agentmods.dev

code-engine-deploy

A set of instructions and tools for deploying applications and jobs to IBM Code Engine, IBM’s managed service for running containers and batch work.

In plain words
What is it for?
Use it to deploy or update Code Engine apps and jobs, build and push images to IBM Cloud Container Registry, manage secrets and configuration, inspect logs and runs, and set up TLS or custom domains.
Why use it?
It brings deployment, configuration, logs, container images, secrets, and custom domains into one documented workflow.

Skill for Claude CodeCodex

0 1mo ago A scan 88 tokens original Apache-2.0
View the source file markusvankempen/code-engine-mcp-server
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/markusvankempen/code-engine-mcp-server/code-engine-deploy
Any agent
npx skills add markusvankempen/code-engine-mcp-server --skill code-engine-deploy
Clone the repo
git clone --depth 1 https://github.com/markusvankempen/code-engine-mcp-server

Made for: Claude Code, Codex.

Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,981 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 $0.00088 $0.03981
Opus 5 $0.00044 $0.01990
Sonnet 5 $0.00018 $0.00796
Haiku 4.5 $0.00009 $0.00398

Measured yesterday against content hash e9827080a470, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

.github/skills/code-engine-deploy/SKILL.md · 410 lines

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-remote pointing 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_KEY and IBMCLOUD_REGION env vars

Rule: Use ONLY Code Engine MCP tools for all deployment operations. Do not shell out to ibmcloud CLI, docker, or kubectl directly.

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.

Read the full file on GitHub · 410 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. yesterday First seen · 410 lines · 88 tokens per session scan A e9827080a470

Subscribe to this mod's changes

code-engine-deploy is a skill published in the GitHub repository markusvankempen/code-engine-mcp-server (0 stars, last pushed 1mo 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. 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.

DebuggingDevOps and cloudcode-enginecursordockeribm-code-enginemcpmcp-server
Related

Other skills, from other repositories

claude-api

Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports anthropic/@anthropic-ai/sdk; user asks for…

Prismer-AI/PrismerCloud · 193 tokens

tasks

Manage Prismer workspace tasks across the full Kanban lifecycle — create, list, inspect, update, complete, approve, reject, cancel. Use whenever the user asks to add a card to the board, dispatch work to another agent, track progress, or move a task between states. Executes via the cloud task CLI.

Prismer-AI/PrismerCloud · 68 tokens

agent-coordination

Find other agents, list participants in a conversation, send routed messages, attach files, and recover earlier conversation context (history / resolve a fuzzy reference / read a quoted message / read compressed summaries). Use whenever you need to delegate to another agent, address a peer in a multi-agent…

Prismer-AI/PrismerCloud · 122 tokens

image-generate

Generate an image from a text prompt via the cloud LLM image proxy, persist it as a content-addressed workspace asset, and return a ContentBlock that downstream renderers can attach. Use whenever the user asks "draw / generate / make an image of …", an agent needs a diagram / illustration as a follow-up artifact, or a…

Prismer-AI/PrismerCloud · 103 tokens

claim-agent-ownership

Orchestrator skill for resolving multi-daemon binding contention. Use when you (the orchestrator) detect an agent.binding.contested sync event indicating two daemons are racing for the same agent — explicitly rebind ownership to a chosen target daemon so subsequent dispatches route deterministically. Implements Gap…

Prismer-AI/PrismerCloud · 101 tokens

prismer-im-collab

Coordinate reliably in Prismer conversations, use workspace assets through bounded MCP tools, and keep task work on the board.

Prismer-AI/PrismerCloud · 30 tokens