inference-cache

inference-cache is a plugin for Claude Code from air-gapped/skills. Its manifest loads nothing; the 2 skills it bundles cost 426 tokens per session together, scanned A, original, MIT.

A toolkit for moving language-model key-value caches and data between memory, GPUs, local storage, and remote systems. It covers LMCache and NVIDIA NIXL, which are used by model-serving systems such as vLLM and SGLang.

In plain words
What is it for?
Use it to configure LMCache server deployments, connect cache layers and storage adapters, integrate NIXL transport plugins, and examine telemetry for cache offload and distributed data movement.
Why use it?
Model serving can waste time recomputing previously processed context or moving cached data inefficiently between workers and storage. This helps design and inspect cache and transfer paths in standalone servers and Kubernetes deployments.

Plugin for Claude Code

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.

Claude Code
/plugin marketplace add air-gapped/skills
agentmods
npx agentmods add plugins/air-gapped/skills/inference-cache
Clone the repo
git clone --depth 1 https://github.com/air-gapped/skills

Made for: Claude Code.

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 inference-cache

README.md
[![agentmods](https://agentmods.dev/badge/plugins/air-gapped/skills/inference-cache.svg)](https://agentmods.dev/plugins/air-gapped/skills/inference-cache)
Your own site
<a href="https://agentmods.dev/plugins/air-gapped/skills/inference-cache"><img src="https://agentmods.dev/badge/plugins/air-gapped/skills/inference-cache.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 2 skills cost 426 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

inference-cache 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.

.claude-plugin/marketplace.json#inference-cache · 28 lines

What it actually says

{
  "name": "inference-cache",
  "source": "./",
  "description": "Inference KV-cache and transport suite — LMCache multiprocess (MP) standalone-server mode (DaemonSet + Deployment K8s pattern, ZMQ connector, L1 + L2 NIXL/POSIX/GDS/HF3FS/fs/s3/mooncake adapters) and NVIDIA NIXL transfer library (UCX/GDS/Mooncake/libfabric/HF3FS/S3 plugins, agent API, telemetry) used by Dynamo/vLLM/SGLang. Pairs with the vllm-caching skill in the `vllm` suite and sglang-hicache in the `sglang` suite.",
  "version": "0.20260819.12",
  "author": {
    "name": "Jörgen"
  },
  "license": "MIT",
  "skills": [
    "./.claude/skills/lmcache-mp",
    "./.claude/skills/nvidia-nixl"
  ],
  "strict": false,
  "category": "inference",
  "tags": [
    "kv-cache",
    "lmcache",
    "nixl",
    "vllm",
    "sglang",
    "dynamo",
    "offload",
    "prefix-caching",
    "disaggregated-prefill",
    "kubernetes"
  ]
}
Contents

What it installs

The manifest is a name and a version. 2 skills travel with it, and installing the plugin installs all of them — 426 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

1 file beside marketplace.json#inference-cache in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 28 lines scan A 7694d9c29de2

Subscribe to this mod's changes

inference-cache is a plugin published in the GitHub repository air-gapped/skills (5 stars, last pushed 3d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-03.