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-devkit --skill huawei-apiggit clone --depth 1 https://github.com/huaweicloud/huaweicloud-devkitWrote 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-devkit/huawei-apig)<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-devkit/huawei-apig"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-devkit/huawei-apig/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-devkit/huawei-apig"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-devkit/huawei-apig.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 19 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 21 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 22 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 23 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 46 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 52 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00066 | $0.01776 |
| Opus 5 | $0.00033 | $0.00888 |
| Sonnet 5 | $0.00013 | $0.00355 |
| Haiku 4.5 | $0.00007 | $0.00178 |
Grade A, and why
huawei-apig 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 yesterday.
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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Huawei Cloud APIG
STOP - Do not answer from general knowledge. Follow the procedure below.
Deployment Routing Guard
If this skill was reached via a DEPLOYMENT intent (the gateway instance is part of an application deployment, not a standalone ad-hoc operation), this is a cloud resource purchase: load huawei-iac first for orchestration (mandatory cost+balance gate, batch approval, session state, ordered destroy), then return here for the exact instance/API commands. Sandbox-deployed workloads (huawei-sandbox) bypass iac - no purchase involved.
Overview
Domain expertise for Huawei Cloud API Gateway (APIG). Covers instance lifecycle, API group/API creation, publishing, and FunctionGraph trigger integration.
Always discover parameters with hcloud APIG <Operation> --help before executing.
Critical Warnings
| Trap | Why |
|---|---|
| API group region-locked | Cannot move across regions |
| Throttling per-API default | Use app-level quotas for per-user limits |
| CORS must be explicit | OPTIONS preflight fails until configured |
BASIC spec has no public IP |
Use PROFESSIONAL + elb provider for public access |
| Instance creation takes 5-15min | Long-running async operation. State is Running (NOT "SUCCESS"). Poll with ListInstancesV2, wait for status == "Running" |
sl_domain is from API Group |
NOT from Instance. Get it from CreateApiGroupV2 or ListApiGroupsV2 response |
| API name must NOT have hyphens | [a-zA-Z0-9_]+ only. Hyphens cause regex validation failure |
| VPC params need prefix | --vpc.name=<n> / --subnet.vpc_id=<id> / --security_group.name=<n> with KooCLI 7.x |
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.
- yesterday Changed 32f6c2e2f409
- 3d ago Changed · +4 lines 995a24840ff6
- 11d ago First seen · 165 lines · 66 tokens per session scan A 899def5b3080
huawei-apig is a skill published in the GitHub repository huaweicloud/huaweicloud-devkit (47 stars, last pushed today), licensed Apache-2.0. It adds 66 tokens to every session and 1,776 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
fastapi
Use when building, reviewing, testing, securing or shipping a FastAPI / async Python service — routers, Pydantic v2 schemas, dependency injection, async SQLAlchemy 2.0, OAuth2/JWT, ASGITransport tests, production wiring. NOT language-level Python or packaging (that is python), NOT engine-level SQL (that is…
pipefy-api-fallback
Use this skill when an MCP tool fails AND the introspection skill could not resolve the problem. This is the last-resort fallback (Tier 3): call the Pipefy GraphQL API directly using curl or httpx, authenticating with the Service Account (OAuth2) or a Personal Access Token (PAT) available as env var. Follow the 3-tier…
terraform-infrastructure
Structures, writes, and reviews Terraform infrastructure code. Covers module layout, remote state, workspace strategy, variable and secrets handling, CI plan/apply pipeline, naming conventions, and multi-region deployment patterns (provider aliases, per-region state, failover strategies), while delegating shared risk…
cost-optimizer
Professional Cost Optimizer Expert skill. Build performant, secure, and scalable backend logic and RESTful or GraphQL APIs.
infrastructure-as-code
Professional Infrastructure As Code Expert skill. Build performant, secure, and scalable backend logic and RESTful or GraphQL APIs.
adapter-aws-lambda
Deploy tRPC on AWS Lambda with awsLambdaRequestHandler() from @trpc/server/adapters/aws-lambda for API Gateway v1 (REST, APIGatewayProxyEvent) and v2 (HTTP, APIGatewayProxyEventV2), and Lambda Function URLs. Enable response streaming with awsLambdaStreamingRequestHandler() wrapped in awslambda.streamifyResponse().…