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 agentmods add skills/xi-zhao/openquantum/platform-diagnosticsnpx skills add xi-zhao/OpenQuantum --skill platform-diagnosticsgit 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/platform-diagnostics)<a href="https://agentmods.dev/skills/xi-zhao/openquantum/platform-diagnostics"><img src="https://agentmods.dev/badge/skills/xi-zhao/openquantum/platform-diagnostics.svg" alt="Measured on agentmods" 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 | $0.00052 | $0.00776 |
| Opus 5 | $0.00026 | $0.00388 |
| Sonnet 5 | $0.00010 | $0.00155 |
| Haiku 4.5 | $0.00005 | $0.00078 |
Grade A, and why
platform-diagnostics 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
OpenQuantum 平台诊断
本能力只诊断四层架构，不实现量子业务功能。默认执行只读检查；除非用户明确授权，不修改配置、 不启动长期后台进程、不写入生产系统。
核心对象
诊断对象是一份 platform-diagnostics 报告。报告中的每个检查项必须有可复核证据；Capability Validator
根据检查结果推导的是诊断报告聚合状态，不是 Scientific Acceptance，也不能由模型自行宣称。
开始前读取并按 Capability Contract v1 校验 capability.yaml。生成报告时读取
artifacts/diagnostic-report.schema.json；验收时运行 validators/validate-report.mjs。
检查流程
- UI：确认 UI 只通过 Harness transport adapter 发出会话命令，不直接调用 Model Provider 或 MCP Server。
- Harness 配置：运行
npm run harness:config，确认组合能展开且默认模型属于 OpenQuantum route。 - Harness Host：检查 Host 根页面、
session.list和llm.modelsHarness RPC；未启动时记录not_checked， 不把静态配置当成运行证据。 - Skill：通过 Harness
skill.list或当前成功加载的 Skill 上下文证明项目 Skill 可发现。 - Model：运行
npm run models:probe -- --provider openquantum-public，分别验证目录、文本生成和 强制函数调用。不要把“接口返回 200”替代工具调用验收。 - 端到端：有 Provider 凭据时运行
npm run e2e:quantum-harness -- --provider openquantum-public，确认 真实模型在 Harness Session 中产生 QGStool/call/tool/result，且 Result Commit 与中央 Acceptance 通过复核。绕过 Harness MCP Client 直接调用 MCP Server SDK 不能替代这条证据。 - 可选路由：私有网关不可达时记录
warn或可选检查项fail；只要它不是当前任务的硬性要求， 不得覆盖公开主路由的有效证据。 - 按 schema 生成 JSON 报告，不得写入 API Key、Authorization header、完整 Prompt 或敏感科研数据。
- 运行
node .agents/skills/platform-diagnostics/validators/validate-report.mjs <report.json>。 只有 Validator 成功，报告才算形成有效评分。
判定规则
- 任一必需检查为
fail：整体blocked。 - 无必需失败，但存在
warn、not_checked或可选失败：整体degraded。 - 所有检查均为
pass：整体ready。 pass必须有运行证据；推测、配置存在、模型自述都不算证据。- 非
pass检查必须给出nextAction。
输出先给结论，再给证据和下一步。不要把运行成功等同于科学验收；具体量子能力的 Scientific Validator 只产生运行时 observations，Acceptance Profile 定义规则，central Acceptance Builder 推导验收；开发期 eval evidence 只用于回归和发布门禁。
What ships with it
10 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.
- artifacts/diagnostic-report.schema.json 2.2 KB
- capability.yaml 2.6 KB
- evals/cases.json 651 B
- evals/fixtures/blocked-report.json 1.7 KB
- evals/fixtures/degraded-report.json 2.0 KB
- evals/fixtures/invalid-self-score.json 1.7 KB
- evals/fixtures/ready-report.json 1.7 KB
- evals/run-evals.mjs 1.1 KB runs code
- inputs/request.schema.json 477 B
- validators/validate-report.mjs 5.8 KB runs code
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 First seen · 48 lines · 52 tokens per session scan A 5d7603a815bd
platform-diagnostics is a skill published in the GitHub repository xi-zhao/OpenQuantum (48 stars, last pushed 3d ago), licensed MIT. It adds 52 tokens to every session and 776 once invoked, about $0.0003 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
code-review
Reviews a supplied code path or diff for correctness, security, maintainability, and style without executing or modifying it.
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…
obsidian-bases
内容创作者与技术写作员在管理海量笔记时，当需要构建 Obsidian 数据库视图、配置过滤器或编写 YAML 公式，使用此技能可自动生成标准 .base 文件，轻松实现笔记的表格/卡片多维展示与数据汇总，让知识库管理效率翻倍。.
archify
Create polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable standalone HTML with inline SVG, dark/light themes, optional trace motion, and PNG/JPEG/WebP/SVG/WebM export. Accept plain-language requirements or pasted Mermaid flowchart, sequenceDiagram, and…
competitor-content-intelligence
Analyze competitor content coverage and uncover differentiated content opportunities using web search, page extraction, and DataForSEO content analysis. Use when asked for competitor content research, editorial gap analysis, content brief inputs, or topic whitespace.
exa-deep-search
Search, extract, and compare high-quality public sources with Exa through SandBase. Use when asked for deep web research, source discovery, current evidence, topic investigation, company research, or citation-ready findings.