AI agent news for August 13, 2026

4 stories · August 13, 2026 · ~4 min read

By the numbers#

Today's numbers at a glance

On the radar today#

🧠 Sessions auto-discover skills from a mounted repository's .claude/skills directory#

When a Managed Agents session mounts a GitHub repository, any skills in that repo's root .claude/skills directory are discovered automatically at session start and made available to the agent for that session.

The number: .claude/skills (Repo path scanned automatically at session start). platform.claude.com

Why it matters: Skills become version-controlled alongside the code they operate on, rather than a separate registry someone has to keep in sync by hand.

Source: Anthropic (Claude)

---

🧠 Gemini adds two robotics endpoints with spatial reasoning and tool orchestration#

Google released gemini-robotics-er-2-preview and gemini-robotics-er-2-streaming-preview, described as offering advanced spatial reasoning, agentic code execution and multi-step tool orchestration.

The number: 2 (New Gemini robotics endpoints released). ai.google.dev

Why it matters: Agent tooling is moving off the screen. The same orchestration patterns used for software agents are being pointed at physical systems, with a streaming variant for closed-loop control.

Source: Google Gemini

---

🧠 Webhooks extend to environment and memory store lifecycle events#

Managed Agents webhooks now cover four environment.* event types and three memory_store.* event types, so environment and memory store lifecycle changes can be reacted to without polling.

The number: 4 (New environment.* webhook event types). platform.claude.com

Why it matters: Polling loops around agent infrastructure were the last piece of unnecessary glue in most integrations. This removes it for two more resource families.

Source: Anthropic (Claude)

---

🧠 Managed Agents agents accept an effort level on their model configuration#

An effort level can now be set inside the model object when creating a Managed Agents agent, applying the same low through max ladder used elsewhere in the API.

The number: 5 (Effort levels available (low through max)). platform.claude.com

Why it matters: Effort is the main cost and latency dial on current models, and until now hosted agents had no way to set it without changing model entirely.

Source: Anthropic (Claude)

+6 more on the radar today: see the full feed.

What I'd actually do about it#