# What&#x27;s New in Claude for Agent Workflows (2026)

Canonical page: https://aiagentskills.biz/updates/claude/
Brand: AI Agent Skills - Built by AI agents, for AI agents. Logo: https://aiagentskills.biz/assets/logo.svg

[Home](/) › [Release trackers](/updates/) › Claude Release tracker

# What's new in Claude for agent workflows

A running changelog of Claude releases that actually matter when you run standing AI agents - new features, limits, and file/project handling. Dated, sourced, no rumor filler.

[Run agents on Claude](/for/claude/)[All trackers](/updates/)

### September 10, 2026: Smart reports (beta) for Enterprise

Claude can assemble smart reports on Enterprise plans, in beta.

**What this means for your agents:** Recurring reporting agents (pipeline, cash flow, content) get a native report surface instead of a pasted chat answer.

[Source →](https://support.claude.com/en/articles/12138966-release-notes)

### September 1, 2026: Claude Fable 5.1 and Mythos 5.1

Two new Claude models shipped: Fable 5.1 and Mythos 5.1.

**What this means for your agents:** Fresh model options for agent runs - worth re-testing your agent’s prompts against the new models before switching the default.

[Source →](https://support.claude.com/en/articles/12138966-release-notes)

### August 25, 2026: Memory across chat and Cowork, with editable topics

Claude’s memory now works across chat and Cowork, and you can edit what it remembers by topic.

**What this means for your agents:** Your agent stops re-asking setup questions, and you can prune wrong memories directly instead of prompt-patching around them.

[Source →](https://support.claude.com/en/articles/12138966-release-notes)

### August 6, 2026: Security scanning for skills and plugins (beta)

Claude added beta security scanning for third-party skills and plugins.

**What this means for your agents:** A real safety layer for exactly what this store sells - third-party skill files get scanned before they run.

[Source →](https://support.claude.com/en/articles/12138966-release-notes)

### July 24, 2026: Claude Opus 5

Anthropic released Claude Opus 5, the new top-tier model.

**What this means for your agents:** The ceiling for hard agent tasks (long reconciliations, multi-document diligence) moved up.

[Source →](https://support.claude.com/en/articles/12138966-release-notes)

## More Claude agent resources

[AI agent skills for Claude](/for/claude/) - the honest setup guide for running our 28 agents on Claude. Start with the [Sourcing Agent on Claude](/for/claude/recruiters/sourcing-agent/) guide if you want a concrete example.

*AI Agent Skills is an independent store. We are not affiliated with, endorsed by, or sponsored by Claude or its makers. Release details belong to their sources; check Claude's own documentation for the authoritative record.*
