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 agentmods add skills/kvcache-ai/mooncake/mooncake-apinpx skills add kvcache-ai/Mooncake --skill mooncake-apigit clone --depth 1 https://github.com/kvcache-ai/MooncakeWhat 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 | $0.00122 | $0.04106 |
| Opus 5 | $0.00061 | $0.02053 |
| Sonnet 5 | $0.00024 | $0.00821 |
| Haiku 4.5 | $0.00012 | $0.00411 |
Grade A, and why
mooncake-api scanned grade A with 1 finding 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://localhost:50051 How it starts
The opening of the file, as written. The whole thing — 538 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mooncake Python API Skill
Use this skill to help users work with Mooncake Python APIs for distributed storage and high-performance data transfer.
When to Use This Skill
Use this skill when users ask about:
- Using Mooncake Store for distributed KV cache storage
- Using Transfer Engine for RDMA/TCP data transfers
- Setting up Mooncake services (master, metadata server)
- Working with PyTorch tensors in Mooncake Store
- Zero-copy operations and buffer management
- Batch operations and replication configuration
- Mooncake EP (Expert Parallelism) and Mooncake Backend
- Troubleshooting Mooncake Python API issues
Routing Guidance
- For most vLLM and SGLang users, start from
docs/source/getting_started/quick-start.md. - For PD disaggregation, direct users to the SGLang/vLLM integration guides listed in Quick Start. Those guides own the serving-framework configuration.
- For Mooncake Store integrations, direct users to the SGLang/vLLM Store setup guides listed in Quick Start. Do not duplicate
mooncake_masterstartup commands in general API answers unless the user is working outside those frameworks. - For direct low-level Transfer Engine usage, use
docs/source/design/transfer-engine/index.md#using-transfer-engine-in-your-projects. - For API signatures and method details, use the Python API references under
docs/source/python-api-reference/.
Core Components
1. Mooncake Store (Distributed KV Cache)
Import:
from mooncake.store import MooncakeDistributedStore, ReplicateConfig
Basic Setup:
store = MooncakeDistributedStore()
store.setup(
"localhost", # local_hostname
"http://localhost:8080/metadata", # metadata_server
512*1024*1024, # global_segment_size (512MB)
128*1024*1024, # local_buffer_size (128MB)
"tcp", # protocol ("tcp" or "rdma")
"", # rdma_devices (empty for auto-select)
"localhost:50051" # master_server_address
)
What ships with it
1 file beside SKILL.md 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.
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.
- 3d ago First seen · 538 lines · 122 tokens per session scan A 67a219d00ba9
mooncake-api is a skill published in the GitHub repository kvcache-ai/Mooncake (6,472 stars, last pushed today), licensed Apache-2.0. It adds 122 tokens to every session and 4,106 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
sglang-diffusion-performance
Use when choosing the fastest SGLang Diffusion flags for a model, GPU, and VRAM budget.
add-jit-kernel
Step-by-step tutorial for adding a new lightweight JIT CUDA kernel to sglang's jitkernel module.
sglang-diffusion-add-model
Use when adding a new diffusion model or Diffusers pipeline to SGLang.
llm-torch-profiler-analysis
Unified LLM torch-profiler triage skill for sglang, vllm, TensorRT-LLM, and TokenSpeed. Use it to inspect an existing trace.json(.gz) or profile directory, or to drive live profiling against a running server when supported and return one three-table report with kernel, overlap-opportunity, and fuse-pattern tables.
sglang-diffusion-modelopt-quant
Use when quantizing a diffusion DiT with NVIDIA ModelOpt and making the resulting FP8 or NVFP4 checkpoint loadable, verifiable, and benchmarkable in SGLang Diffusion.
cookbook-add-model
Add a new model to the SGLang Cookbook (docs/, Mintlify), config-driven format — instantiate the model-agnostic template into a per-model config (+ benchmarks) JSX under src/snippets/configs/, an MDX page, the docs.json nav entry, NEW-tag hygiene, and the homepage vendor card. Interactive, multi-phase. Run with…