Claude Code adds built-in scheduled tasks

// 81d agoPRODUCT UPDATE

Claude Code adds built-in scheduled tasks

Anthropic has added documented built-in scheduling to Claude Code, letting developers use `/loop` or natural-language reminders to run recurring checks and one-shot follow-ups during an active session. It makes Claude Code more useful for deployment watching, build polling, and PR babysitting, but the tasks are session-scoped and disappear when the session ends.

// ANALYSIS

This is a deceptively important upgrade: Claude Code moves from one-shot assistant to lightweight background automation layer inside the dev workflow. Anthropic is also drawing a clear line between convenient in-session orchestration and true unattended automation.

–`/loop` can rerun prompts or packaged workflows like review commands on a schedule without leaving the Claude Code session
–One-time reminders are a practical fit for long-running builds, test suites, and deployment checks that normally force developers to keep context in their head
–The feature is intentionally constrained: tasks run only while Claude Code is open and idle, and recurring jobs expire after three days
–That makes scheduled tasks great for active coding sessions, but still not a replacement for GitHub Actions or other durable schedulers

// TAGS

claude-codeai-codingagentcliautomation

DISCOVERED

81d ago

2026-03-07

PUBLISHED

81d ago

2026-03-07

RELEVANCE

8/ 10

AUTHOR

DIY Smart Code

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

UPDATE1h ago

Cursor adds dedicated subagents for skills

Cursor now allows developers to execute tool-heavy or research-intensive agent skills within dedicated subagents. This architectural shift isolates noisy background tasks, keeping the main chat context clean and focused.

UPDATE2h ago

YouTube moves AI labels to video player

YouTube is moving its AI content disclosures from video descriptions to more prominent placements beneath the player and on Shorts overlays. Starting in May, the platform will use internal signals to automatically label photorealistic AI content that creators fail to disclose.

OPEN SOURCE5h ago

Taste Skill kills AI "frontend slop"

Taste-Skill is an open-source framework that provides portable "agent skills" to enforce high-end design principles in AI-generated code. By injecting specific design directives and "anti-slop" rules, it enables LLMs to produce editorial-grade UIs that bypass generic, boilerplate-heavy AI templates.