A single connection to more than 2,000 AI models and API tools for tasks such as text, image, video and audio generation, search, scraping, embeddings, social data, and structured retrieval. An API is a way for software to request work or data from another service.

Use it to find and call AI models, generate media, search or scrape web data, create embeddings, access social data, and retrieve structured information.

It provides one interface for trying many external models and services instead of building a separate connection for each one.

sandbase — Skill for Claude Code and Codex by sandbaseai/cli

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 sandbaseai/cli --skill sandbase

Clone the repo

git clone --depth 1 https://github.com/sandbaseai/cli

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/sandbaseai/cli/sandbase/github.svg)](https://agentmods.dev/skills/sandbaseai/cli/sandbase)

Your own site

<a href="https://agentmods.dev/skills/sandbaseai/cli/sandbase"><img src="https://agentmods.dev/badge/skills/sandbaseai/cli/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/sandbaseai/cli/sandbase"><img src="https://agentmods.dev/badge/skills/sandbaseai/cli/sandbase.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 236 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,613 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 2 findings, up to medium

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 →

medium MCP Rug Pull · line 21
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]
low Supply Chain · line 27
Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.

How audits are shown

Origin 97% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5.1	$0.00236	$0.04613
Opus 5.5	$0.00094	$0.01845
Sonnet 5.5	$0.00047	$0.00923
Haiku 4.5	$0.00024	$0.00461

Measured 8d ago against content hash 79c5fe27765d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sandbase 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 8d 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.

Origin

This is a copy

97% identical to sandbase — 334 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/sandbase/SKILL.md · 267 lines

How it starts

The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SandBase

SandBase gives you 2,000+ models and APIs behind one interface: search the catalog, read a tool's input schema and price, run it, and fetch the result. One balance covers everything; the user never manages provider keys.

There are two transports with the same capabilities. Pick one before doing anything else.

0. Set up

Do this when the user asks you to set up SandBase (for example "set up https://www.sandbase.ai/SKILL.md"), or when §1 finds neither transport. You run the steps yourself; the user only approves a sign-in in their browser.

Check Node.js 20 or newer: node --version. If it is missing or older, ask the user to install it from https://nodejs.org and stop.
Connect this client. Run in a shell, with your client id:
```
npx -y @sandbaseai/cli@latest connect --client <client-id>
```
Client ids: claude-code, codex, cursor, windsurf, kiro, kiro-cli, gemini-cli, opencode, qwen-code, warp, cursor-cli, kimi-cli, amp, crush, hermes, openclaw, iflow-cli, antigravity, trae, qoder, workbuddy, pi, claude-desktop, cowork, chatgpt. If you are not sure which one you are, omit --client to configure every installed client.
- It opens the browser for sign-in (new users get an account in the same step). Tell the user to approve it. If there is no browser, it prints a URL — show that URL to the user.
- It waits for the approval, so give the command a timeout of at least 5 minutes. If your shell cannot wait that long, ask the user to run the same command in their own terminal.
- Never ask the user to paste an API key into the chat.
When it reports the client as configured, tell the user to start a new session (or restart the app) so the sandbase_* tools load. Until then, use the CLI right away: npx -y @sandbaseai/cli@latest discover -q "<what you need>" (§3).
Keep this Skill installed. connect saves it for supported clients; if yours is not covered, save https://www.sandbase.ai/SKILL.md to your skills directory and enable it so it loads in future sessions.

Read the full file on GitHub · 267 lines

Files

What ships with it

1 file 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.

skill.json 548 B

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.

8d ago Changed · +74 lines · +21 tokens per session 79c5fe27765d
9d ago Changed · -29 lines · +148 tokens per session 63059ec0bdfd
1mo ago First seen · 222 lines · 67 tokens per session scan A 61ce4861afd2

Subscribe to this mod's changes

sandbase is a skill published in the GitHub repository sandbaseai/cli (185 stars, last pushed 8d ago), licensed Apache-2.0. It adds 236 tokens to every session and 4,613 once invoked, about $0.0009 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 97% identical to sandbase, differing in 334 lines, and is treated as a copy.

Building agents Claude Code Data and AI LLM ai-agents cli codex mcp

system-prompts

Write system prompts, tool docs, and agent definitions. Project tag conventions + RFC 2119 keywords + dense compression. Use when authoring or editing any prompt the model reads.

can1357/oh-my-pi · 40 tokens

tool-prompt-optimization

Optimize the description prompts an AI agent reads to learn its built-in tools (the .md files under prompts/tools/). Two halves: (1) measure how much of a prompt is already inferable from the tool's JSON parameter schema + name, to prune redundancy with evidence; (2) house authoring rules for what belongs in a tool…

can1357/oh-my-pi · 0 tokens

pyhealth

Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC)…

synthetic-sciences/openscience · 109 tokens

deepchem

Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first…

synthetic-sciences/openscience · 78 tokens

shap

Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing…