Mooncake is a serving platform for Kimi, an LLM service from Moonshot AI, built around sharing and transferring the KV cache used during language-model inference. It supports disaggregated serving and data movement between inference, training, and rollout systems. The catalogue add-ons operate or integrate with Mooncake-based serving and transfer workflows.
Borrowing it
Nothing to install: this file belongs to kvcache-ai/Mooncake. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kvcache-ai/Mooncake/main/.claude/skills/mooncake-troubleshoot/SKILL.mdgit clone --depth 1 https://github.com/kvcache-ai/MooncakeWrote 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/kvcache-ai/mooncake/mooncake-troubleshoot)<a href="https://agentmods.dev/skills/kvcache-ai/mooncake/mooncake-troubleshoot"><img src="https://agentmods.dev/badge/skills/kvcache-ai/mooncake/mooncake-troubleshoot/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/kvcache-ai/mooncake/mooncake-troubleshoot"><img src="https://agentmods.dev/badge/skills/kvcache-ai/mooncake/mooncake-troubleshoot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00134 | $0.03483 |
| Opus 5.5 | $0.00054 | $0.01393 |
| Sonnet 5.5 | $0.00027 | $0.00697 |
| Haiku 4.5 | $0.00013 | $0.00348 |
Grade A, and why
mooncake-troubleshoot 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://127.0.0.1:2379/version How it starts
The opening of the file, as written. The whole thing — 384 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mooncake Deployment Troubleshooting
You are a Mooncake deployment troubleshooting specialist. Your job is to systematically diagnose issues and provide actionable solutions based on the comprehensive troubleshooting knowledge from Mooncake documentation.
Diagnostic Strategy
Run checks systematically, reporting findings as you go. Start with simple checks (services, connectivity) before diving into complex issues (RDMA, memory registration).
1. Service Status Check
Check if critical services are running:
# Check mooncake_master
ps aux | grep mooncake_master | grep -v grep
# Check port usage
netstat -tuln | grep -E '(50051|8080|2379|9003)'
# If using etcd
ps aux | grep etcd | grep -v grep
Common issues:
bind address already in use→ Port conflict, use different port with--rpc_port- Master not running → Check startup logs for errors
2. Metadata Server Connectivity
The metadata server is critical for node discovery and coordination.
# Test etcd connectivity
curl -s http://127.0.0.1:2379/version
# Or test custom metadata server
curl -s $MC_METADATA_SERVER
# Check for proxy interference
echo "http_proxy: $http_proxy"
echo "https_proxy: $https_proxy"
Common issues:
Error from etcd client→ Metadata server unreachable- Fix: Ensure etcd is bound to
0.0.0.0not127.0.0.1:etcd --listen-client-urls http://0.0.0.0:2379 --advertise-client-urls http://<your_ip>:2379 - Fix: Disable HTTP proxy:
unset http_proxy https_proxy
- Fix: Ensure etcd is bound to
3. Environment Variables Check
Verify critical environment variables are set correctly:
# Display Mooncake variables
env | grep -E '^(MC_|MOONCAKE_STORE_CHECKSUM=)'
# Key variables to check:
echo "MC_METADATA_SERVER: $MC_METADATA_SERVER"
echo "MC_FORCE_TCP: $MC_FORCE_TCP"
echo "MC_LOG_LEVEL: $MC_LOG_LEVEL"
echo "MC_YLT_LOG_LEVEL: $MC_YLT_LOG_LEVEL"
echo "MC_MS_AUTO_DISC: $MC_MS_AUTO_DISC"
echo "MC_MS_FILTERS: $MC_MS_FILTERS"
echo "MC_GID_INDEX: $MC_GID_INDEX"
echo "MC_MTU: $MC_MTU"
echo "MC_IB_PORT: $MC_IB_PORT"
echo "MC_ENABLE_DEST_DEVICE_AFFINITY: $MC_ENABLE_DEST_DEVICE_AFFINITY"
echo "MOONCAKE_STORE_CHECKSUM: $MOONCAKE_STORE_CHECKSUM"
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.
- 1mo ago First seen · 384 lines · 134 tokens per session scan A 11954aa27aa0
mooncake-troubleshoot is a skill published in the GitHub repository kvcache-ai/Mooncake (6,818 stars, last pushed yesterday), licensed Apache-2.0. It adds 134 tokens to every session and 3,483 once invoked, about $0.0005 per session on Opus 5.5. 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-benchmark-profile
Use when benchmarking denoise latency or profiling a diffusion bottleneck in SGLang.
inference-precision-tensor-dump-compare
A debugging tool that captures intermediate tensors, the numerical data passed between model layers, during inference and compares them between GPUs and Ascend NPUs. It supports vLLM and SGLang inference frameworks.
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
sglang-diffusion-cache-dit
Workflow for upgrading/integrating cache-dit in SGLang diffusion (multimodalgen): DBCache, DMD calibrator, TaylorSeer, SVDQuant DQ; porting upstream PRs and resolving conflicts against the per-request knob system; adding new cache knobs; building the sglang generate CLI test matrix; precision validation (PSNR / log…
python-debugpy
Debug Python: pdb REPL + debugpy remote (DAP).
resolve-handoff
Emit the complete Resolve handoff with exact modes, outcomes, test evidence, and publication state.