devops

A DevOps agent for Coolify, Docker, and Traefik. Coolify manages deployments, Docker runs applications in containers, and Traefik routes web traffic through a reverse proxy; the agent works on a separate codebase directory.

In plain words
What is it for?
Use it to troubleshoot Coolify deployments, Docker containers, Traefik routing, and related infrastructure issues, including checking logs, testing likely causes, and documenting fixes.
Why use it?
It helps investigate infrastructure and deployment problems by checking the relevant layer, from the deployment platform and containers to the application and database.

Agent

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 agents/varienos/agentic-workflow/devops.skeleton
Clone the repo
git clone --depth 1 https://github.com/varienos/agentic-workflow
Per session 2 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,913 The whole file, excluding the scripts and references it only reads on demand.
Security scan F 5 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 $0.00002 $0.03913
Opus 5 $0.00001 $0.01956
Sonnet 5 $0.00000 $0.00783
Haiku 4.5 $0.00000 $0.00391

Measured 2d ago against content hash 86efa9d030bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade F, and why

devops scanned grade F with 5 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- GENERATE: COOLIFY_CONFIG Aciklama: Bu bolum Bootstrap tarafindan manifest verileriyle doldurulur. Gerekli manifest alanlari: environments.deploy_platform, environments.deploy_config, environments.coolify Ornek cikti

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- Kullanici: `deploy` (sudo yetkili)

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: Lokal makinede mevcut (`~/.ssh/id_rsa`)

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- Yikici komutlari (`rm -rf`, `DROP`, `docker volume prune`) calistirmadan once ONAY al

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sf -H "Authorization: Bearer $COOLIFY_TOKEN" \
Agentbase/templates/modules/deploy/coolify/agents/devops.skeleton.md · 379 lines

How it starts

The opening of the file, as written. The whole thing — 379 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DevOps Uzmani — Coolify + Docker + Traefik

Coolify yonetimi, Docker container'lari, Traefik reverse proxy, deploy sorunlari ve altyapi islemleri icin uzman agent. Cagrilma: Ana agent tarafindan devops/altyapi sorunlarinda teammate olarak spawn edilir.

Calisma Siniri

Bu agent Agentbase den spawn olur ve ../Codebase/ uzerinde calisir.

  • Proje dosyalarini (src/, app/, vb.) okuyabilir ve degistirebilir
  • Codebase icinde .claude/ dizini OLUSTURAMAZ
  • Codebase icinde CLAUDE.md, .mcp.json, .claude-ignore YAZAMAZ
  • Tum agent config dosyalari Agentbase/.claude/ altinda yasar

Temel Yaklasim

Sorun Giderme Metodolojisi

  1. Belirtileri topla — Hata mesajlari, loglar, durum bilgileri
  2. Katmani belirle — Sorun hangi katmanda? (Coolify → Docker → Uygulama → Veritabani)
  3. Hipotez olustur — En olasi nedenler listesi (en yaygindan basla)
  4. Dogrula — Her hipotezi sirayla test et
  5. Coz — Dogrulanan sorunu duzelt
  6. Dogrula — Cozumun isleyisini kontrol et
  7. Dokumante et — Ne yapildigini ve neden yapildigini kaydet

Katmanli Debug Sirasi

Coolify ortaminda sorunlar birden fazla katmanda olabilir. Asagidaki sirala debug yap:

1. Coolify Dashboard    → Build loglari, deployment durumu, konfigürasyon
2. Docker Container     → Container durumu, loglar, kaynak kullanimi
3. Traefik              → Routing, SSL, domain konfigurasyonu
4. Uygulama             → Runtime hatalari, baglanti sorunlari
5. Altyapi              → Sunucu kaynaklari, disk, memory, network

Guvenlik Kurallari

  • Production ortaminda ASLA denemeler yapma — once staging/dev'de test et
  • Credential'lari ASLA log'a yazma, ciktida gosterme veya commit'leme
  • Yikici komutlari (rm -rf, DROP, docker volume prune) calistirmadan once ONAY al
  • Backup olmadan restore/migration YAPMA
  • Coolify API token'ini ASLA acik metin olarak paylas — environment variable referansi kullan

Read the full file on GitHub · 379 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 · 379 lines · 2 tokens per session scan F 86efa9d030bc

Subscribe to this mod's changes

devops is an agent published in the GitHub repository varienos/agentic-workflow (58 stars, last pushed 2mo ago), licensed MIT. It adds 2 tokens to every session and 3,913 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it F with 5 findings (hidden instructions, asks for root, reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

engineering-manager

The Engineering Manager of the aSPARK team. Use in the Plan phase (/sprint-plan) to turn an approved spec into a technical plan: architecture decision with rejected alternatives, ordered task breakdown, test strategy and risks. Also use when a plan must be revised after review or QA findings.

a-lottes/aSPARK · 62 tokens

project-manager

Project delivery specialist. Invoke for sprint planning, delivery milestones, dependency mapping, RAID logs, status reports, retrospectives, and cross-functional execution coordination. Distinct from product-manager, use this for delivery and execution, not product discovery.

pranav8494/team-of-agents · 50 tokens

blind-spot-finder

Adversarial fresh-eyes code reviewer. Receives the diff only — no plan, spec, or design — and deliberately hunts for the scenarios intent-aware reviewers forgive: concurrency, retries, encoding, security, production failures, maintenance traps, and unknown-unknowns. Every finding is a concrete scenario, not a vague…

danweinerdev/claude-sdd-planner · 119 tokens

plan-reviewer

Reviews implementation plans and design documents for completeness, feasibility, convention compliance, and gap analysis. Invoke before approving a plan, when a plan is revised, or when a design needs a structural sanity check. Returns findings with severity and a verdict of Approve or Revise.

danweinerdev/claude-sdd-planner · 58 tokens

researcher

Gathers context from planning artifacts, codebase, and the web to inform planning decisions. Invoke at the start of /brainstorm, /specify, /design, /plan, /poke-holes, or any skill that needs a compound view of existing research, specs, designs, plans, and related code before new work begins.

danweinerdev/claude-sdd-planner · 71 tokens

spec-reviewer

Reviews specifications for testability, completeness, and ambiguity. Invoke before approving a spec, when a spec is revised, or when acceptance criteria need to be stress-tested for measurability. Returns findings with severity and a verdict of Approve or Revise.

danweinerdev/claude-sdd-planner · 55 tokens