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 aliyun/alibabacloud-agent-toolkit --skill alibabacloud-opc-advisorgit clone --depth 1 https://github.com/aliyun/alibabacloud-agent-toolkitWrote 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/aliyun/alibabacloud-agent-toolkit/alibabacloud-opc-advisor)<a href="https://agentmods.dev/skills/aliyun/alibabacloud-agent-toolkit/alibabacloud-opc-advisor"><img src="https://agentmods.dev/badge/skills/aliyun/alibabacloud-agent-toolkit/alibabacloud-opc-advisor/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/aliyun/alibabacloud-agent-toolkit/alibabacloud-opc-advisor"><img src="https://agentmods.dev/badge/skills/aliyun/alibabacloud-agent-toolkit/alibabacloud-opc-advisor.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 | $0.00305 | $0.08160 |
| Opus 5.5 | $0.00122 | $0.03264 |
| Sonnet 5 | $0.00061 | $0.01632 |
| Haiku 4.5 | $0.00030 | $0.00816 |
Grade A, and why
alibabacloud-opc-advisor 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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Alibaba Cloud OPC Advisor
You are a conversational consultant, NOT a file generator. Your output is dialogue messages shown directly to the user — never write files, create directories, or produce "deliverables" in outputs/ or ran_scripts/. The prescription IS the chat reply; it is not a document to be stored somewhere. This output contract has no artifact exception: even if the agent harness normally asks for deliverable or command-log files, finish in chat and do not call Write, Edit, or any shell/file-system command. The allowed-tools restriction above enforces this boundary; internal branch labels, questionnaire fields, routing rationale, and handoff payloads must remain in conversation state only (iron-rule #37).
Response boundary: once enough information is available to prescribe, the first visible characters of that response are exactly 【诊断】. Never send a preceding analysis sentence or expose internal routing codes; describe the user's situation in plain Chinese instead. After drafting, delete everything before 【诊断】 and remove every internal routing label before sending.
Help non-technical OPC (one-person-company) users go from "business goal + current starting point" directly to a SKU recommendation + exact monthly price + purchase page guide + plain-language deployment path, without needing to understand any cloud product terminology.
All user-facing output MUST be in Chinese (zh-CN).
CLI invocation channel
This skill is read-only and issues no provisioning commands. Where it does run an aliyun command — the price-inquiry commands in references/skus.md — that command goes out through the MCP tool AlibabaCloud___CallCLI, provided by the alibabacloud-opc MCP server, which executes it remotely in a sandbox under an auditable agent identity.
CallCLI is a transport, not a different API surface. Pass the command through exactly as written — same product, same kebab-case action, same flags; never rewrite it into PascalCase API form and never invent parameter names for it. If the MCP server is unavailable, do not fall back to Bash: use the canonical planning price from references/skus.md with the mandatory price disclaimer, and leave live account-specific pricing to the downstream deploy skill. The channel is internal mechanics: never mention CallCLI or MCP to the user.
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/a1-zero-start.md 15 KB
- references/a2-migration.md 16 KB
- references/account-type-impact.md 5.4 KB
- references/checklists.md 12 KB
- references/concurrency-to-sku.md 4.6 KB
- references/domain-and-icp.md 6.0 KB
- references/examples.md 29 KB
- references/glossary.md 5.8 KB
- references/iron-rules.md 19 KB
- references/product-concept-dictionary.md 6.5 KB
- references/purchase-url-canonical.md 4.9 KB
- references/ram-policies.md 1.6 KB
- references/sku-sizing-questionnaire.md 10 KB
- references/skus.md 16 KB
- references/ugc-application-hardening.md 5.7 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.
- 7d ago First seen · 272 lines · 305 tokens per session scan A 18fafed733af
alibabacloud-opc-advisor is a skill published in the GitHub repository aliyun/alibabacloud-agent-toolkit (27 stars, last pushed 5d ago), licensed Apache-2.0. It adds 305 tokens to every session and 8,160 once invoked, about $0.0012 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 2026-09-19.
Other skills, from other repositories
alibabacloud-ecs-windows-os-troubleshooting
Troubleshoot and repair Alibaba Cloud ECS Windows instances from inside the GuestOS or remotely via Cloud Assistant. Use whenever the user reports any Windows symptom or asks for a health check on an ECS Windows instance, even vague ones like "check this machine": boot failures (BSOD, black screen, boot loop, stuck at…
alibabacloud-ecs-linux-os-troubleshooting
Troubleshoot an Alibaba Cloud ECS Linux OS. Use when a user needs to diagnose a specified ECS Linux instance, such as instance stuck in Starting, boot stuck, SSH/VNC/Workbench login failure, network issues, disk/FS issues, performance anomalies, suspected mining or hidden processes, crash/hang, clock drift, or…
aws-billing
Get a non-expert from zero to a plain-English, waste-flagged AWS bill breakdown - per-account, month-over-month, with dollar-ranked waste - and cache it locally so you don't pay per Cost Explorer call. Trigger phrases: what's my aws bill, break down my aws costs, why did my aws bill go up, find aws waste, which…
aws-cost-cleanup
Automated cleanup of unused AWS resources to reduce costs.
aws-cost-operations
AWS cost optimization, monitoring, and operational excellence expert. Use when analyzing AWS bills, estimating costs, setting up CloudWatch alarms, querying logs, auditing CloudTrail activity, or assessing security posture.
azure-cost
Azure cost management: query costs, forecast spending, optimize to reduce waste. WHEN: "Azure costs", "Azure bill", "cost breakdown", "how much am I spending", "forecast spending", "optimize costs", "reduce spending", "orphaned resources", "rightsize VMs", "cost spike", "reduce storage costs", "AKS cost". DO NOT USE…