CloudBase AI Toolkit is an integration layer that lets AI coding tools use Tencent CloudBase as an application backend, including databases, authentication, functions, storage, and deployments. Developers use it to have coding agents build and operate CloudBase-backed applications through skills, plugins, commands, and chat-accessible tools. The catalogue entries are the toolkit’s own skills, agents, hooks, plugins, rules, instructions, and MCP tools.
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 TencentCloudBase/CloudBase-AI-Toolkit --skill cloudbase-platformgit clone --depth 1 https://github.com/TencentCloudBase/CloudBase-AI-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/tencentcloudbase/cloudbase-ai-toolkit/cloudbase-platform)<a href="https://agentmods.dev/skills/tencentcloudbase/cloudbase-ai-toolkit/cloudbase-platform"><img src="https://agentmods.dev/badge/skills/tencentcloudbase/cloudbase-ai-toolkit/cloudbase-platform/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/tencentcloudbase/cloudbase-ai-toolkit/cloudbase-platform"><img src="https://agentmods.dev/badge/skills/tencentcloudbase/cloudbase-ai-toolkit/cloudbase-platform.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Rogue Agent · line 343 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00054 | $0.07988 |
| Opus 5.5 | $0.00022 | $0.03195 |
| Sonnet 5.5 | $0.00011 | $0.01598 |
| Haiku 4.5 | $0.00005 | $0.00799 |
Grade A, and why
cloudbase-platform 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 today.
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.
Copies of this mod
2 near-identical copies found in the catalogue:
- cloudbase-platform — 100% identical, 269 lines differ
- cloudbase-platform — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 401 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sibling skills (local only)
Sibling CloudBase skills ship beside this skill. Use local relative paths such as ../auth-tool-cloudbase/SKILL.md.
If a referenced sibling skill file is missing from this environment, ask the user to install the full CloudBase plugin (or the missing skill). Do not HTTP-fetch remote skill or protocol markdown into the agent context.
Cross-cutting protocols (required before code changes or deployments):
- Change Safety Protocol:
references/protocols/change-safety-protocol.md - Deployment Gate:
references/protocols/deployment-gate.md - Sensitive Runtime Data Protection:
references/protocols/sensitive-runtime-data-protection.md
Post-deployment (optional, non-intrusive): after a deployment is verified successful, you may offer at most once to generate anonymized shareables and, in that same offer, optionally submit the work to the case wall (Deployment Share) — see references/protocols/deployment-share.md. Never follow up if declined; never publish or submit on the user's behalf.
Activation Contract
Use this first when
- The user asks which CloudBase capability, service, or tool to use, or needs a high-level understanding of hosting, storage, authentication, cloud functions, or database options.
- The task is about console navigation, cross-platform differences, permission models, or platform-level best practices before implementation.
Read before writing code if
- It is still unclear whether the task belongs to Web, mini program, cloud functions, storage, MySQL / NoSQL, or auth.
- The response needs platform selection, conceptual explanation, or control-plane navigation more than direct implementation steps.
Then also read
- Minimal Web + database demo (BaaS-first, no cloud functions by default) ->
../minimal-web-baas-demo/SKILL.md- Stack order for 最小前后端 / Lovable-like demos: Web SDK CRUD > MCP schema > template warmup during credential wait > cloud functions (default count = 0). Capability sniff: connector ready →
queryEnv→ lock one DB plane → MCP schema →@cloudbase/js-sdkCRUD → preview.
- Stack order for 最小前后端 / Lovable-like demos: Web SDK CRUD > MCP schema > template warmup during credential wait > cloud functions (default count = 0). Capability sniff: connector ready →
- Web app implementation ->
../web-development/SKILL.md - Web auth and provider setup ->
../auth-tool-cloudbase/SKILL.md,../auth-web-cloudbase/SKILL.md - Mini program development ->
../miniprogram-development/SKILL.md - WeChat Pay, Official Account OAuth, JSAPI Pay, or Native QR-code Pay through CloudBase Integration Center ->
../cloudbase-wechat-integration/SKILL.md(official docs:https://docs.cloudbase.net/integration/introduce.md) - Cloud functions ->
../cloud-functions/SKILL.md - Official HTTP API clients ->
../http-api-cloudbase/SKILL.md - Document database ->
../cloudbase-document-database-web-sdk/SKILL.mdor../cloudbase-document-database-in-wechat-miniprogram/SKILL.md - CloudBase PostgreSQL / PG ->
../postgresql-development-cloudbase/SKILL.md - Realtime / live push / channels / live table change subscriptions / multiplayer sync ->
../postgresql-development-cloudbase/references/realtime.md- PG mode only. Run its Step 0 environment probe before writing any realtime code; if the environment has no
realtimeschema, stop and report rather than working around it. app.realtime()(Broadcast / Presence / Postgres CDC) is not document-databasecollection.watch(). Do not answer a realtime request withwatch()code, or the reverse.
- PG mode only. Run its Step 0 environment probe before writing any realtime code; if the environment has no
- MySQL relational database / data modeling ->
../relational-database-mcp-cloudbase/SKILL.mdor../data-model-creation/SKILL.md - Cloud storage ->
../cloud-storage-web/SKILL.md
What ships with it
5 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.
- today Changed · +1 lines 738a1385f862
- yesterday Changed · +4 lines 302e76bc2415
- 3d ago Changed d52f75ee9845
- 7d ago Changed · +1 lines 8f9e15138375
- 16d ago Changed a957643e1abb
- 17d ago Changed e7250e900f2a
- 18d ago Changed · +4 lines 40b3c1f726c7
- 23d ago Changed · +3 lines · +10 tokens per session b797f700815e
- 25d ago Changed 7cc33733bf07
- 26d ago First seen · 388 lines · 44 tokens per session scan A 673cd91bf544
cloudbase-platform is a skill published in the GitHub repository TencentCloudBase/CloudBase-AI-Toolkit (1,138 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 7,988 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
cis-aws-foundations-4.10
Ensure all AWS-managed web front-end services have access logging enabled.
shippage
Publish HTML or Markdown to a public URL instantly. Zero config, auto-registers on first use. Use when the user wants to share, preview, host, or deploy generated HTML, Markdown, JSX, or web content as a live webpage accessible from any device including mobile phones and WeChat. Perfect for sharing AI-generated pages…
nginx
Nginx configuration and optimization.
nginx-reverse-proxy
Configure nginx as a reverse proxy with TLS termination, headers, and upstream health — for self-hosted web apps.
apache
Apache HTTP Server 配置.
shippage
Publish HTML or Markdown to a public URL instantly. Zero config, auto-registers on first use. Use when the user wants to share, preview, host, or deploy generated HTML, Markdown, JSX, or web content as a live webpage accessible from any device including mobile phones and WeChat. Perfect for sharing AI-generated pages…