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 skills add markusvankempen/code-engine-mcp-server --skill code-engine-deploygit clone --depth 1 https://github.com/markusvankempen/code-engine-mcp-serverWrote 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.
[](https://agentmods.dev/skills/markusvankempen/code-engine-mcp-server/code-engine-deploy)<a href="https://agentmods.dev/skills/markusvankempen/code-engine-mcp-server/code-engine-deploy"><img src="https://agentmods.dev/badge/skills/markusvankempen/code-engine-mcp-server/code-engine-deploy/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/markusvankempen/code-engine-mcp-server/code-engine-deploy"><img src="https://agentmods.dev/badge/skills/markusvankempen/code-engine-mcp-server/code-engine-deploy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00088 | $0.03981 |
| Opus 5.5 | $0.00035 | $0.01592 |
| Sonnet 5.5 | $0.00018 | $0.00796 |
| Haiku 4.5 | $0.00009 | $0.00398 |
Grade A, and why
code-engine-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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 410 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IBM Code Engine Deployment Skill
When to Use
Invoke this skill whenever the task involves:
- Deploying or updating a Code Engine application or job
- Building and pushing a container image (local Docker/Podman → ICR)
- Managing Code Engine projects, secrets, config maps, or domain mappings
- Checking app logs, revisions, or job runs
- Setting up or renewing TLS / custom domains
- Any task touching the IBM Cloud Container Registry (ICR)
MCP Server Selection
Before performing any Code Engine task, determine which MCP server to use:
1. Prefer Remote (if available)
Check whether the remote-code-engine MCP server is configured and reachable:
- Use
mcp-remotepointing to the bridge URL (e.g.https://ce-mcp-remote.<hash>.<region>.codeengine.appdomain.cloud/sse) - If the remote server responds, use it exclusively — it avoids running a local node process and is already authenticated via the bridge.
2. Fall back to Local
If remote is unavailable or not configured, use the local code-engine stdio server:
- Launched via
npx -y code-engine-mcp-server@latest - Requires
IBMCLOUD_API_KEYandIBMCLOUD_REGIONenv vars
Rule: Use ONLY Code Engine MCP tools for all deployment operations. Do not shell out to
ibmcloudCLI,docker, orkubectldirectly.
MCP Setup Guide
Prerequisites
- Node.js 18+ — verify:
node --version - IBM Cloud API key — create at cloud.ibm.com/iam/apikeys
- Required IAM permissions: Code Engine Editor + Container Registry Reader
API Key Storage (choose one)
Option A — Shell env var (recommended)
cp dot.env.example .env # .env is already in .gitignore
# Edit .env: IBMCLOUD_API_KEY=your-key-here
source .env
# Or permanently: echo 'export IBMCLOUD_API_KEY="your-key"' >> ~/.zshrc
Reference in any config file as "${env:IBMCLOUD_API_KEY}" — the key never appears in the file.
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.
- 1mo ago First seen · 410 lines · 88 tokens per session scan A e9827080a470
code-engine-deploy is a skill published in the GitHub repository markusvankempen/code-engine-mcp-server (0 stars, last pushed 15d ago), licensed Apache-2.0. It adds 88 tokens to every session and 3,981 once invoked, about $0.0004 per session on Opus 5.5. 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
n8n-self-hosting
Deploy a production self-hosted n8n end-to-end to a fresh Linux VM over SSH, using Docker Compose behind a Caddy reverse proxy with automatic HTTPS. Use whenever the user wants to self-host, install, set up, provision, or deploy n8n on their own server/VPS/box (Hetzner, DigitalOcean, AWS EC2, bare metal, etc.) — in…
release-ota-promote
Publish signed Electron UI/daemon bundles to a local OTA feed with atomic manifest switch and digest readback, while dry-running the K8s drainrespawn rollout. Prod is refused before writes; feed publication is not client apply.
dokploy-deploy
This skill should be used when user asks to "deploy with Dokploy", "use Dokploy Cloud", "manage self-hosted Dokploy", "deploy Docker Compose on Dokploy", "manage Dokploy databases", "configure Dokploy domains", or "look up Dokploy CLI commands".
ecspresso
ECS deployment tool - deploy, manage, and troubleshoot ECS services.
k8s-dev-deploy
Build, push, and deploy Kurtosis dev images to a Kubernetes cluster without creating a release. Rebuilds engine, core, and files-artifacts-expander as multi-arch Docker images with a unique tag, pushes to the logged-in user's Docker Hub, and restarts the engine. Use when testing local code changes on a k8s cluster.
04-security
A security and operations guide for deploying Dify, an open-source platform for building AI applications, in production.