# Claude API

> Claude API is an agent skill for ai models and llm tooling. Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model. It is available on Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose.

- **Kind:** Skill
- **Platforms:** Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, Goose
- **Website:** https://github.com/anthropics/skills/tree/main/skills/claude-api
- **Repository:** https://github.com/anthropics/skills
- **GitHub stars:** 196,392
- **Skill name:** claude-api
- **Collection:** https://github.com/anthropics/skills
- **Categories:** AI models and LLM tooling, knowledge and memory
- **Listing updated:** 2026-11-17

## About

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.
TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens).
SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST

## When your agent uses it

> Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST

## What it can access

From a static check of the files on GitHub; nothing was run.

- [Runs JavaScript and Python scripts](https://github.com/anthropics/skills/tree/HEAD/skills/claude-api)
- [Network calls found in its scripts](https://github.com/anthropics/skills/tree/HEAD/skills/claude-api)
- [No license found](https://github.com/anthropics/skills/tree/HEAD/skills/claude-api)

## Install

### Claude Code

This skill ships in the `claude-api` plugin. In Claude Code, add the marketplace and install the plugin (it may include other skills too):

```sh
/plugin marketplace add anthropics/skills
/plugin install claude-api@anthropic-agent-skills
```

Or copy only this skill to `~/.claude/skills/claude-api`:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/anthropics/skills.git "$tmp" &&
mkdir -p ~/.claude/skills &&
rm -rf ~/.claude/skills/claude-api &&
cp -R "$tmp/skills/claude-api" ~/.claude/skills/claude-api &&
rm -rf "$tmp"
```

For one project only, put the folder in `.claude/skills/claude-api` inside it instead.

### Codex

Copy the skill folder to `~/.agents/skills/claude-api` to use it in every repository:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/anthropics/skills.git "$tmp" &&
mkdir -p ~/.agents/skills &&
rm -rf ~/.agents/skills/claude-api &&
cp -R "$tmp/skills/claude-api" ~/.agents/skills/claude-api &&
rm -rf "$tmp"
```

For one repository only, put the folder in `.agents/skills/claude-api` inside it instead.

### Cursor

Copy the skill folder to `~/.cursor/skills/claude-api` to use it in every project:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/anthropics/skills.git "$tmp" &&
mkdir -p ~/.cursor/skills &&
rm -rf ~/.cursor/skills/claude-api &&
cp -R "$tmp/skills/claude-api" ~/.cursor/skills/claude-api &&
rm -rf "$tmp"
```

For one project only, put the folder in `.cursor/skills/claude-api` inside it instead.

### Gemini CLI

Run in a terminal (add `--scope workspace` to install it for the current workspace only):

```sh
gemini skills install https://github.com/anthropics/skills.git --path skills/claude-api
```

Or copy the folder to `~/.gemini/skills/claude-api` yourself.

### VS Code

For GitHub Copilot in VS Code, copy the skill folder to `~/.copilot/skills/claude-api`:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/anthropics/skills.git "$tmp" &&
mkdir -p ~/.copilot/skills &&
rm -rf ~/.copilot/skills/claude-api &&
cp -R "$tmp/skills/claude-api" ~/.copilot/skills/claude-api &&
rm -rf "$tmp"
```

For one project only, put the folder in `.github/skills/claude-api` inside it instead.

### Other agents

Get the folder:

```sh
git clone --depth 1 https://github.com/anthropics/skills.git
```

Then copy `skills/skills/claude-api` into your agent's skills folder as `claude-api`. Agents that support SKILL.md read one folder per skill.

## FAQ

### How do I install Claude API in Claude Code?

Copy the skill folder from GitHub to ~/.claude/skills/claude-api to use it in all your projects, or to .claude/skills/claude-api in one project. Or install the claude-api plugin, which includes it: /plugin marketplace add anthropics/skills, then /plugin install claude-api@anthropic-agent-skills.

### Does Claude API run scripts?

Yes. It runs JavaScript and Python scripts. Its scripts contain network calls. This comes from a static check of the files on GitHub; nothing was run. Read the files before you install it.

### Which AI agents can use Claude API?

Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose. Each reads skills in the SKILL.md format from its own folder; the install steps on this page list them.

### What are the best alternatives to Claude API?

The closest alternatives to Claude API are Academy guide, MCP builder, Agent governance, Agentic eval and AI prompt engineering safety review.

## Alternatives

- [Academy guide](https://ai-powered.com/skills/academy-guide): Academy guide is an agent skill for ai models and llm tooling.
- [MCP builder](https://ai-powered.com/skills/mcp-builder): MCP builder is an agent skill for ai models and llm tooling.
- [Agent governance](https://ai-powered.com/skills/agent-governance): Agent governance is an open-source agent skill for ai models and llm tooling.
- [Agentic eval](https://ai-powered.com/skills/agentic-eval): Agentic eval is an open-source agent skill for ai models and llm tooling.
- [AI prompt engineering safety review](https://ai-powered.com/skills/ai-prompt-engineering-safety-review): AI prompt engineering safety review is an open-source agent skill for ai models and llm tooling.

---
Source: https://ai-powered.com/skills/claude-api
