Reference instructions for building applications with Claude, Anthropic's AI model and developer service, using its official software libraries or web requests.

Use them when adding or changing Claude API calls, streaming responses, tool use, MCP connections, agents, prompt caching, token counting, or model migration.

They help select the right Claude model and settings while preventing Claude-specific code from being added to a project built for another AI provider.

claude-api — Skill for Claude Code by guanyang/open-agent-hub

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 guanyang/open-agent-hub --skill claude-api

Clone the repo

git clone --depth 1 https://github.com/guanyang/open-agent-hub

Made for: Claude Code.

Or install open-agent-hub, the plugin that ships this one along with the rest of its 105 skills, 3 commands, 5 agents, 6 MCP servers.

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/guanyang/open-agent-hub/claude-api/github.svg)](https://agentmods.dev/skills/guanyang/open-agent-hub/claude-api)

Your own site

<a href="https://agentmods.dev/skills/guanyang/open-agent-hub/claude-api"><img src="https://agentmods.dev/badge/skills/guanyang/open-agent-hub/claude-api/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/guanyang/open-agent-hub/claude-api"><img src="https://agentmods.dev/badge/skills/guanyang/open-agent-hub/claude-api.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 294 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 26,696 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 86% 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	$0.00294	$0.26696
Opus 5.5	$0.00118	$0.10678
Sonnet 5.5	$0.00059	$0.05339
Haiku 4.5	$0.00029	$0.02670

Measured 14d ago against content hash 40537cca17c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-api 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 14d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (shared/evals/report/build-report-lite.mjs, shared/evals/report/runner-scaffold.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

2. **Raw HTTP** (`curl`, `requests`, `fetch`, `httpx`, etc.) - only when the user explicitly asks for cURL/REST/raw HTTP, the project is a shell/cURL project, or the language has no official SDK.

Origin

This is a copy

86% identical to claude-api — 146 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/claude-api/SKILL.md · 617 lines

How it starts

The opening of the file, as written. The whole thing — 617 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Building LLM-Powered Applications with Claude

This skill helps you build LLM-powered applications with Claude. Choose the right surface based on your needs, detect the project language, then read the relevant language-specific documentation.

Before You Start

Scan the target file (or, if no target file, the prompt and project) for non-Anthropic provider markers - import openai, from openai, langchain_openai, OpenAI(, gpt-4, gpt-5, file names like agent-openai.py or *-generic.py, or any explicit instruction to keep the code provider-neutral. If you find any, stop and tell the user that this skill produces Claude/Anthropic SDK code; ask whether they want to switch the file to Claude or want a non-Claude implementation. Do not edit a non-Anthropic file with Anthropic SDK calls. (Exception: the prompt-audit subcommand is non-interactive and does not stop here - it records non-Anthropic provider markers in its report's stated assumptions and never proposes switching a non-Anthropic file to the Anthropic SDK.)

Output Requirement

When the user asks you to add, modify, or implement a Claude feature, your code must call Claude through one of:

The official Anthropic SDK for the project's language (anthropic, @anthropic-ai/sdk, com.anthropic.*, etc.). This is the default whenever a supported SDK exists for the project.
Raw HTTP (curl, requests, fetch, httpx, etc.) - only when the user explicitly asks for cURL/REST/raw HTTP, the project is a shell/cURL project, or the language has no official SDK.

Never mix the two - don't reach for requests/fetch in a Python or TypeScript project just because it feels lighter. Never fall back to OpenAI-compatible shims.

Never guess SDK usage. Function names, class names, namespaces, method signatures, and import paths must come from explicit documentation - either the {lang}/ files in this skill or the official SDK repositories or documentation links listed in shared/live-sources.md. If the binding you need is not explicitly documented in the skill files, WebFetch the relevant SDK repo from shared/live-sources.md before writing code. Do not infer Ruby/Java/Go/PHP/C# APIs from cURL shapes or from another language's SDK.

Read the full file on GitHub · 617 lines

Files

What ships with it

60 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.

14d ago Changed · +11 lines 40537cca17c4
18d ago Changed · +2 lines d2d78eb15972
25d ago Changed · +31 lines 9aac10d9ffb8
1mo ago Changed · +2 lines 8227f0d11925
1mo ago Changed · +14 lines 001abd67b06d
1mo ago First seen · 557 lines · 294 tokens per session scan A 0d39c5469299

Subscribe to this mod's changes

claude-api is a skill published in the GitHub repository guanyang/open-agent-hub (981 stars, last pushed yesterday), licensed MIT. It adds 294 tokens to every session and 26,696 once invoked, about $0.0012 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). It is 86% identical to claude-api, differing in 146 lines, and is treated as a copy.

Backend and APIs Building agents Planning Workflows ai-skills anthropic-skills skills superpowers

agent-communication-protocol-enuno-claude-command-and-c-2

This page used to hold an archived copy of this skill. The archive now lives in the registry's data repository.

majiayu000/claude-skill-registry · 0 tokens

n8n-workflows

Use when n8n workflow automation — nodes, triggers, expressions, credentials, webhooks, error handling. Use when working with n8n workflows.

oyi77/1ai-skills · 37 tokens

pipedream-workflows

Use when pipedream serverless workflows — triggers, code steps, pre-built actions, data stores, HTTP. Use when working with pipedream workflows.

oyi77/1ai-skills · 38 tokens

integrate-arcjet-guard-cloudflare-think

Integrate Arcjet Guard into Cloudflare Think — delegate beforeToolCall to guardHooks so a DENY substitutes or blocks the tool, and read a caller-owned id via cloudflareThinkContext. Use when asked to add Arcjet to @cloudflare/think, Cloudflare Agents Think, rate limit those tools, screen inbound messages, or block…

arcjet/skills · 107 tokens

integrate-arcjet-guard-google-adk-py

Integrate Arcjet Guard into Python Google ADK — assign guardtool to LlmAgent(beforetoolcallback=), put guardplugin first on Runner(plugins=) so a deny dict with arcjetDenied skips the tool, and read a caller-owned id via googleadkcontext. Use when asked to add Arcjet to google-adk, Google ADK Python, rate limit those…

arcjet/skills · 127 tokens

neo-rabbitmq

Use this skill when a request involves RabbitMQ message-topology design, reliability analysis, Broker operations, cluster or security configuration, monitoring, troubleshooting, or performance optimization. Use stable RabbitMQ 4.3 by default and keep development guidance language-neutral. Do not use this skill for…

Benknightdark/neo-skills · 73 tokens

claude-api