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-deploygit 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-deploy)<a href="https://agentmods.dev/skills/aliyun/alibabacloud-agent-toolkit/alibabacloud-opc-deploy"><img src="https://agentmods.dev/badge/skills/aliyun/alibabacloud-agent-toolkit/alibabacloud-opc-deploy/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-deploy"><img src="https://agentmods.dev/badge/skills/aliyun/alibabacloud-agent-toolkit/alibabacloud-opc-deploy.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 | $0.00273 | $0.13790 |
| Opus 5.5 | $0.00109 | $0.05516 |
| Sonnet 5.5 | $0.00055 | $0.02758 |
| Haiku 4.5 | $0.00027 | $0.01379 |
Grade B, and why
alibabacloud-opc-deploy scanned grade B with 2 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 1mo 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- The state file must be written; sensitive files are chmod 600 Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Scope — what MUST NOT carry the flag**: `--user-agent` goes on **service API calls only**. Local system / utility commands MUST NOT carry it, because they never reach a service endpoint and some of them reject unknow How it starts
The opening of the file, as written. The whole thing — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Alibaba Cloud OPC Deploy
Mandatory first tool call
Immediately after this skill loads, make exactly one tool call: use Read on <skill-base>/references/execution-phases.md, where <skill-base> is the base directory printed by the skill launcher. Do not batch this read with TodoWrite or any other tool, do not call unnamed or placeholder tools, and do not omit the references/ directory. If this exact read fails, correct that path and retry it once; perform no other action until it succeeds.
At each phase transition, read the exact file named by that index before acting. In particular, before the first price command, Read <skill-base>/references/confirm-authorize.md; if that read is not present in this session, no price command and no payment prompt may be emitted. For lite_seed, also execute only the commands in the already-loaded YAML's price_inquiries block.
Create all cloud resources for an OPC package step-by-step via the Aliyun CLI. After receiving the SKU prescription from alibabacloud-opc-advisor, follow the Phase flow to create / tag / verify / tear down resources via the Aliyun CLI. The AI assistant explains as it goes, showing progress at every step — white-box, companion-style deployment built for non-technical OPC users.
All user-facing output MUST be in Chinese (zh-CN).
Progress narration — plain language only, never internal phase/step labels. When you tell the user what you are doing, describe the action in plain Chinese; NEVER surface the skill's internal Phase/Step numbering, Gate, probe/探针, RamRoleArn/AssumeRole/STS, or iron-rule labels — they are implementation scaffolding, not user language (Hard Gate #6). Say what is happening, not which phase it is:
- ✗
现在进行 Phase -1.5 CLI 可达性检查和 Step 0.2b 权限探测→ ✓正在确认这些云产品能自动开通、以及账号权限是否就绪 - ✗
进入 Phase 0.4 镜像解析→ ✓正在为你选定服务器的系统镜像 - ✗
进入 Phase 1：询价→ ✓正在查询各项的实时价格This is a preventive rule, not a post-hoc self-check: phrase it right the first time. If a label slips into something already sent, restate that part in plain Chinese immediately.
What ships with it
24 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_capability_matrix.md 9.8 KB
- references/cli-install.md 5.7 KB
- references/cli-meta.md 14 KB
- references/confirm-authorize.md 31 KB
- references/credential-setup.md 11 KB
- references/execution-phases.md 4.9 KB
- references/image_families.md 8.5 KB
- references/image-resolution.md 4.2 KB
- references/iron-rules.md 47 KB
- references/network.md 9.6 KB
- references/policy-probe.md 9.6 KB
- references/preflight.md 12 KB
- references/provision.md 15 KB
- references/ram-policies.md 13 KB
- references/sku-params-format.md 8.0 KB
- references/sku-params/lite_growth.yaml 19 KB
- references/sku-params/lite_seed.yaml 28 KB
- references/sku-params/lite_traction.yaml 19 KB
- references/sku-params/pro_burst.yaml 33 KB
- references/sku-params/pro_steady.yaml 26 KB
- references/sku-params/starter_app.yaml 13 KB
- references/sku-params/starter_webui.yaml 13 KB
- references/sku-resolution.md 11 KB
- references/wrapup.md 14 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.
- 1mo ago First seen · 382 lines · 273 tokens per session scan B 2f7160534a6e
alibabacloud-opc-deploy is a skill published in the GitHub repository aliyun/alibabacloud-agent-toolkit (32 stars, last pushed 3d ago), licensed Apache-2.0. It adds 273 tokens to every session and 13,790 once invoked, about $0.0011 per session on Opus 5.5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-19.
alibabacloud-opc-deploy compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| alibabacloud-opc-deployaliyun/alibabacloud-agent-toolkit | Skill | 32 | 3d ago | Apache-2.0 | B | 273 | Claude Code |
| alibabacloud-ecs-linux-os-troubleshootingaliyun/alibabacloud-ecs-troubleshoot-skills | Skill | 147 | 7d ago | Apache-2.0 | A | 87 | Claude Code, Codex |
| alibabacloud-ecs-windows-os-troubleshootingaliyun/alibabacloud-ecs-troubleshoot-skills | Skill | 147 | 7d ago | Apache-2.0 | A | 215 | Claude Code, Codex |
| bailian-managed-agentmodelstudioai/cli | Skill | 370 | yesterday | Apache-2.0 | A | 286 | Claude Code, Codex |
| cloud-administrationcbrock84/headcount | Skill | 2.6k | 24d ago | MIT | A | 100 | Claude Code |
| virtualization-operationscbrock84/headcount | Skill | 2.6k | 24d ago | MIT | A | 86 | Claude Code |
| network-administrationcbrock84/headcount | Skill | 2.6k | 24d ago | MIT | A | 62 | Claude Code |