claude-api
Reference for the Claude API / Anthropic SDK — models, pricing, streaming, tool use, MCP, agents.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for claude-api, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
Anthropic's official reference skill for building LLM apps with Claude. Bundles per-language SDK docs (Python, TypeScript, Go, Java, PHP, Ruby, C#, curl) plus shared references on models, pricing, prompt caching, token counting, tool use, managed agents, and model migration, with live-source fetch guidance. Steers correct SDK code generation and flags stale API patterns.
Key features and capabilities
- Per-language SDK usage docs for 8 surfaces
- Model ids, pricing, caching, token-counting references
- Managed-agents and tool-use concept guides
Use cases
- Add a streaming Claude call to a TypeScript app
- Look up current model ids and pricing before coding