bounded watch — primary path (not
wait: true):deployment({ action: "watch", deployment_uuid: "<deployment_uuid>", timeout: 300 }) -
On
COOLIFY_WATCH_TIMEOUT— re-calldeployment.watchwith the samedeployment_uuid. Raisetimeoutif builds are slow (max 1800s). -
On
failedorcancelled-by-user— surface the error and logs hint; do not treat as success.
Legacy:
application.deploy wait:trueis back-compat only. Preferdeployment.watchfor bounded polling with backoff.
Logs and capabilities
Check system({ action: "version" }) before relying on optional capability flags.
- Fetch build/deployment output with
deployment.logs:deployment({ action: "logs", deployment_uuid: "<deployment_uuid>" }). - Fetch or follow application runtime output with
application.logs:application({ action: "logs", uuid: "<uuid>", follow: true }). - Coolify 4.1.x has no service/database log endpoints.
Recipe shortcuts
Greenfield provisioning uses the recipe tool (recipeActionsCatalog):
create-git-app(server_uuid, git_repository, git_branch, repo_path?, build_pack?)create-app-db(server_uuid, app_name, db_name, db_engine, env_key?)create-one-click(server_uuid, type, instant_deploy?)
After recipe create, deploy with the workflow above.
Safety
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.
- yesterday First seen · 75 lines · 25 tokens per session scan A e1933d944074
coolify-deploy is a skill published in the GitHub repository clezcoding/awesome-coolify (0 stars, last pushed 3d ago), licensed MIT. It adds 25 tokens to every session and 673 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
artifact
Share documents, images, and PDFs with a human as persistent links via the Artifacts MCP server. Use when the user asks to publish or share an artifact, document, diagram, generated image, or PDF with a link.
coss
Helps implement coss UI components correctly. Use when building UIs with coss primitives (buttons, dialogs, selects, forms, menus, tabs, inputs, toasts, etc.), migrating from shadcn/Radix to coss/Base UI, composing trigger-based overlays, or troubleshooting coss component behavior. Covers imports, accessibility…
post-build-flow
Handles workflow verification and setup after build-workflow succeeds, or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds, when verificationReadiness requires action, or on orchestrator verify/setup follow-up turns.
n8n:content-design
Product content designer for UI copy. Use when writing, reviewing, or auditing user-facing text: button labels, error messages, tooltips, empty states, modal copy, placeholder text, confirmation dialogs, onboarding flows, or i18n strings. Also use when the user says /copy, /content, or /ux-copy.
n8n:human-like-code-review
Reviews a GitHub pull request like a thoughtful human reviewer and writes the feedback to a markdown file. Prioritizes context, architecture fit, solution complexity, bugs, security edge cases, and missing tests. Use when given a PR URL to review, or when the user says /human-like-code-review.
n8n:node-add-oauth
Add OAuth2 credential support to an existing n8n node — creates the credential file, updates the node, adds tests, and keeps the CLI constant in sync. Use when the user says /node-add-oauth.