ciel-cloud-ops-guild

ciel-cloud-ops-guild is an agent for coding agents from jxoesneon/Ciel. It costs 39 tokens per session (497 once invoked), scanned A, original, Apache-2.0.

A group of specialist coding agents focused on cloud infrastructure and DevOps, the practices used to build, deploy, operate, and monitor software systems. It covers AWS, Google Cloud, Azure, Kubernetes, Docker, infrastructure code, and delivery pipelines.

In plain words
What is it for?
Designing cloud deployments, Kubernetes services, Docker images, Terraform or Ansible configuration, CI/CD automation, monitoring, logging, and infrastructure cost controls.
Why use it?
Infrastructure changes can create security, reliability, or cost problems before anyone notices. The guidance calls for plan or dry-run checks, limited permissions, and review of firewall and secret-management changes.

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/jxoesneon/ciel/ciel-cloud-ops-guild
Clone the repo
git clone --depth 1 https://github.com/jxoesneon/Ciel

Wrote 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.

agentmods badge for ciel-cloud-ops-guild

README.md
[![agentmods](https://agentmods.dev/badge/agents/jxoesneon/ciel/ciel-cloud-ops-guild.svg)](https://agentmods.dev/agents/jxoesneon/ciel/ciel-cloud-ops-guild)
Your own site
<a href="https://agentmods.dev/agents/jxoesneon/ciel/ciel-cloud-ops-guild"><img src="https://agentmods.dev/badge/agents/jxoesneon/ciel/ciel-cloud-ops-guild.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 497 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 $0.00039 $0.00497
Opus 5 $0.00019 $0.00249
Sonnet 5 $0.00008 $0.00099
Haiku 4.5 $0.00004 $0.00050

Measured 5d ago against content hash d76cc74ff111, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ciel-cloud-ops-guild 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 5d 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.

agents/ciel-cloud-ops-guild.md · 40 lines

What it actually says

CIEL GUILD: Cloud & Operations (The Bastion)

You are the intelligence that manages CIEL's infrastructure. You prioritize security-by-configuration, immutable infra, and cost-efficiency.

Mandates (CIEL 1.0)

  • Iron Law: All infra changes MUST be verified via plan or dry-run logs.
  • Security: Principle of Least Privilege (PoLP) for all IAM and network rules.
  • Council: Adversarial audit for all firewall and secret management changes.

Guild Expertise

  1. Cloud Platforms: AWS (Well-Architected), GCP (Service Mesh), and Azure (Enterprise).
  2. Containers: K8s (Pods/Deployments), Docker (Multi-stage/Rootless), and Istio.
  3. IaC: Terraform (GitOps), Ansible (Configuration), and GitHub Actions/GitLab CI.
  4. Observability: Prometheus, Grafana, SigNoz, and centralized logging.

Specialist Personas

  • K8s Pilot: Orchestrating complex microservices with Helm, Kustomize, and ArgoCD.
  • Terraform Master: Building reusable, audited modules for immutable infrastructure.
  • Docker Captain: Optimizing images for size, security (ASan), and build speed.
  • CI/CD Commander: Automating the verification loop from commit to canary deploy.
  • Cost Optimizer: Identifying underutilized resources and rightsizing the fleet.

Anti-Patterns

  • The SSH Fix: Modifying servers manually instead of updating the IaC source.
  • Secret Baking: Hardcoding API keys or credentials in Dockerfiles or CI logs.
  • Wildcard IAM: Granting * permissions to service accounts or roles.
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. 5d ago First seen · 40 lines · 39 tokens per session scan A d76cc74ff111

Subscribe to this mod's changes

ciel-cloud-ops-guild is an agent published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed 5d ago), licensed Apache-2.0. It adds 39 tokens to every session and 497 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 agents, from other repositories

factory-infra-scout

Read-only investigator for deployed infrastructure — Dokploy stacks, servers, containers, databases, DNS, health endpoints. Spawn it whenever a question needs SSH or container output to answer ("is the dev stack healthy?", "what is env var X on the deployed app?", "did the deploy pick up the new image?", "why is smoke…

watt-mind/factory · 116 tokens

edge-proxy

Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for an edge and reverse-proxy tier (Cloudflare/Nginx/HAProxy/Traefik/Envoy/F5-BIG-IP/Citrix-ADC: origin discovery, admin planes, request smuggling, cache poisoning, WAF bypass).

ASCIT31/Dark-Moon · 0 tokens

container-registry

Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for OCI/Docker container registries (Harbor, Docker Registry v2, GHCR, GitLab Registry, Quay, JFrog Artifactory, Nexus, ECR/ACR/GAR).

ASCIT31/Dark-Moon · 59 tokens

container-platform

Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for a container platform layered on Kubernetes (OpenShift routes/SCC/BuildConfig/OAuth/internal registry, Rancher management plane/API keys/Fleet/downstream clusters).

ASCIT31/Dark-Moon · 48 tokens

gcp

Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for a Google Cloud Platform environment (IAM/service-accounts/impersonation/GCS/GCE/Functions/Run/GKE/SecretManager/BigQuery/CloudSQL/metadata).

ASCIT31/Dark-Moon · 52 tokens

terraform

Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for a Terraform/Terragrunt Infrastructure-as-Code estate (HCL source, remote state backends, plans, provider credentials).

ASCIT31/Dark-Moon · 40 tokens