Mooncake: Skill for Claude Code

.claude/skills/mooncake-troubleshoot/SKILL.md

mooncake-troubleshoot is a skill for Claude Code from kvcache-ai/Mooncake. It costs 134 tokens per session (3,483 once invoked), scanned A, original, Apache-2.0.

A troubleshooting guide for Mooncake, a distributed system that uses several services and machines to coordinate data movement.

In plain words
What is it for?
Use it to investigate deployment failures, startup problems, connection errors, metadata-server issues, port conflicts, and relevant log messages.
Why use it?
It provides a structured way to find whether failures come from stopped services, blocked connections, RDMA devices, settings, memory limits, or damaged objects.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is kvcache-ai/Mooncake's own configuration. It tells Claude Code how to work on Mooncake itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Mooncake configures →

Part of the mooncake-troubleshoot plugin — 1 skill shipped together

About the project

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.

kvcache-ai/Mooncake · 6,818 stars · on GitHub · kvcache-ai.github.io

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/kvcache-ai/Mooncake/main/.claude/skills/mooncake-troubleshoot/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/kvcache-ai/Mooncake

Made for: Claude Code.

Or install mooncake-troubleshoot, the plugin that ships this one along with the rest of its 1 skill.

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 mooncake-troubleshoot

README.md
[![agentmods](https://agentmods.dev/badge/skills/kvcache-ai/mooncake/mooncake-troubleshoot/github.svg)](https://agentmods.dev/skills/kvcache-ai/mooncake/mooncake-troubleshoot)
Your own site
<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.

agentmods 80×15 button for mooncake-troubleshoot

Your own site · 80×15
<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>
Per session 134 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,483 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00134 $0.03483
Opus 5.5 $0.00054 $0.01393
Sonnet 5.5 $0.00027 $0.00697
Haiku 4.5 $0.00013 $0.00348

Measured 1mo ago against content hash 11954aa27aa0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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
.claude/skills/mooncake-troubleshoot/SKILL.md · 384 lines

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 0.0.0.0 not 127.0.0.1:
      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
      

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"

Read the full file on GitHub · 384 lines

Files

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.

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. 1mo ago First seen · 384 lines · 134 tokens per session scan A 11954aa27aa0

Subscribe to this mod's changes

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.