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 skills add xi-zhao/OpenQuantum --skill mrmustard-opticsgit clone --depth 1 https://github.com/xi-zhao/OpenQuantumWrote 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/xi-zhao/openquantum/mrmustard-optics)<a href="https://agentmods.dev/skills/xi-zhao/openquantum/mrmustard-optics"><img src="https://agentmods.dev/badge/skills/xi-zhao/openquantum/mrmustard-optics/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/xi-zhao/openquantum/mrmustard-optics"><img src="https://agentmods.dev/badge/skills/xi-zhao/openquantum/mrmustard-optics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00046 | $0.00870 |
| Opus 5.5 | $0.00018 | $0.00348 |
| Sonnet 5.5 | $0.00009 | $0.00174 |
| Haiku 4.5 | $0.00005 | $0.00087 |
Grade A, and why
mrmustard-optics 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 4d 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.
What it actually says
MrMustard 连续变量光学
原生 SDK 路径
本能力同时支持 MrMustard 的原生公开 API。用户需要 任意连续变量态、门、信道、参数与优化 时，由 Agent 在固定依赖环境中编写和运行任务代码，不限于下文便捷 Tool 的预设模型。
使用 node scripts/sdk-access.mjs inspect mrmustard-optics 定位环境，按完整 SDK 工作流执行。模块导航：mrmustard；导航不是 API 白名单。
固定 Python 3.11 / TensorFlow 2.15 环境；原生 wheel 与目标平台兼容性需核验。
下文关于模型、门集、输入与预算的限制描述便捷 Tool 的合同；原生 SDK 另受上游版本、可选依赖、宿主资源与用户授权约束。已禁用或被拒绝的动作不能借代码路径绕过。执行状态和科研验收分别报告。
Agent 经 Harness 调用 mrmustard_local 的 simulate_mrmustard_optics。适合相干、压缩、双模关联和线性光学模型；有确定光子数输入时优先选 Perceval/Lightworks，需要可微 Fock 层时选 MerLin。
输入 numModes、操作序列和每模式的 cutoff。初态为真空。D 使用 x,y，对应复位移 alpha=x+iy；S 与 S2 使用非负压缩量 r 和相位 phi；R 使用 theta；BS 使用 theta,phi，幅度混合的系数为 cos(theta)、sin(theta)；LOSS 使用 [0,1] 的 transmissivity。角度均为弧度，模式从 0 编号。两个模式的门接受任意不同模式。
hbar=2，真空协方差为单位阵；输出的 quadrature 顺序是所有 x 后接所有 p。相空间均值、协方差和 meanPhotons 不使用 Fock 截断。fockProbabilities 只包含各模式 0 到 cutoff−1 的占据数，并保留原始概率；retainedProbability 是其总质量，不做归一化掩盖截断。判断分布前检查该值并按需要增大 cutoff，输出规模为 cutoff^numModes。浮点舍入可能使极小概率或总和略偏离物理范围，不能把它当成新物理。
固定 MrMustard 0.7.3（Apache-2.0）。上游仓库已于 2026-07-29 归档，因此按需启用该兼容接口；不是仍受上游维护的承诺。本接口不开放训练、非高斯初态、测量条件化或硬件控制。
先显式运行 node scripts/setup-paper-tools.mjs mrmustard-optics 准备 Python 3.11 固定环境，再启用连接。调用不安装依赖，不连接远程服务；SDK 编译/缓存可能写本地文件，最大副作用为 workspace-write。部署线程、超时、输出预算使用 execution，不作为物理参数上限。
当前为 L1；结果 scientificValidation=not_evaluated。数值回归与 MCP 测试不替代 central Acceptance Builder 的科学验收。
What ships with it
6 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.
- 4d ago Changed · +13 lines 709bf139eaa1
- 18d ago First seen · 19 lines · 46 tokens per session scan A 5bb60ba103ee
mrmustard-optics is a skill published in the GitHub repository xi-zhao/OpenQuantum (75 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 870 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-29.
Other skills, from other repositories
academic-research
Search academic papers, scholarly articles, and research publications through SandBase. Use when asked for literature review, academic citations, scholarly research, paper discovery, or scientific evidence gathering.
rhylthyme
Schedule multi-step procedures that a person carries out against a clock, with parallel tracks, shared equipment and steps that end when the person says so. Use when turning a lab protocol, recipe, event run sheet or workout into a timed plan; when several procedures must share one instrument (one centrifuge, one…
memory-search-mcp
Long-term memory and context retrieval for AI agents. Semantic search across conversation history with care-weighted relevance.
gc-minimal-zine-poster-v0-3
Generate or analyze poetic paper-texture minimal zine posters with large negative space, a small editorial collage or focal element, experimental typography, and one clear color accent. Use when the user gives a theme, sentence, article, mood, object, photo, content brief, reference images, or an image folder and…
ask-sonner
Guide to Sonner, the React toast library — install and wire up the Toaster, pick the right toast() call, promise and loading toasts, updating, dismissing and persisting toasts, styling, theming and icons, positioning and multiple toasters. Use when working with Sonner or troubleshooting it — toasts that don't appear…
kill-ai-slop
Find and remove AI slop — the generic, machine-default visual and copy tics of vibe-coded products — from a web project. Use when the user asks to "kill AI slop", "de-slop", "remove the AI look", "make this not look AI-generated", or clean up a landing page / UI / docs that feels templated. Detects and fixes the…