What is Mooncake AGENTS.md?

Contribution instructions for Mooncake, including rules for changing documentation and preparing pull requests. A pull request is a proposed set of changes submitted for review.

Editing documentation, checking related issues or pull requests, running targeted pre-commit checks, and completing pull request templates.

They reduce duplicated work, prevent low-value changes, and ensure AI-assisted contributions are checked and tested before review.

Mooncake AGENTS.md — Instructions file by kvcache-ai

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.

agentmods

npx agentmods add instructions/kvcache-ai/mooncake/agents-md

Clone the repo

git clone --depth 1 https://github.com/kvcache-ai/Mooncake

Made for: Codex, OpenCode.

Per session 315 This file is loaded in full into every session.

When invoked 315 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00315	$0.00315
Opus 5	$0.00158	$0.00158
Sonnet 5	$0.00063	$0.00063
Haiku 4.5	$0.00032	$0.00032

Measured 3d ago against content hash ea1d953b4e45, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Mooncake AGENTS.md 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 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.

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.

AGENTS.md · 28 lines

What it actually says

AGENTS.md

`docs/` Directory Changes

Before modifying files under docs/, read docs/AGENTS.md.

Pull Request Guidelines

Follow CONTRIBUTING.md for PR title prefixes, RFC expectations, and contribution workflow.
Before opening a PR for nontrivial work, check whether an existing issue or open PR already covers the same change. If the work overlaps, explain the difference instead of duplicating it.
Do not open low-value busywork PRs for isolated typo, style, or mechanical changes unless they are part of a substantive requested change.
Use .github/pull_request_template.md when preparing a PR, and fill in the relevant sections for description, module, type of change, testing, checklist, and AI assistance disclosure.
For AI-assisted changes, make sure the human submitter has reviewed every changed line and can defend the change end-to-end.
Before handoff, run pre-commit on the files touched by the change when the toolchain is available (see CONTRIBUTING.md for the PR-scoped pre-commit run --files ... command). Do not use pre-commit run --all-files for routine PRs; if it rewrites unrelated files, leave those edits out of the PR.
Keep PRs lean: review git diff before staging, and include only changes required for the requested task.

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.

3d ago First seen · 28 lines · 315 tokens per session scan A ea1d953b4e45

Subscribe to this mod's changes

Mooncake AGENTS.md is an instructions file published in the GitHub repository kvcache-ai/Mooncake (6,460 stars, last pushed yesterday), licensed Apache-2.0. It adds 315 tokens to every session, about $0.0016 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.

LLM SGLang inference kvcache rdma vLLM

UniRL CLAUDE.md

Claude Code instructions for Tencent-Hunyuan/UniRL, covering claude.md, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.

Tencent-Hunyuan/UniRL · 1,414 tokens

UniRL AGENTS.md

AGENTS.md instructions for Tencent-Hunyuan/UniRL, a project described as: UniRL is a Framework for Unified Multimodal Model Reinforcement Learning.

Tencent-Hunyuan/UniRL · 11 tokens

semantic-router copilot-instructions.md

Copilot instructions for vllm-project/semantic-router, covering github copilot instructions, start here and review priorities.

vllm-project/semantic-router · 304 tokens

oumi AGENTS.md

AGENTS.md instructions for oumi-ai/oumi, covering agent instructions, publication policy and working with contributions.

oumi-ai/oumi · 436 tokens

semantic-router AGENTS.md

AGENTS.md instructions for vllm-project/semantic-router, covering vllm semantic router agent entry, read first, task routing, repository map and supported environments.

vllm-project/semantic-router · 2,046 tokens

oumi CLAUDE.md

Claude Code instructions for oumi-ai/oumi: Instructions for coding agents live in AGENTS.md — read that file. It covers the publication policy (never push, fork, or open a pull request without the developer's explicit per-instance approval) and points at CONTRIBUTING.md for the contribution workflow.

oumi-ai/oumi · 72 tokens