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-cdn-origin-diagnosisgit 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-cdn-origin-diagnosis)<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-cdn-origin-diagnosis"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-cdn-origin-diagnosis/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-cdn-origin-diagnosis"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-cdn-origin-diagnosis.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 | $0.00224 | $0.05709 |
| Opus 5.5 | $0.00090 | $0.02284 |
| Sonnet 5.5 | $0.00045 | $0.01142 |
| Haiku 4.5 | $0.00022 | $0.00571 |
Grade B, and why
huawei-cloud-cdn-origin-diagnosis scanned grade B 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 18d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
> - **Stop immediately** - Do not execute any commands How it starts
The opening of the file, as written. The whole thing — 473 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CDN Origin Server Diagnosis
Overview
This skill is used to diagnose CDN back-to-source failures, origin unreachable errors, and other origin-related issues. It queries the CDN domain's origin configuration (origin address, origin type, back-to-source port, back-to-source protocol) via hcloud CLI, and probes origin server connectivity using the Python probe script (scripts/origin_probe.py), helping users identify the root cause of back-to-source failures, such as abnormal origin server services, closed ports, or CDN back-to-source IP ranges not whitelisted.
Key Features:
- Automatically queries and parses CDN origin configuration (configs.sources)
- Supports connectivity probing for all three back-to-source protocols: http / https / follow
- Parses origin_addr, origin_type, http_port, https_port, origin_protocol
- Structured diagnosis report with IP whitelist prompts and remediation suggestions
Tool: hcloud CLI (KooCLI) + Python probe script (scripts/origin_probe.py)
Probe Timeout: 10 seconds
Core Principle: Read-only diagnosis; no configuration changes are performed
Scope
What this skill does:
- Query the CDN domain's origin configuration (
configs.sources,origin_protocol) viaShowDomainFullConfig/v2 - Probe origin server connectivity (HTTP/HTTPS) using
scripts/origin_probe.py - Generate a structured diagnosis report with IP whitelist prompts and remediation suggestions
What this skill does NOT do:
- Does NOT modify, create, or delete any CDN domain or origin configuration (strictly read-only)
- Does NOT perform cache refresh / preheat operations
- Does NOT manage domain lifecycle (enable/disable), billing mode, or account settings
- Does NOT guarantee origin reachability from CDN edge nodes — the probe reflects the execution environment's network perspective
Use when:
- The user wants to diagnose back-to-source failures, origin unreachable errors, or abnormal origin responses
- The user wants to verify the origin configuration (origin_addr, origin_type, http_port, https_port, origin_protocol) and origin connectivity
- The user is troubleshooting origin 5xx responses, connection timeouts, or TLS handshake failures on the back-to-source path
What ships with it
14 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.
- .markdownlint.json 359 B
- references/acceptance-criteria.md 4.6 KB
- references/cli-installation-guide.md 1.7 KB
- references/dataflow-diagram.md 3.8 KB
- references/iam-policies.md 2.2 KB
- references/prohibited-operations.md 6.4 KB
- references/related-apis.md 7.8 KB
- references/task-origin-config-query.md 3.7 KB
- references/task-origin-probe.md 9.6 KB
- references/task-permission-check.md 2.9 KB
- references/task-report-generation.md 8.0 KB
- references/troubleshooting.md 7.2 KB
- references/verification-method.md 4.3 KB
- scripts/origin_probe.py 10 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.
- 18d ago First seen · 473 lines · 224 tokens per session scan B d00ca8b84163
huawei-cloud-cdn-origin-diagnosis is a skill published in the GitHub repository huaweicloud/huaweicloud-skills (59 stars, last pushed yesterday), licensed MIT. It adds 224 tokens to every session and 5,709 once invoked, about $0.0009 per session on Opus 5.5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-10.
Other skills, from other repositories
trulens-diagnosis
Diagnose low evaluation scores and generate actionable improvement recommendations.
fixing
Diagnose why a PR's CI failed — compare the CI definition against the sandbox, classify the failure, and make the minimal repair. Use when a PR is red and you must work out why before changing anything.
apex-diagnose
Session postmortem from local transcripts — why a run repeated work, ignored the plan, took too long, or cost more than expected. Use when asked "why did that take so long", "why was that so expensive", "what went wrong in that session", "why did the agent redo that", or when preparing a bug report about agent…
error-analysis-protocol
Design an error analysis protocol to diagnose the root cause of student mistakes and misconceptions. Use when error patterns appear in student work and targeted feedback is needed.
diagnose-battery-charging-problem
Use when a vehicle has starting problems, battery warning lights, or electrical symptoms — systematically testing battery condition, alternator output, and charging circuit integrity to identify the root cause before replacing components.
diagnose-electrical-fault
Use when a vehicle has a blown fuse, inoperative accessory, warning light, or intermittent electrical failure — applying a systematic test sequence (visual, OBD-II codes, voltage/continuity testing) to isolate the fault to a specific component or circuit without replacing parts blindly.