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 cqlib-kernelgit 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/cqlib-kernel)<a href="https://agentmods.dev/skills/xi-zhao/openquantum/cqlib-kernel"><img src="https://agentmods.dev/badge/skills/xi-zhao/openquantum/cqlib-kernel/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/cqlib-kernel"><img src="https://agentmods.dev/badge/skills/xi-zhao/openquantum/cqlib-kernel.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 | $0.00042 | $0.00697 |
| Opus 5.5 | $0.00017 | $0.00279 |
| Sonnet 5.5 | $0.00008 | $0.00139 |
| Haiku 4.5 | $0.00004 | $0.00070 |
Grade A, and why
cqlib-kernel 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 yesterday.
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
cqlib-qml
原生 SDK 路径
本能力同时支持 CQLib 的原生公开 API。用户需要 上游计算内核、编码器、量子核、学习算法与用户数据 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 cqlib-kernel 定位环境，按完整 SDK 工作流执行。模块导航：cqlib、cqlib_qml；导航不是 API 白名单。
固定兼容的 CQLib 2.0.0b4 与完整 cqlib-qml Git 包；两者仍属上游预发布接口。原生 API 使用已安装 QML 包，不能把 Skill/upstream 的旧裁剪适配目录加到 sys.path。便捷 Tool 保留旧 angle-kernel 适配及独立回归。
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。
先在设置中心按需启用 cqlib_kernel_local，准备 Rust 构建环境。明确给出 trainX/trainY、testX 及可选 testY，再调用 fit_cqlib_angle_kernel。不从全数据拟合缩放或选择划分；所有实特征按弧度使用，实际编码为 RY(2x)。
报告真实 SDK 核与独立 ∏cos²(x−y) 对照，区分无 jitter 的 fidelity Gram 与上游训练时的 1e-8 对角 jitter；同时给解析核分类和同数据 RBF baseline。该核可经典解析，不宣称量子优势。只开放 classical angle 核，不开放 signed amplitude、共享参数 parameter-shift、VQC 或 swap test。若用户要求这些路径，解释上游当前缺陷，不能暗中用不同算法替代。
资源由用户选择，通过 execution.timeoutMs、maxOutputBytes、threads 控制进程；依赖须显式准备；计算仍可能写 SDK 缓存，保留 workspace-write。不要把执行成功或参考相符写成最终科学验收。安装、来源与示例见 候选库接入说明。
依赖准备
运行前执行 node scripts/setup-paper-tools.mjs cqlib-kernel。缺失、旧锁和已安装环境的处理见共同准备说明；Tool 不自动安装或升级依赖。
What ships with it
17 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.
- mcp/bridge.py 3.1 KB runs code
- mcp/contracts.mjs 2.2 KB runs code
- mcp/server.mjs 215 B runs code
- pyproject.toml 464 B
- upstream/compatibility.patch 628 B
- upstream/cqlib_qml/__init__.py 80 B runs code
- upstream/cqlib_qml/algorithms/__init__.py 44 B runs code
- upstream/cqlib_qml/algorithms/QKM.py 11 KB runs code
- upstream/cqlib_qml/algorithms/QSVM.py 9.4 KB runs code
- upstream/cqlib_qml/encoder/__init__.py 112 B runs code
- upstream/cqlib_qml/encoder/amplitude.py 6.8 KB runs code
- upstream/cqlib_qml/encoder/angle.py 3.9 KB runs code
- upstream/cqlib_qml/encoder/ZZFeature.py 5.1 KB runs code
- upstream/LICENSE 11 KB
- upstream/provenance.json 2.3 KB
- upstream/README.md 860 B
- uv.lock 53 KB
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.
- yesterday Changed · +13 lines 2447b4f61216
- 19d ago Changed · +4 lines 5d5a5fb01435
- 23d ago First seen · 13 lines · 42 tokens per session scan A 36cce327150f
cqlib-kernel is a skill published in the GitHub repository xi-zhao/OpenQuantum (75 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 697 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 2026-09-21.
Other skills, from other repositories
automodel
Guides the user in discovering a better model structure (e.g. from feature transformations in logistic regression to equation terms within PDEs to neural network layer compositions) out of data. Use when the user asks to create or improve an existing model. Uses an iterative meta/inner agent loop to explore structural…
ml-experiment-review
Use this skill when reviewing an ML experiment, benchmark, ablation, or training run.
kermt-pretrain-scratch
Pretrain a fresh KERMT model from scratch on a user-provided corpus. Builds a new vocabulary from the corpus, instantiates the model architecture from defaults, and launches pretrainddp.py inside the kermt container (detached for long runs). Unlike kermt-continue-pretrain, no starting checkpoint is loaded — the model…
i4h-workflow-dataset-convert
Convert workflow HDF5 recordings to LeRobot datasets for training or browser inspection. Use for conversion; do not use for replay, augmentation, or raw-data repair.
nemo-mbridge-perf-cuda-graphs
Validate and use CUDA graph capture in Megatron Bridge, including local full-iteration graphs and Transformer Engine scoped graphs for attention, MLP, and MoE modules.
onescience-dataset-builder
A workflow tool for building and checking scientific datasets. It can create a small startup script around existing data-processing code, then check the finished dataset and produce metadata.