coolify-diagnose

coolify-diagnose is a skill for Claude Code, Codex from clezcoding/awesome-coolify. It costs 32 tokens per session (715 once invoked), scanned A, original, MIT.

A troubleshooting guide for Coolify applications and servers. Coolify is a platform for deploying and managing applications, databases, and servers.

In plain words
What is it for?
Use it to diagnose an application, server, or fleet-wide scan in Coolify. It covers finding identifiers, validating systems, reviewing bounded application log tails, and summarizing findings.
Why use it?
It provides a structured way to investigate failed health checks, errors, scans, and runtime logs instead of checking each part randomly. It also distinguishes application logs from unavailable service or database logs.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/clezcoding/awesome-coolify/coolify-diagnose
Any agent
npx skills add clezcoding/awesome-coolify --skill coolify-diagnose
Clone the repo
git clone --depth 1 https://github.com/clezcoding/awesome-coolify

Made for: Claude Code, Codex.

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 715 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00032 $0.00715
Opus 5 $0.00016 $0.00358
Sonnet 5 $0.00006 $0.00143
Haiku 4.5 $0.00003 $0.00072

Measured 2d ago against content hash b30650d4e48d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

coolify-diagnose 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 2d 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.

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.

skills/coolify-diagnose/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Coolify Diagnose

Install this skill pack (Cursor, Claude Code, Codex):

npx skills add clezcoding/awesome-coolify -a cursor -a claude-code -a codex

MCP prompt analog: diagnose (src/mcp/prompts.ts)

Related skills: coolify-setup · coolify-deploy · coolify-incident

Diagnose tool

Primary entry: MCP diagnose tool (diagnoseActionsCatalog):

Actions: app(query?, uuid?, name?, domain?, limit?) · server(query?, uuid?, name?, ip?, trigger_validate?) · scan(format?, page?, per_page?) · logs(uuid, mode?, lines?, max_chars?)

Workflow

  1. Resolve UUID — from args, .coolify/manifest.json, or ask the user.

  2. Application path:

    diagnose({ action: "app", uuid: "<uuid>" })
    
  3. Server path:

    diagnose({ action: "server", uuid: "<server-uuid>" })
    
  4. Fleet scan path:

    diagnose({ action: "scan" })
    
  5. Application logs path:

    system({ action: "version" })
    diagnose({ action: "logs", mode: "full", uuid: "<uuid>" })
    

    logs combines application diagnosis with a bounded runtime tail. It is application-only in Coolify 4.1.x; service/database logs are unavailable because those REST endpoints do not exist.

  6. Summarize findings by severity and recommend the next remediation step.

  7. If remediation requires redeploy — use coolify-deploy deployment.watch flow:

    deployment({ action: "watch", deployment_uuid: "<deployment_uuid>", timeout: 300 })
    

Recipe context

When diagnosis points to missing infrastructure, use recipe actions:

  • create-git-app · create-app-db · create-one-click

Or run coolify-setup for full greenfield wire.

Safety

  • reveal opt-in — pass reveal: true on read/get actions only when the human explicitly needs unmasked secrets or env values. Default responses mask sensitive fields.
  • confirm gates — destructive mutations (delete, emergency redeploy, force overrides) require explicit human approval and confirm: true on the second call after preview.

Read the full file on GitHub · 91 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. 2d ago First seen · 91 lines · 32 tokens per session scan A b30650d4e48d

Subscribe to this mod's changes

coolify-diagnose is a skill published in the GitHub repository clezcoding/awesome-coolify (0 stars, last pushed 4d ago), licensed MIT. It adds 32 tokens to every session and 715 once invoked, about $0.0002 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.

Related

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…

StuMason/coolify-mcp · 156 tokens

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.

dbtlr/artifacts · 47 tokens

verify

Run this repo's verification gate — typecheck, the unit suite, the DB-backed suite. Load before running tests, pointing DATABASEURL anywhere, or reporting a unit done.

getpostern/postern · 37 tokens

new-connector

Add or change a source connector, a REGISTRY object, or a migration. Load before writing anything in src/connectors/, src/core/schema.ts, or db/migrations/.

getpostern/postern · 39 tokens

tube-bridge-research

Operate tube-bridge as a coherent YouTube research system: frame questions, discover sources, select subtitle tracks, classify claims, test competing hypotheses, capture timestamped evidence, build and search local corpora, and report traceable conclusions. Use for evidence-oriented YouTube research, transcript…

TheWhiteWater/tube-bridge · 76 tokens

tomtom

TomTom Maps MCP integration — search, routing, traffic, maps, POIs, and EV via hosted endpoint.

Drknght4/hermes-mcp-tomtom · 25 tokens