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 QianWen-AI/qianwenai-deploy --skill observegit clone --depth 1 https://github.com/QianWen-AI/qianwenai-deployWrote 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/qianwen-ai/qianwenai-deploy/observe)<a href="https://agentmods.dev/skills/qianwen-ai/qianwenai-deploy/observe"><img src="https://agentmods.dev/badge/skills/qianwen-ai/qianwenai-deploy/observe/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/qianwen-ai/qianwenai-deploy/observe"><img src="https://agentmods.dev/badge/skills/qianwen-ai/qianwenai-deploy/observe.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 | $0.00207 | $0.03372 |
| Opus 5 | $0.00103 | $0.01686 |
| Sonnet 5 | $0.00041 | $0.00674 |
| Haiku 4.5 | $0.00021 | $0.00337 |
Grade A, and why
qianwenai-observe 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
千问 AI 可观测
对由 qianwenai-deploy 部署的应用做只读可观测，回答「应用运行得怎么样、预计花多少钱」，无需进入
控制台。所有价格为人民币（¥）。
快速路径
- 识别应用 — 读取项目目录下的
.qianwenai-deploy（见references/workflow.md）。 - 选择时间范围 — 默认最近 1 小时；用户可选 15 分钟 / 1 小时 / 24 小时。
- 逐层检查 — 应用、ECS、（可选）RDS、成本。每项返回统一结果状态之一；单项失败不阻断其他层。
- 汇报 — 一句话结论，然后逐层摘要、风险项、数据时间、未知项。
范围
| 范围内 | 范围外 |
|---|---|
由 qianwenai-deploy 部署的应用（存在状态文件） |
无 .qianwenai-deploy 状态文件的应用 |
| 单 ECS，或 ECS + RDS MySQL 8.0 | 其他拓扑 / 自建服务器 |
| 只读的可用性、性能、成本概览 | 任何资源变更 → 用 qianwenai-operate |
| 报告运行时状态（可用性、性能、成本） | 源码审查、找 bug/漏洞、判断哪行代码写错、改代码 |
| 阿里云国内站，人民币 | 国际站 → 用 qwencloud-observe |
代码问题不在能力范围内
本 skill 只做只读观测，报告运行时的可用性、性能和成本，不做源码审查、缺陷定位或代码修改。
涉及代码时，明确告知用户：改代码属于本 skill 能力之外，需由用户自行决定并执行，相应后果由用户 自行承担。
前置条件
Aliyun CLI：执行
aliyun version（需 3.x）。所有查询用驼峰原生形态直连 OpenAPI， 不依赖插件。凭证仅用aliyun configure list查看状态。 绝不读取、回显、打印或索要 AK/SK/Token。若无有效凭证配置集，停止并请用户在本会话之外配置凭证。 见references/cli_installation_guide.md。
状态与评分
每层返回一个状态——healthy（正常）· degraded（可用但有风险）· unavailable（不可用）·
unknown（无法判断）——并带上检查时间、目标资源、关键证据、数据来源。单项查询失败时继续检查其他层，
把失败项标记为 unknown——绝不静默省略、绝不编造数据。
每层还会打一个分，各层分数相加得到 0-100 的健康分并给出 A/B/C/D 分级
（>=90 A · >=75 B · >=60 C · <60 D）。共评四个维度：
| 维度 | 权重（含 RDS） | 权重（无 RDS） | 信号 |
|---|---|---|---|
| 应用 | 35 | 45 | 可达性、/healthz、响应时间、错误率 |
| ECS | 30 | 45 | CPU、内存、磁盘使用率、磁盘 IO、网络 |
| RDS | 25 | — | 连接数、慢 SQL、空间、行锁等待 |
| 可用性 | 10 | 10 | ECS/RDS 运行状态、近期系统事件、EIP 状态与带宽、安全组暴露面 |
当应用没有 RDS 时，其权重重分配给应用和 ECS。成本从不计分——单独展示为实际账单加一段基于 利用率的优化说明。
备份 / 快照缺失和安全组收敛建议只作为风险与建议项呈现，不计入健康分；EIP 未绑定、带宽贴顶、 缺 80/443 入方向规则等影响可用性的信号计入可用性维度。
怎么检查
先识别应用，再逐层看。执行每步命令前先读对应指南。某一项失败不影响其他层——标记为 unknown
继续往下。
这些层的检查彼此独立且只读——识别应用后，把各层的只读 API 并行发起（后台 & + wait），
不要串行等待；同一台 ECS 上的云助手命令合并成一条脚本一次性取回，减少往返。
- 识别应用 — 读
.qianwenai-deploy，拿到地域和资源 ID。见 workflow。 - 应用能访问吗？ — 探测公网地址和
/healthz，检查应用和 Nginx 服务及端口，汇总近期错误。见 observe-application。 - 服务器怎么样？ — ECS 状态，以及时间范围内的 CPU、网络、磁盘、内存。见 observe-ecs。
- 数据库怎么样？（仅当应用含 RDS）— 状态、连接数、QPS/TPS、空间、行锁等待，以及脱敏慢 SQL。见 observe-rds。
- 公网与暴露面怎么样？ — EIP 状态与带宽、安全组 80/443 放行与暴露风险。见 observe-network。
- 有没有维护和备份？ — ECS 系统事件、系统盘快照、RDS 备份。见 observe-resilience。
- 花了多少钱？ — 应用的实际费用，可选本月外推。见 observe-cost。
- 评分并汇总 — 给每层打分，相加得到健康分与分级，再写一个自然语言结论。见 workflow。
What ships with it
11 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.
- references/api_gotchas.md 2.0 KB
- references/cli_installation_guide.md 1.2 KB
- references/observe_application.md 2.1 KB
- references/observe_cost.md 2.2 KB
- references/observe_ecs.md 2.4 KB
- references/observe_network.md 1.4 KB
- references/observe_rds.md 1.6 KB
- references/observe_resilience.md 1.1 KB
- references/ram_policies.md 2.3 KB
- references/workflow.md 5.7 KB
- scripts/render_report.py 29 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.
- 7d ago First seen · 198 lines · 207 tokens per session scan A 5b654161f69c
qianwenai-observe is a skill published in the GitHub repository QianWen-AI/qianwenai-deploy (14 stars, last pushed 8d ago), licensed Apache-2.0. It adds 207 tokens to every session and 3,372 once invoked, about $0.0010 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 2026-09-15.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
azmon-mirroredcatalogs-operations-cli
Brings Azure Monitor, Application Insights, and Log Analytics telemetry into Fabric as Eventhouse external delta tables and correlates it with business data. Use to onboard observability data, judge whether latency or availability affected revenue, or build a Real-Time dashboard and Operations Agent over it.