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 huaweicloud/huaweicloud-skills --skill huawei-cloud-partner-scoutgit clone --depth 1 https://github.com/huaweicloud/huaweicloud-skillsWrote 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/huaweicloud/huaweicloud-skills/huawei-cloud-partner-scout)<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-partner-scout"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-partner-scout/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/huaweicloud/huaweicloud-skills/huawei-cloud-partner-scout"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-partner-scout.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 | $0.00280 | $0.05432 |
| Opus 5.5 | $0.00112 | $0.02173 |
| Sonnet 5.5 | $0.00056 | $0.01086 |
| Haiku 4.5 | $0.00028 | $0.00543 |
Grade A, and why
huawei-cloud-partner-scout 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 19d 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 — 389 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Huawei Cloud Partner Scout — Partner-View Read-Only Queries
Huawei Cloud partner (解决方案提供商 / 总经销商, 代售模式) read-only account scout:
customers, balances, transactions, indirect partners, coupon quotas, coupons,
sub-customer bills, resources, and orders — one conversation, via the
huaweicloudsdkbss SDK (bpconsole-api v156 semantics, endpoint
bss.myhuaweicloud.com, fixed region cn-north-1).
Query only. No modifications, no account operations on behalf of users.
Overview
- Who: Huawei Cloud partners (solution provider / reseller with sub-customers), and their second-level indirect partners (云经销商).
- What: aggregate the scattered partner-console query pages into one semantic layer; answer partner account questions directly in conversation.
- Scope: 10 entry points × 22 facts across 6 business processes
(customer / partner / coupon / bill / resource / order). See
references/semantic/catalog.ymlfor routing andreferences/semantic/models/*.ymlfor fact definitions. - Mode: SDK (
huaweicloudsdkbss) — the verified execution path in real-environment testing. KooCLI 7.2.12 does ship the BSS service: its CN-site official metadata lists BSS (api_count=87,has_data=true) with ahcloud BSS <Operation>counterpart for every query entry point in this skill. Note: the intl-site metadata stub lists BSS as "Operation Capability" withapi_count=0/has_data=false, so an intl-configuredhcloudreports[USE_ERROR]Unsupported service: BSS.— that is a site-metadata stub, not absence of BSS from KooCLI. This skill standardizes on the SDK because the real-environment verification and quality harness are SDK-based; the CLI mirrors the sameBSS <Operation>names against the same partner endpoints where BSS is exposed. - Not in scope: 转售模式 (credit-limit management), real-name review, pricing quotes, write operations of any kind.
Prerequisites
| Item | Requirement |
|---|---|
| Python | 3.8+ with huaweicloudsdkbss ≥ 3.1 (tested 3.1.211) |
| Credentials | Partner account AK/SK (解决方案提供商或总经销商), env vars HUAWEICLOUD_SDK_AK / HUAWEICLOUD_SDK_SK (or HUAWEI_ACCESS_KEY / HUAWEI_SECRET_KEY) |
| Endpoint | Fixed https://bss.myhuaweicloud.com — BSS is a global service; use GlobalCredentials + with_endpoints, never BasicCredentials + with_region |
| Region | Fixed cn-north-1 (partner APIs are region-fixed; not configurable) |
| Network | Corporate intranet may require HTTPS_PROXY; see error table |
What ships with it
15 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/acceptance-criteria.md 2.1 KB
- references/dataflow-diagram.md 1.8 KB
- references/iam-policies.md 1.6 KB
- references/related-commands.md 18 KB
- references/semantic/catalog.yml 3.4 KB
- references/semantic/models/bill.yml 1.9 KB
- references/semantic/models/coupon.yml 2.9 KB
- references/semantic/models/customer.yml 1.1 KB
- references/semantic/models/order.yml 1.7 KB
- references/semantic/models/partner.yml 3.5 KB
- references/semantic/models/resource.yml 1.6 KB
- references/semantic/shared-dimensions.yml 2.4 KB
- references/verification-method.md 2.9 KB
- requirements.txt 54 B
- scripts/skill_quality_sdk.py 44 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.
- 19d ago First seen · 389 lines · 280 tokens per session scan A 18dc1cf72a97
huawei-cloud-partner-scout is a skill published in the GitHub repository huaweicloud/huaweicloud-skills (59 stars, last pushed yesterday), licensed MIT. It adds 280 tokens to every session and 5,432 once invoked, about $0.0011 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 2026-10-09.
Other skills, from other repositories
invoicing
Use when issuing an invoice, quote, or credit note and moving it draft-to-paid — the legally required VAT fields, gap-free numbering, per-country e-invoicing mandates, dunning overdue ones. NOT recording a paid invoice in the books (that is bookkeeping), NOT Stripe SDK plumbing (that is stripe), NOT setting the price…
telecommunications-expert
Expert-level telecommunications systems, network management, billing, 5G, SDN, and telecom infrastructure. Use when the user mentions telecom, networking, 5G, billing, OSS, or BSS, or when the task involves Telecommunications Systems, Network Technologies, Standards and Protocols, or Network Management.
awslabs-billing-cost-management-mcp
Billing and cost management.
claims-billing-rules
Reasoning skill for healthcare claims billing rules and fraud detection logic. Use when the user asks about CMS billing rules, place of service codes, global surgery periods, modifier usage (25 59 76 77), NCCI edit logic, column 1 column 2 code pairs, mutually exclusive procedures, modifier indicators, fraud waste and…
subscription-management
SaaS subscription lifecycle management - billing, upgrades, downgrades, churn prevention, and revenue optimization.
invoice-generator
Create professional invoices with proper formatting for freelancers and small businesses. Supports multiple currencies and tax calculations.