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-ci-local/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-ci-local)<a href="https://agentmods.dev/skills/kvcache-ai/mooncake/mooncake-ci-local"><img src="https://agentmods.dev/badge/skills/kvcache-ai/mooncake/mooncake-ci-local/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-ci-local"><img src="https://agentmods.dev/badge/skills/kvcache-ai/mooncake/mooncake-ci-local.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 | $0.00108 | $0.01109 |
| Opus 5 | $0.00054 | $0.00554 |
| Sonnet 5 | $0.00022 | $0.00222 |
| Haiku 4.5 | $0.00011 | $0.00111 |
Grade A, and why
mooncake-ci-local 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 10d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mooncake Pre-PR Local Validation
Use bash scripts/run_ci_test.sh as the default entry point. This is the single local lane for PR-before-submit validation, and it already coordinates the reproducible parts of GitHub Actions.
Default Entry Point
When the user asks for any of the following, run the repo script first instead of reconstructing the workflow by hand:
- 提交 PR 前本地验证
- run ci test
- run local CI
- check my branch before PR
- reproduce CI locally
Default command:
bash scripts/run_ci_test.sh
What this script already covers:
- GitHub-like
paths-filteragainstorigin/main typosscripts/code_format.sh --check- default CMake configure/build/install in
build-ci-local ctest- wheel build in
build-wheel-local - wheel installation validation
scripts/run_tests.sh- selected Python API and integration tests
- per-stage summary and logs under
local_test/run-ci-logs/<timestamp>/
Standard Agent Workflow
- Run
bash scripts/run_ci_test.shfrom the repo root unless the user explicitly asks for a narrower subset. - Read the stage summary instead of dumping raw terminal output.
- Report these items back to the user:
- passed stages
- failed stages
- blocked stages
- unsupported stages
- whether
paths-filterskipped downstream stages - the log directory under
local_test/run-ci-logs/...
- If there is a failure, inspect the corresponding stage log and summarize the root cause.
Common Options
Force a full lane even if paths-filter would skip downstream stages:
bash scripts/run_ci_test.sh --skip-path-filter
Use another base ref:
bash scripts/run_ci_test.sh --base origin/main
Auto-install missing dependencies:
bash scripts/run_ci_test.sh --install-deps
Keep services running for follow-up debugging:
bash scripts/run_ci_test.sh --keep-services
Minimal Example
User prompt:
- 提交 PR 前，帮我跑一遍本地 CI 验证当前分支。
Expected action:
bash scripts/run_ci_test.sh
What ships with it
3 files 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.
- 10d ago First seen · 160 lines · 108 tokens per session scan A 31e47725438c
mooncake-ci-local is a skill published in the GitHub repository kvcache-ai/Mooncake (6,536 stars, last pushed today), licensed Apache-2.0. It adds 108 tokens to every session and 1,109 once invoked, about $0.0005 per session on Opus 5. 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 2026-08-30.
Other skills, from other repositories
sglang-diffusion-performance
Use when choosing the fastest SGLang Diffusion flags for a model, GPU, and VRAM budget.
sglang-diffusion-benchmark-profile
Use when benchmarking denoise latency or profiling a diffusion bottleneck in SGLang.
baby-sit
Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.
groq-inference
Ultra-fast LLM inference on custom LPU hardware. OpenAI-compatible API at api.groq.com. Lowest latency in the industry (500-1000+ tok/s). Supports chat completions, vision, audio (Whisper STT + TTS), tool calling, JSON mode, and streaming. Free tier available. Inference only — no training.
meta-long-running-build-watchdog
Watches a long-running command via tmux, lets sub-agent diagnose failures and propose a fix, and records the diagnosis to memory. Designed for overnight model fine-tunes, CI image builds, or repeated regression suites that may fail intermittently.
ci-cd
CI/CD pipeline expert for GitHub Actions, GitLab CI, Jenkins, and deployment automation.