sandbase

sandbase is a skill for Claude Code from iflytek/skillhub. It costs 67 tokens per session (2,197 once invoked), scanned A, original, Apache-2.0.

A single MCP connection to more than 2,000 AI models and external APIs for tasks such as text and media generation, search, scraping, embeddings, social data, and structured retrieval.

In plain words
What is it for?
Use it to discover and call supported models and APIs for inference, image, video, or audio generation, web scraping, search, embeddings, and social-media data.
Why use it?
It gives the agent one interface for services that would otherwise need separate integrations and credentials.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Good fit Use it to discover and call supported models and APIs for inference, image, video, or audio generation, web scraping, search, embeddings, and social-media data.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/iflytek/skillhub/sandbase
About the project

SkillHub is a self-hosted registry where organizations publish, discover, version, and manage reusable skills for AI agents. Teams use it to share governed skill packages privately, with namespaces, role-based access control, audit logs, and CLI installation; the catalogue entries are skills and related agent integrations that can be managed through it.

iflytek/skillhub · 5,083 stars · on GitHub · skill.xfyun.cn

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.

Any agent
npx skills add iflytek/skillhub --skill sandbase
Clone the repo
git clone --depth 1 https://github.com/iflytek/skillhub

Made for: Claude Code.

Wrote 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.

agentmods badge for sandbase

README.md
[![agentmods](https://agentmods.dev/badge/skills/iflytek/skillhub/sandbase/github.svg)](https://agentmods.dev/skills/iflytek/skillhub/sandbase)
Your own site
<a href="https://agentmods.dev/skills/iflytek/skillhub/sandbase"><img src="https://agentmods.dev/badge/skills/iflytek/skillhub/sandbase/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.

agentmods 80×15 button for sandbase

Your own site · 80×15
<a href="https://agentmods.dev/skills/iflytek/skillhub/sandbase"><img src="https://agentmods.dev/badge/skills/iflytek/skillhub/sandbase.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,197 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00067 $0.02197
Opus 5 $0.00034 $0.01099
Sonnet 5 $0.00013 $0.00439
Haiku 4.5 $0.00007 $0.00220

Measured yesterday against content hash 78d18b40d8d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

sandbase scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fLO https://github.com/sandbaseai/cli/releases/download/v0.1.17/sandbaseai-cli-0.1.17.tgz
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • sandbase — 97% identical, 1 lines differ
builtin-skills/skills/sandbase/SKILL.md · 223 lines

How it starts

The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SandBase MCP

SandBase provides access to 2,000+ AI models and API tools through a unified MCP interface. One account covers LLMs, image generation, video generation, audio, embeddings, web scraping, social media APIs, and more.


Setup

If the six sandbase_* MCP tools are not already available, connect the current machine with the immutable v0.1.17 release. Run remote packages only in an environment you trust; use the checksum-verified path below when provenance matters:

npx -y https://github.com/sandbaseai/cli/releases/download/v0.1.17/sandbaseai-cli-0.1.17.tgz connect

For a checksum-verified install, download the same immutable asset first and verify the SHA-256 published with the GitHub Release:

curl -fLO https://github.com/sandbaseai/cli/releases/download/v0.1.17/sandbaseai-cli-0.1.17.tgz
printf '%s  %s\n' '1ad535b2899ca460b57b3c268aef278fee28fd28e649a89b92951514fd71fffa' 'sandbaseai-cli-0.1.17.tgz' | shasum -a 256 -c -
npx -y ./sandbaseai-cli-0.1.17.tgz connect

Approve the browser sign-in once. Authentication happens with SandBase in the browser; the CLI stores the resulting local session record with restricted file permissions. The CLI detects supported clients, installs the local MCP bridge and this managed Skill, and verifies the resulting configuration. No provider API keys are required. Invoke the same release URL with doctor to inspect the connection or unregister to remove only SandBase-managed state.

This file is managed by SandBase CLI and may be replaced during a later CLI-managed update, so keep custom instructions in a separate Skill. Check the official repository for newer releases before copying it independently.

The disable-model-invocation: true frontmatter prevents this Skill from being invoked as a standalone model action. It is contextual guidance for an agent orchestrating the six sandbase_* MCP tools.

Before sending sensitive or regulated data, review the SandBase Privacy Policy and Terms of Service, plus the selected upstream provider's policies. Send only the minimum data needed for the requested tool call.

Read the full file on GitHub · 223 lines

Files

What ships with it

2 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.

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 · 223 lines · 67 tokens per session scan A 78d18b40d8d8

Subscribe to this mod's changes

sandbase is a skill published in the GitHub repository iflytek/skillhub (5,083 stars, last pushed yesterday), licensed Apache-2.0. It adds 67 tokens to every session and 2,197 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-10.

Related

Other skills, from other repositories

iflytek-image-understanding

An image-analysis tool that describes pictures and answers questions about what they contain. It uses an AI vision service, which interprets visual content rather than only reading text files.

iflytek/iFly-Skills · 61 tokens

video-frame-extractor

A video-frame extraction and analysis helper that selects key frames, describes their contents with a vision model, and creates structured prompts for further creation.

anbeime/skill · 78 tokens

antinet-doc-parse

A document-processing skill for building RAG systems, which let an AI search a knowledge base before answering. It handles complex PDF, Word, and Excel files and produces structured Markdown and metadata.

anbeime/skill · 79 tokens

doc-parse

A document parser that converts PDFs, PowerPoint files, spreadsheets, and Word files into structured Markdown with metadata and a confidence score.

anbeime/skill · 43 tokens

openclaw-docs

Find authoritative guidance for installing, configuring, operating, securing, and troubleshooting OpenClaw, including channels, model providers, Gateway operations, tools, plugins, automation, nodes, multi-agent routing, and CLI errors. Use for any question or maintenance task involving an OpenClaw installation…

tbdavid2019/openclaw-docs-skill · 80 tokens

freeride

Manages free AI models from OpenRouter for OpenClaw. Automatically ranks models by quality, configures fallbacks for rate-limit handling, and updates openclaw.json. Use when the user mentions free AI, OpenRouter, model switching, rate limits, or wants to reduce AI costs.

Shaivpidadi/FreeRide · 63 tokens