runtime-modes

runtime-modes is a skill for Claude Code, Codex from amirtaherkhani/dev-io-mcp. It costs 0 tokens per session (573 once invoked), scanned A, original, MIT.

A set of rules for changing a Kubernetes-only HTTP deployment. Kubernetes is software for running applications in managed containers, while a Helm chart describes how to deploy them.

In plain words
What is it for?
For deploying dev-io-mcp through Kubernetes and Traefik, checking its local image and registry setup, preserving stored posts and metrics, and keeping only the currently deployed image.
Why use it?
It keeps the service's network endpoints, stored data, container images, and security requirements consistent during deployment changes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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/amirtaherkhani/dev-io-mcp/runtime-modes
Any agent
npx skills add amirtaherkhani/dev-io-mcp --skill runtime-modes
Clone the repo
git clone --depth 1 https://github.com/amirtaherkhani/dev-io-mcp

Made for: Claude Code, Codex.

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 runtime-modes

README.md
[![agentmods](https://agentmods.dev/badge/skills/amirtaherkhani/dev-io-mcp/runtime-modes.svg)](https://agentmods.dev/skills/amirtaherkhani/dev-io-mcp/runtime-modes)
Your own site
<a href="https://agentmods.dev/skills/amirtaherkhani/dev-io-mcp/runtime-modes"><img src="https://agentmods.dev/badge/skills/amirtaherkhani/dev-io-mcp/runtime-modes.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 573 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 5.1 $0.00000 $0.00573
Opus 5 $0.00000 $0.00287
Sonnet 5 $0.00000 $0.00115
Haiku 4.5 $0.00000 $0.00057

Measured 5d ago against content hash da3208c3c391, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

runtime-modes 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.

skills/runtime-modes/SKILL.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Runtime Modes

Use this skill when changing the Kubernetes-only HTTP deployment.

Mode contract

Mode Transport Entry point State
Kubernetes Streamable HTTP Helm chart PVC-backed posts/ and data/

Rules

  • Keep the HTTP endpoint at /mcp and health endpoints at /healthz and /readyz.
  • Bind HTTP to 0.0.0.0 inside the Kubernetes pod and expose it through the Traefik Ingress.
  • Do not expose the MCP service publicly without authentication, network controls, and a reviewed threat model.
  • Do not use emptyDir for production posts or metrics unless data loss is explicitly acceptable.
  • Do not deploy a local image to a remote cluster; use an immutable registry tag or digest.

Local image lifecycle

This project overrides the general local deployment retention default: after a successful rollout, keep exactly one dev-io-mcp image—the image currently deployed.

  1. Confirm the Kubernetes context is Rancher Desktop and the registry is localhost:5001.
  2. Before building, collect image references from every project pod and inspect the local containerd store and local registry for localhost:5001/dev-io-mcp.
  3. Remove old dev-io-mcp images that are not referenced by an active pod. Keep the running image until the new rollout has passed verification.
  4. Build and push a new immutable timestamped tag with nerdctl. Never use or overwrite latest.
  5. Render and apply charts/dev-io-mcp/ with the new repository and tag, then wait for the rollout.
  6. Verify /healthz, /readyz, and an MCP initialize request to POST /mcp.
  7. Only after verification succeeds, remove the former deployed image and any other stale dev-io-mcp images from both the local containerd store and the local registry. Confirm that the newly deployed image is the only retained project image.

Never run a global image prune. Cleanup must be scoped to dev-io-mcp, and no image referenced by an active pod may be removed. If deployment or verification fails, retain both the running image and the failed image for rollback and diagnosis; report the exception instead of forcing the one-image policy.

Read the full file on GitHub · 57 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. 5d ago First seen · 57 lines · 0 tokens per session scan A da3208c3c391

Subscribe to this mod's changes

runtime-modes is a skill published in the GitHub repository amirtaherkhani/dev-io-mcp (0 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 573 tokens. 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

openshell-cli

Guide agents through using the OpenShell CLI (openshell) for sandbox management, gateway registration, provider configuration and refresh, policy iteration, settings, service exposure, BYOC workflows, and inference routing. Covers basic through advanced multi-step workflows. Trigger keywords - openshell, sandbox…

NVIDIA/OpenShell · 127 tokens

langbot-deploy

Deploy and configure a LangBot instance — Docker / Docker Compose, Kubernetes, the config.yaml model, the Box sandbox runtime, the plugin runtime, and the global API key. Use when installing, deploying, upgrading, or configuring LangBot in production or self-hosted environments. Triggers on "deploy langbot", "langbot…

langbot-app/LangBot · 104 tokens

compute-env-setup

Set up a compute environment on a remote provider so Claude Science jobs can run there. Covers direct SSH/conda hosts, Slurm clusters, container-via-bridge runners, and managed-API providers (Modal, GCP, RunPod). Use when standing up a new provider, porting an env to a different backend, adding a tool that needs its…

UnicomAI/wanwu · 134 tokens

azure-cloud-migrate

Assess and migrate cross-cloud workloads to Azure with reports and code conversion. Supports Lambda→Functions, Beanstalk/Heroku/App Engine→App Service, Fargate/Kubernetes/Cloud Run/Spring Boot→Container Apps. WHEN: migrate Lambda to Functions, AWS to Azure, migrate Beanstalk, migrate Heroku, migrate App Engine, Cloud…

microsoft/skills · 106 tokens

compute-env-setup

Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup.

companion-inc/feynman · 45 tokens

atmos-helmfile

Helmfile orchestration: sync/apply/destroy/diff, Kubernetes deployments, varfile generation, EKS integration, source management.

cloudposse/atmos · 33 tokens