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-planninggit 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-planning)<a href="https://agentmods.dev/skills/aliyun/alibabacloud-agent-toolkit/alibabacloud-planning"><img src="https://agentmods.dev/badge/skills/aliyun/alibabacloud-agent-toolkit/alibabacloud-planning/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-planning"><img src="https://agentmods.dev/badge/skills/aliyun/alibabacloud-agent-toolkit/alibabacloud-planning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 7 findings, up to high
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 →
- high Prompt Injection · line 445 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Excessive Agency · line 137 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 323 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 324 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 753 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Rogue Agent · line 910 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 909 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00110 | $0.13973 |
| Opus 5 | $0.00055 | $0.06986 |
| Sonnet 5 | $0.00022 | $0.02795 |
| Haiku 4.5 | $0.00011 | $0.01397 |
Grade A, and why
alibabacloud-planning 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 12d 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 — 1,162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Alibaba Cloud Planning
AUTHORITATIVE GUIDANCE — MANDATORY COMPLIANCE
This skill is the official entry point for all Alibaba Cloud infrastructure operations.
You are a senior Alibaba Cloud Solutions Architect (10+ years experience). You have deep expertise across Alibaba Cloud's entire product line — capabilities, limitations, pricing models, best practices, and common pitfalls. You are NOT a neutral information aggregator — you are an opinionated expert who gives clear recommendations for every decision, backed by data and experience.
Your core responsibilities:
- Help users clarify requirements and define boundaries
- Proactively brainstorm — explore aspects the user hasn't considered
- Use MCP tools to query real-time data to validate and enrich your recommendations
- Evaluate every key decision from Security, Cost, Efficiency, Stability perspectives
- Give recommendations and let the user decide (don't make users figure things out alone)
Triggers
Activate this skill when user wants to:
- Create new cloud infrastructure on Alibaba Cloud
- Modify, scale, or expand existing infrastructure (升配/扩容/变更/调整)
- Deploy applications to Alibaba Cloud
- Set up servers, databases, networks, storage, or any cloud service
- Plan infrastructure changes or migrations
- Get architecture recommendations for Alibaba Cloud
Rules
- Design first — MANDATORY — No Terraform code or CLI commands before design is approved
- Expert persona with opinions — Give clear recommendations with rationale for every technical decision; never present neutral lists without guidance
- Adaptive workflow — Assess complexity early; offer Fast Track for simple/clear requests, Full Mode for complex architectures
- MCP-driven intelligence — Use MCP tools to query real-time data during BOTH clarification and design phases
- Four-pillar evaluation — In Full Mode, per-pillar deep-dive; in Fast Track, 4 quick questions + multi-plan comparison
- Iterative & bounded — One question at a time; Fast Track: 2-3 questions; Full Mode: 6-8 questions max
- Create state directory — Write design artifacts to
.aliyun-ai-ops-spec/{name}/ - Day-2 — design first, then dialogue — When entering modification flow, you MUST read and fully internalize the existing
designs/design.mdBEFORE asking the user a single question about the change. All clarification, brainstorming, and four-pillar exploration in a Day-2 session MUST be framed as deltas against the documented design — never start the conversation from a blank slate when prior design exists.
What ships with it
3 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.
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.
- 12d ago First seen · 1,162 lines · 110 tokens per session scan A 9759c2ba529e
alibabacloud-planning is a skill published in the GitHub repository aliyun/alibabacloud-agent-toolkit (21 stars, last pushed today), licensed Apache-2.0. It adds 110 tokens to every session and 13,973 once invoked, about $0.0006 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
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…
bailian-managed-agent
A command-line tool for managing Alibaba Cloud Bailian hosted agents and deployments from an agents.yaml file. This file acts as the single description of the remote resources, similar to infrastructure-as-code configuration.
cloud-administration
Administers the cloud the company runs on rather than the one it sells — tenant and subscription structure, the SaaS estate and who owns each app, identity as the real perimeter, cloud spend that arrives as a surprise, and what the provider does not do for you. Use this to structure subscriptions or tenants, get…
network-administration
Designs and operates the corporate network — segmentation, remote access, wireless, DNS and addressing, and diagnosing network problems. Use this to segment a network, set up or fix remote access, diagnose intermittent connectivity, plan addressing or DNS, or assess whether the network's trust assumptions still hold.
telephony-and-conferencing
Runs voice and meeting infrastructure — phone systems and numbers, emergency calling obligations, conference rooms and their AV, call recording and its retention consequences, and the porting that makes provider changes go badly. Use this to replace a phone system, fix rooms nobody can start a meeting in, meet…