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 quantum-vqlsgit 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/quantum-vqls)<a href="https://agentmods.dev/skills/xi-zhao/openquantum/quantum-vqls"><img src="https://agentmods.dev/badge/skills/xi-zhao/openquantum/quantum-vqls/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/quantum-vqls"><img src="https://agentmods.dev/badge/skills/xi-zhao/openquantum/quantum-vqls.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 | $0.00056 | $0.00769 |
| Opus 5.5 | $0.00022 | $0.00308 |
| Sonnet 5.5 | $0.00011 | $0.00154 |
| Haiku 4.5 | $0.00006 | $0.00077 |
Grade A, and why
quantum-vqls 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 13d 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
vqls
本地开源适配。上游指南 ID：algorithms/linear-systems/vqls。
适用方法
Qiskit 参数电路与全局归一化残差 cost 的变分线性求解；报告数值残差与优化终止原因。
使用步骤
- 先识别用户是在询问原理、要求运行，还是要求生成/修改代码；仅解释时不自动开始计算。
- 阅读共同运行说明和本地实现。可通过已有
quantum_practicesTool 的get动作、id=algorithms/linear-systems/vqls读取完整理论、原始参数和推导；其中的外部安装命令及 UnitaryLab 后端要求不适用于本地执行。 - 根据任务准备实际输入，核对下面的参数签名。省略输入只会运行教学示例，不能把它冒充用户数据的结果。需要示例以外的 ansatz、oracle、边界条件或输出时，基于开源 SDK 生成可审查的任务代码。
- 使用 Harness 已有的
bash（Windows 为pwsh）Tool 执行。在 OpenQuantum 仓库根目录，先检查示例 Python 环境；缺少依赖时显式执行npm run capability:algorithms:setup -- --minimal。执行和安装均受现有 Harness 权限、审批、超时及 Job 管理约束。Skill 不启动服务。 - 读取实际结果和错误；保留输入、依赖版本、种子、近似参数与输出。优化未收敛、后选择概率低、码距未计算或样本不足都必须按实际字段报告。通过经典对照或收敛检查支持数值结论；最终科学验收仍为
not_evaluated。
参数：
vqls(a=None, b=None, layers=2, maxiter=150, seed=7)
最小可运行示例（macOS/Linux；Windows Python 路径见共同说明）：
examples/quantum-algorithms/.venv/bin/python examples/quantum-algorithms/run.py --algorithm vqls
用户参数写入 JSON 文件，追加 --input <path>；需要保留报告时追加 --output <path>。输入规模由用户选择，不能把示例默认值当成算法上限。
来源与边界
上游 MIT 指南：algorithms/linear-systems/vqls。原文作为参考保存在固定检索库，本文件将执行路线改为开源 SDK。来源摘要和算法模块对应关系见coverage.json，许可证与改动说明见NOTICE。
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.
- 13d ago First seen · 39 lines · 56 tokens per session scan A abb089b1d279
quantum-vqls is a skill published in the GitHub repository xi-zhao/OpenQuantum (74 stars, last pushed 9d ago), licensed MIT. It adds 56 tokens to every session and 769 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 2026-09-25.
Other skills, from other repositories
sympy
Apply sympy in reproducible local data workflows with version-aware APIs, explicit assumptions, and validation. Use when the user chooses sympy or its strengths fit the task.
cudaq-importing
Use when porting circuits from another framework (e.g. Qiskit) into CUDA-Q kernels while preserving the source algorithm and validation fidelity.
cuopt-numerical-optimization-api
LP, MILP, and QP (beta) with cuOpt — Python, C, and CLI. Use when the user is solving LP, MILP, or QP with any cuOpt interface.
cupynumeric-install
Install and verify cuPyNumeric for Python — requirements, commands, verification. Source builds are out of scope.
umap-learn
Apply umap-learn in reproducible local data workflows with version-aware APIs, explicit assumptions, and validation. Use when the user chooses umap-learn or its strengths fit the task.
torchtalk-analyzer
Analyze PyTorch internals across Python, C++, and CUDA layers using the TorchTalk MCP server. Use when asked about how PyTorch operators work internally, where functions are implemented, what would break if code is modified, or finding tests for PyTorch operators.