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 amirtaherkhani/dev-io-mcp --skill runtime-modesgit clone --depth 1 https://github.com/amirtaherkhani/dev-io-mcpWrote 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/amirtaherkhani/dev-io-mcp/runtime-modes)<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/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/amirtaherkhani/dev-io-mcp/runtime-modes"><img src="https://agentmods.dev/badge/skills/amirtaherkhani/dev-io-mcp/runtime-modes.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 | $0.00000 | $0.00573 |
| Opus 5.5 | $0.00000 | $0.00229 |
| Sonnet 5.5 | $0.00000 | $0.00115 |
| Haiku 4.5 | $0.00000 | $0.00057 |
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 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 — 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
/mcpand health endpoints at/healthzand/readyz. - Bind HTTP to
0.0.0.0inside 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
emptyDirfor 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.
- Confirm the Kubernetes context is Rancher Desktop and the registry is
localhost:5001. - Before building, collect image references from every project pod and inspect
the local containerd store and local registry for
localhost:5001/dev-io-mcp. - Remove old
dev-io-mcpimages that are not referenced by an active pod. Keep the running image until the new rollout has passed verification. - Build and push a new immutable timestamped tag with
nerdctl. Never use or overwritelatest. - Render and apply
charts/dev-io-mcp/with the new repository and tag, then wait for the rollout. - Verify
/healthz,/readyz, and an MCPinitializerequest toPOST /mcp. - Only after verification succeeds, remove the former deployed image and any
other stale
dev-io-mcpimages 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.
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 · 57 lines · 0 tokens per session scan A da3208c3c391
runtime-modes is a skill published in the GitHub repository amirtaherkhani/dev-io-mcp (0 stars, last pushed 3mo 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.
Other skills, from other repositories
openshell-cli
Guide agents through using the OpenShell CLI (openshell) for sandbox management, gateway registration, provider configuration and refresh, profile management, policy iteration, settings, service exposure, BYOC workflows, and attached-provider inference. Covers basic through advanced multi-step workflows. Trigger…
azd-deployment
Deploy containerized frontend + backend applications to Azure Container Apps with remote builds, managed identity, and idempotent infrastructure.
cdf-orchestration-setup
Use when the user asks to deploy, install, reinstall, redeploy, upgrade, or connect to the CDF Orchestration Airflow controller. Owns the end-to-end deploy sequence and runs the cdf-orchestration-preflight audit first. Covers make setup, controller image builds, Helm installation, controller connection…
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…
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.
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…