Anthropic's official "Code with Claude" workshop materials — nine hands-on courses on skills, MCP, evals and Claude Managed Agents.
- official
- workshops
- anthropic
- managed-agents
Claude Fable 5.1 & Mythos 5.1 Announcement
Anthropic's announcement of Fable 5.1 and Mythos 5.1 — one base model, two guardrail postures.
Anthropic's announcement of the Fable 5.1 and Mythos 5.1 models: Fable 5.1 targets coding and knowledge work (API id claude-fable-5-1, $10/M input, $50/M output, cache reads cut 75% to $0.25/M), while Mythos 5.1 is the same base model with relaxed guardrails, gated to the Cyber and Life Sciences Verification Programs (US organizations). Terminal-Bench 4.0 at 60.9% (Mythos), HLE 65.0% with tools.
What it does
- Anthropic's official announcement for the Claude Fable and Mythos 5.1 models
- Primary source for model capabilities, positioning, and availability claims
- Reference point for what the newer Claude generation targets (coding, agentic work)
When to use it
Check here when you need Anthropic's own framing of what Fable/Mythos 5.1 are and where they fit — useful before picking a model tier.
Getting started
No install — an announcement page. Models are accessed through the Claude API, claude.ai, or Claude Code depending on availability.
Things to know
Marketing-adjacent source: capabilities are described by the vendor — verify independent benchmarks for hard numbers.
Charted
Related on the map
Anthropic's canonical essay on agent design — workflows vs agents, and five composable patterns.
- official
- agents
- engineering
- patterns
12-Factor Agents
GuideHumanLayer's 12 design principles for production-grade LLM agents — the closest thing to a 'best practices' manifesto.
- agents
- best-practices
- production
- principles