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 agentmods add skills/tencentcloudbase/cloudbase-ai-toolkit/cloudbase-sites-runtimenpx skills add TencentCloudBase/CloudBase-AI-Toolkit --skill cloudbase-sites-runtimegit clone --depth 1 https://github.com/TencentCloudBase/CloudBase-AI-ToolkitWhat 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 | $0.00159 | $0.04432 |
| Opus 5 | $0.00079 | $0.02216 |
| Sonnet 5 | $0.00032 | $0.00886 |
| Haiku 4.5 | $0.00016 | $0.00443 |
Grade A, and why
cloudbase-sites-runtime 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 2d 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 — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CloudBase Sites Runtime
This skill orchestrates a single working directory = single project flow for CloudBase Web apps. The cwd itself is the workspace; we do not manage cross-cwd state or session IDs at the skill level.
This runtime is shared by the Codex, Claude Code, and CodeBuddy plugin surfaces. The CLI and CloudBase MCP workflows are the source of truth. Some hosts also run bundled lifecycle hooks that start previews or inject compact rules at session start; if hooks are unavailable, disabled, or not yet trusted, use the explicit CLI commands in this skill.
Activation contract
Use this skill when
- The user says "build me a website / app", "I want to make a landing page", "create a React app and let me preview", "deploy this to CloudBase", "save this version", "roll back to v1", or similar.
- The current cwd looks like a CloudBase + Vite project (has
package.jsonwithvite+reactorvue). - The user is running this conversation inside Codex, Claude Code, CodeBuddy,
or a compatible host with the
cloudbase-sitesplugin enabled —cloudbase-mcpis registered and thecloudbase-sitesbinary is either on PATH or available from the plugin root'sbin/cloudbase-sites.
Do NOT use this skill when
- It's a mini-program project — route to mini-program guidance instead.
- It's a native app project — route to http-api guidance.
- It's a backend-only project — route to cloud-functions / cloudrun guidance.
- The framework is Next/Nuxt/Astro/Remix — politely tell the user this skill only covers Vite-based React/Vue apps and stop. Do NOT try to adapt the scripts to those frameworks.
What this skill orchestrates — three layers
1. CloudBase MCP tools (provided by cloudbase-mcp, registered via plugin's .mcp.json)
These are the only tools that produce CloudBase side effects. Highlights:
downloadTemplate({ template: "react" | "vue", ide })— pull official templateenvQuery({ action: "info" })+auth({ action: "set_env", envId })— bind envmanageApps({ action: "deployApp", ... })— deploy to CloudApp (independent subdomain)envDomainManagement({ action: "create", domains })— whitelist dev origin for CORSsearchKnowledgeBase({ mode: "skill", skillName: "<name>" })— fetch CloudBase domain skills (see below)
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.
- 2d ago First seen · 332 lines · 159 tokens per session scan A ca0d2a824d9d
cloudbase-sites-runtime is a skill published in the GitHub repository TencentCloudBase/CloudBase-AI-Toolkit (1,087 stars, last pushed yesterday), licensed MIT. It adds 159 tokens to every session and 4,432 once invoked, about $0.0008 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
fix-codesign-error
Slash command that inspects a macOS signing or entitlement failure and explains the minimum fix path. Invoke explicitly with /fix-codesign-error — this skill never self-triggers.
browse-and-evaluate
Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.
specflow-use
To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.
loop-engineering
Shared loop-engineering reference for COG skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns. Invoke when designing or debugging a skill that iterates (search-verify-retry, scan-until-dry, fetch-retry-gate).
telnyx-messaging-hosted-curl
Set up hosted SMS numbers, toll-free verification, and RCS messaging. Use when migrating numbers or enabling rich messaging features. This skill provides REST API (curl) examples.
render-airdrop-carousel
Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like to share a · Decline / Accept") springs up and its preview window CYCLES through the products, landing on a range/lineup payoff with an…