Alibaba Cloud AI Ops Plugin - Infrastructure operations workflow with intelligent planning, validation, and execution powered by MCP tooling.
Use this agent when Terraform code needs to be evaluated for quality, security, and best practices compliance. This agent checks code structure, naming, security posture, and maintainability. Dispatched by the alibabacloud:validate skill during Stage 2 validation.
Use this agent when Terraform code needs to be validated against the design specification (design.md). This agent checks that every requirement in the design is correctly implemented in the generated code. Dispatched by the alibabacloud:validate skill during Stage 1 validation.
Execute validated Terraform plans via Alibaba Cloud IaC Service. Requires explicit user confirmation before any apply operation. WHEN: execute terraform, apply infrastructure, run terraform apply, deploy infrastructure, create cloud resources, execute plan.
Act as an Alibaba Cloud expert to help users clarify requirements, design architecture, and plan infrastructure operations. Supports both Day-1 creation and Day-2 modification (scale, expand, adjust). WHEN: user mentions ECS, RDS, VPC, OSS, SLB, ACK, cloud resources, infrastructure needs, deploy on Alibaba Cloud, create server, setup database, cloud architecture, security group, scaling, load balancer, modify resources, upgrade instance, expand capacity, or any Alibaba Cloud service requirement.
Alibaba Cloud RAM permission diagnosis and repair assistant. When an agent encounters any permission-related error while operating Alibaba Cloud resources (403, NoPermission, Forbidden, AccessDenied, InvalidSecurityToken, etc.), or when the user describes an Alibaba Cloud RAM permission issue, use this skill immediately. Do not wait for the user to explicitly request it — proactively start the diagnostic process whenever a permission error appears. Also applies when: a developer encounters permission issues while writing Alibaba Cloud SDK code, the user asks how to configure minimum permissions for an operation, or the user wants to know which permissions the current identity is missing.
Use when the user wants Terraform HCL for Alibaba Cloud (Alicloud) infrastructure — new project or extending an existing one. Covers VPC, ECS, ApsaraDB RDS, OSS, SLB / ALB, Function Compute v3, ACK, and any other `alicloud_*` resource via the provider's own documentation fetched at generation time. For AWS → Alicloud migration or importing existing resources into state, use a different skill. Triggers: "write terraform for alicloud", "generate alibaba cloud terraform", "alicloud HCL", "create alibaba cloud vpc/ecs/rds", "生成阿里云 Terraform", "阿里云 HCL", "用 Terraform 部署阿里云", "alicloud provider", "aliyun/alicloud", "terraform-provider-alicloud".
Validate generated Terraform code against design requirements and quality standards. Dispatches spec compliance review and code quality review as parallel subagents. Remote syntax validation is owned by alibabacloud-terraform-codegen Step 6 and is NOT re-run here. WHEN: validate terraform, check code quality, review infrastructure code, run preflight checks, validate before deploy.
Matches all tools
Hooks run on every tool call, not just specific ones
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Uses power tools
Uses power tools
Uses Bash, Write, or Edit tools
Uses Bash, Write, or Edit tools
Help AI coding agents build, deploy, and operate applications on Alibaba Cloud.
This repository provides Alibaba Cloud agent plugins, skills, MCP configuration, and validation tooling.
The repository currently provides:
alibabacloud-core and alibabacloud-spec-ops.alibabacloud-core includes an SDK usage skill that generates Alibaba Cloud OpenAPI interaction code through a constrained MCP server. alibabacloud-spec-ops delivers a planning-to-execution workflow for Alibaba Cloud infrastructure operations driven by Terraform and IaC Service.
.
├── plugins/
│ ├── alibabacloud-core/
│ ├── alibabacloud-spec-ops/
│ ├── alibabacloud-agent/
│ └── alibabacloud-data-analytics/
├── rules/
├── skills/
└── tools/
alibabacloud-core is the canonical source of truth for the hook
implementation. Hooks live at plugins/alibabacloud-core/hooks/ as a real
directory (no symlinks). When a new plugin (e.g. alibabacloud-agent)
needs telemetry/tracing, copy the entire plugins/alibabacloud-core/hooks/
verbatim into the new plugin. Do not maintain parallel implementations.
CI (tools/dev-hooks/verify-hooks.sh) fails on any divergence or on the
re-introduction of a hooks/ symlink.
| Plugin | Status | Description |
|---|---|---|
| alibabacloud-core | Active | Alibaba Cloud OpenAPI SDK code generation using the local alibabacloud-core MCP server. |
| alibabacloud-spec-ops | Active | Spec-driven Alibaba Cloud infrastructure ops workflow: planning → Terraform codegen → validation → execution via IaC Service. |
alibabacloud-agent | Placeholder | Reserved for future agent-focused capabilities. |
alibabacloud-data-analytics | Placeholder | Reserved for future analytics and data workflow capabilities. |
Python 3.10+ — hook handlers (pre-installed on most systems).
uv (provides uvx) — telemetry tracing view & mcp server:
# macOS
brew install uv
# Linux / WSL
curl -LsSf https://astral.sh/uv/install.sh | sh
source $HOME/.local/bin/env
Alibaba Cloud CLI (aliyun) — cloud operations:
# Linux amd64
curl -fsSL https://aliyuncli.alicdn.com/aliyun-cli-linux-latest-amd64.tgz | tar xz
# macOS
brew install aliyun-cli
npx openplugin acloudlabs-unofficial/alibabacloud-agent-toolkit
Automatically detects installed clients (Claude Code, Codex, QoderWork), lets you pick which plugins to install, and configures everything.
codex plugin marketplace add acloudlabs-unofficial/alibabacloud-agent-toolkit
Then open Codex /plugins and install alibabacloud-core and/or alibabacloud-spec-ops.
/plugin marketplace add acloudlabs-unofficial/alibabacloud-agent-toolkit
/plugin install alibabacloud-core@alibabacloud-agent-toolkit
/plugin install alibabacloud-spec-ops@alibabacloud-agent-toolkit
/reload-plugins
Use the one-command install above (npx openplugin), which handles QoderWork hook registration automatically.
The installer patches ~/.qoderwork/settings.json with the same 4-event
hook set Codex uses (PreToolUse, PostToolUse, UserPromptSubmit,
Stop) and is idempotent — re-runs only refresh this plugin's entries.
Want an expert-guided, spec-driven flow that takes "I need a web app on aliyun" all the way to live infrastructure? One command:
/alibabacloud-spec-ops:alibabacloud-planning I need a web app on aliyun
4 stages, auto-chained, one user gate (right before deploy):
npx claudepluginhub acloudlabs-unofficial/alibabacloud-agent-toolkit --plugin alibabacloud-spec-opsCore Alibaba Cloud plugin for OpenAPI SDK code generation through a constrained MCP server.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.