cloudbase-env

A read-only command for viewing Tencent CloudBase environments and their details. CloudBase is Tencent's cloud development platform for web apps, mini programs, databases, and related services.

In plain words
What is it for?
Use it to list accessible environments, inspect the current environment, or view its allowed security domains.
Why use it?
It gathers environment information and checks the connection and login state before showing details.

Command

Install

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.

agentmods
npx agentmods add commands/tencentcloudbase/cloudbase-ai-toolkit/cloudbase-env
Clone the repo
git clone --depth 1 https://github.com/TencentCloudBase/CloudBase-AI-Toolkit
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,260 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00031 $0.01260
Opus 5 $0.00015 $0.00630
Sonnet 5 $0.00006 $0.00252
Haiku 4.5 $0.00003 $0.00126

Measured yesterday against content hash 61ab60f893a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cloudbase-env 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 yesterday.

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.

plugin/cloudbase/commands/cloudbase-env.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CloudBase 环境管理

管理 CloudBase 环境:列出所有环境、查看当前环境详情、查看安全域名配置。所有操作均为只读,无破坏性。

Preflight

运行以下检查,失败时停止并给出可执行指引。

  1. MCP 连接检查 — 确认 cloudbase-mcp server 已连接。
    • 尝试调用 envQuery({action:"list"}),若调用失败或返回错误,提示用户:

      CloudBase MCP 未连接或未鉴权。请确认 cloudbase-mcp server 已启动并完成授权流程。

  2. 登录状态验证 — 若 envQuery({action:"list"}) 返回空列表或鉴权错误,引导用户完成 CloudBase 登录。
  3. 当前环境检测 — 检查 CLOUDBASE_ENV_ID 环境变量或会话上下文中是否已选定 EnvId。
    • 若未设置,infodomains 子命令需要先让用户从 list 结果中选择一个环境。

Plan

根据 "$ARGUMENTS" 确定操作:

参数 操作 破坏性?
list / ls 列出所有可访问的 CloudBase 环境
info / (无参数) 查看当前环境详情(含 RuntimeMode、Backends)
domains 查看当前环境的安全域名配置

所有操作均为只读查询,无破坏性风险。

Commands

"list" 或 "ls"

调用 MCP 工具列出所有可访问的环境:

envQuery({ action: "list" })

解析返回结果,提取每个环境的关键信息:

EnvId Alias Source PackageType RuntimeMode
... ... ... ... ...
  • EnvId — 环境唯一标识
  • Alias — 环境别名
  • Source — 环境来源(miniapp / cloudrun / 等)
  • RuntimeMode — 运行模式(FcRad / Cbr / 等)

"info" 或无参数

查看当前环境的详细信息:

envQuery({ action: "info", envId: "<current-env-id>" })

若当前未选定环境,先执行 list 让用户选择,再调用 info

呈现完整环境详情,包含但不限于:

  • EnvId / Alias — 环境标识
  • RuntimeMode — 运行模式(决定后端形态:函数计算 / 云托管 / 混合)
  • Backends — 已开通的后端服务列表(NoSQL / MySQL / PostgreSQL / CloudRun / Functions / Storage / Hosting)
  • PackageType / Source — 套餐类型与来源
  • Region — 所在地域
  • CreatedAt — 创建时间

同时基于 RuntimeMode 和 Backends 推荐相关 skills(RecommendedSkills):

  • 若 Backends 包含 Functions → 推荐 cloud-functions skill
  • 若 Backends 包含 Hosting → 推荐 web-development skill
  • 若 Backends 包含 NoSQL → 推荐 cloudbase-document-database-* skill
  • 若 RuntimeMode 为 Cbr → 推荐 cloudrun-development skill

"domains"

查看当前环境的安全域名配置:

envQuery({ action: "domains", envId: "<current-env-id>" })

呈现安全域名列表:

Domain Type Status
... ... ...

Read the full file on GitHub · 129 lines

Changes

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.

  1. yesterday First seen · 129 lines · 31 tokens per session scan A 61ab60f893a5

Subscribe to this mod's changes

cloudbase-env is a command published in the GitHub repository TencentCloudBase/CloudBase-AI-Toolkit (1,087 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 1,260 once invoked, about $0.0002 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.