Anthropic Sources

中文 | English

Summary

This family groups Anthropic engineering notes, managed-agent framing, Mythos Preview release material, and the Claude Code corpus that currently matters most to the vault's agent-workflow synthesis.

Claude Code

Everything Claude Code

• Affaan Mustafa Claude Code Shorthand Guide - Source on skills versus commands, hook design, MCP and plugin budgeting, subagent scoping, and practical Claude Code setup surfaces.

• Affaan Mustafa Claude Code Longform Guide - Source on session logs, strategic compaction, token-aware delegation, eval loops, bounded parallelization, and reusable Claude Code operating patterns.

• Everything Claude Code GitHub Repository - Repository snapshot showing ECC as a multi-harness distribution surface for rules, hooks, skills, Codex config, and packaged agent workflows.

• Claude Code Auto Dream Memory Consolidation - Source on periodic memory consolidation, contradiction repair, absolute dating, and keeping index files compact.

Managed Agents And Harnesses

• Anthropic Harness Design For Long-Running Application Development - Source on planner-generator-evaluator harnesses, skeptical evaluation, and reducing scaffolding as models improve.
• Claude Managed Agents Overview - Product overview defining Anthropic's managed agent primitives, beta constraints, rate limits, and the hosted alternative to building your own loop.
• Scaling Managed Agents: Decoupling The Brain From The Hands - Engineering source on meta-harness interfaces, externalized session state, credential separation, and many-brains many-hands scaling.

Mythos Preview

• Claude Mythos Preview Cybersecurity Assessment - Source on real-world zero-day evaluation, exploit-capable model scaffolds, and coordinated defensive rollout.
• Claude Mythos Preview System Card - Source on Anthropic's full release-governance, capability, cyber, alignment, welfare, and safeguards record for Mythos Preview.

Release Notes

• Introducing Claude Opus 4.7 - Launch note tying Opus 4.7's coding gains, stricter instruction following, xhigh effort default, /ultrareview, and staged cyber safeguards into one operator-facing release surface.

Related Pages

• Source Catalog
• Knowledge Operations
• Agent Harness Design