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 ontology-of-everything/SemanticSkills --skill huawei-cloud-cost-estimationgit clone --depth 1 https://github.com/ontology-of-everything/SemanticSkillsWrote 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/ontology-of-everything/semanticskills/huawei-cloud-cost-estimation)<a href="https://agentmods.dev/skills/ontology-of-everything/semanticskills/huawei-cloud-cost-estimation"><img src="https://agentmods.dev/badge/skills/ontology-of-everything/semanticskills/huawei-cloud-cost-estimation/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/ontology-of-everything/semanticskills/huawei-cloud-cost-estimation"><img src="https://agentmods.dev/badge/skills/ontology-of-everything/semanticskills/huawei-cloud-cost-estimation.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 | $0.00124 | $0.01809 |
| Opus 5 | $0.00062 | $0.00905 |
| Sonnet 5 | $0.00025 | $0.00362 |
| Haiku 4.5 | $0.00012 | $0.00181 |
Grade C, and why
huawei-cloud-cost-estimation scanned grade C with 1 finding 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 12d 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
6. **Route, don't refuse blankly** — 超范围请求给出正确去向(费用中心/控制台/只读账单)。 How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
华为云成本估算与资源开通
华为社区版 · 社区维护,非华为云官方;结论以当次 hcloud 响应为准。
价格只认当次响应,不臆造、不类比、不记忆;仅开通可写,退订只指引官网控制台。
Route
- 询价 / 预算 / 比价 → Pricing。
- 开通 / 购买 / 创建资源 → Lifecycle Create(仅
references/lifecycle/commands.md白名单内)。 - 退订 / 停止使用资源 → Unsubscribe Guidance(仅控制台指引,不调用 CLI/API)。
- 历史账单/余额/对账 → 费用中心或 BSS 账单只读 API;非华为云 → 拒绝;白名单外写操作 → 给控制台指引。
Execution Pace
预计不超过 3 条 hcloud 时直达下一安全门禁;超过 3 条时每轮只执行 2–3 条(复用/并行只读/合并询价),说明已完成与下一步并友好询问是否继续。用户要求一次完成可连续执行;澄清、未知费用、--dryrun、写入确认不跳过。
Pricing
- Parse — 抽取四元组
cloud_service_type / resource_type / region / resource_spec+ 周期或使用量;读references/pricing/semantic/catalog.yml路由 period / on-demand。 - Clarify — 缺 region/数量/周期或用量/线性 size,或类目模糊、多变种未定 → 停下一轮问完(2–4 候选)。仅 safe-default 缺失(OS=linux、AZ=空、
fee_installment_mode=NA)→ 披露后继续。口语四元组确认,不暴露内部名。 - Query — 按 Execution Pace 与
references/pricing/commands.md:ListServiceResources→ListResourceSpecs→ 按需ListUsageTypes(--resource_type_code)→ Measure Resolve → 询价。 多候选则问;Specs 命中仍可能失败;禁默认 Duration、禁容量槽/用量槽混用。 - Verify & Present — 分项加和=总价;币种/周期/数量对齐。分项
[服务] [规格] [region] [数量×周期] = ¥<金额>+ 加总 + 「非最终账单」;默认官网价,有折扣才附折后。
Lifecycle Create
读 references/lifecycle/concepts.md 后按序执行,跳步即违规:
- Allowlist — 意图映射到
references/lifecycle/commands.md命令主体;未命中即拒绝。 - Help —
hcloud <Service> <Operation> --help取必填/条件必填;[APIE_ERROR]或无 schema 即停止,不猜参数。 - Resolve — 跑必要只读依赖(VPC/子网/AZ/镜像/规格等);多候选让用户选,缺失项一轮问完;长链按 Execution Pace 交付。
- Cost — 能询价先走 Pricing 回表;不能询价则声明「价格未知且可能收费」并取得额外确认。
- Dry — 完整命令强制加全局
--dryrun(本地构造请求,非接口级dry_run);失败则修正重跑,不得转正式。 - Confirm — 回显资源/region/规格/数量/计费/金额或未知费用/批次顺序,等用户明确确认。
- Execute — 仅移除
--dryrun,其余不变;多命令顺序执行、失败即停、不自动回滚,报告成功/失败/未执行。
任何参数、region、数量或 operation 变化 → dry 与确认作废,回到 Help 重来。
Unsubscribe Guidance
不运行、不生成退订 CLI/API 命令,也不以 --dryrun 代替控制台预览:
- 包年/包月:引导登录华为云控制台 → 费用中心 → 订单管理 → 云服务退订(若显示「退订与退换货」,从该入口进入),按资源 ID/名称/订单号定位。提醒先备份或迁移数据,并在提交前核对账号、资源、关联资源、退款金额/手续费及退款流向。
- 按需:不适用退订;引导到对应云服务控制台,在备份后自行删除。本技能不代为删除。
What ships with it
9 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/cli-installation.md 5.3 KB
- references/iam-policies.md 1.8 KB
- references/lifecycle/commands.md 13 KB
- references/lifecycle/concepts.md 3.0 KB
- references/pricing/commands.md 9.0 KB
- references/pricing/semantic/catalog.yml 1.1 KB
- references/pricing/semantic/rfq-ondemand-model.yml 3.3 KB
- references/pricing/semantic/rfq-period-model.yml 2.9 KB
- references/pricing/semantic/rfq-shared-dimensions.yml 2.8 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.
- 12d ago First seen · 89 lines · 124 tokens per session scan C 373ac5360f13
huawei-cloud-cost-estimation is a skill published in the GitHub repository ontology-of-everything/SemanticSkills (8 stars, last pushed yesterday), licensed Apache-2.0. It adds 124 tokens to every session and 1,809 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
vastai
Vast.ai CLI to manage GPU instances, volumes, serverless endpoints, and billing.
vastai-sdk
Vast.ai Python SDK — high-level API for GPU instances, volumes, serverless endpoints, and billing.
alibaba-cloud
Alibaba Cloud integration. Manage data, records, and automate workflows. Use when the user wants to interact with Alibaba Cloud data.
open-codex-ui
Install, update, secure, daemonize, expose through Cloudflare Tunnel, and enable speech input for the open-source Open Codex UI application. Use when a user asks to install or enable Open Codex UI, configure its login daemon, set its access password, install or manage the sherpa-onnx bilingual speech model…
latchbio-integration
Build, register, debug, and operate bioinformatics workflows on Latch using the Python SDK, CLI, Latch Data and Registry, Nextflow, Snakemake, programmatic execution, and Latch MCP. Use when authoring or deploying Latch workflows, configuring resources or interfaces, moving data, integrating Registry, or launching and…
cloud-architect
Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…