
Sign up to save your podcasts
Or


Anthropic’s latest Claude Code update disables built-in todo and task tools on newer models by default, breaking workflows that depend on structured task tracking. The hosts explain how to restore them with an environment variable, plus cover new FinOps gateway settings and a Windows security fix.
This episode breaks down Claude Code 2.1.233’s new opt-in Linux memory cgroup support for Bash tool commands, showing how it can stop runaway builds and leaking processes from taking down your whole dev machine. It also covers GitLab Merge Request worktree support, web cache tuning, and plugin validation improvements.
Show Notes
This episode covers the latest Claude Code 2.1.232 updates, including forked subagents inheriting full conversation context, background execution for interactive agents, and direct session messaging. It also touches on GitLab secret redaction, clipboard image fixes, async code review, and a key tip for keeping parent transcripts lean to avoid heavy token overhead.
We break down how Claude Code 2.1.229 reduces duplicate token spend by staggering parallel subagent fan-outs so prompt caches can warm up, plus how to disable the delay for local benchmarking. The episode also covers new guardrails for commit push PR workflows and quality-of-life updates like remote session continue, resizable side panels, and VS Code session grouping.
Show Notes
This episode breaks down a security fix in Claude Code v2.1.228 that holds cross-session messages for approval before they can reach elevated terminals. It also covers the new dialogExpiry setting for headless workflows, plus quality-of-life updates to Write tool behavior and sandboxing for synced skills.
Show Notes
This episode explains how ANTHROPIC_BEDROCK_REGION_PREFIX can reroute Claude Code requests through cross-region Bedrock inference profiles to avoid AWS us-east-1 bottlenecks and 429 rate limits. It also covers IAM permission requirements, GovCloud behavior, and the latest quality-of-life updates in recent Claude Code releases.
Show Notes
We break down Anthropic’s new claude self hosted runner for Team and Enterprise users, showing how it lets Claude Code sessions run inside your own secure infrastructure instead of the cloud. The episode also covers the latest fail-fast permission checks, clearer spend-limit warnings, workspace trust prompts, and Remote Control improvements for attached images.
Show Notes
Claude Code 2.1.224 adds archive-based plugin installs, letting teams load plugins directly from HTTPS ZIP files without git or npm on locked-down systems. The episode also covers SHA-256 pinning, ZIP structure requirements, and other enterprise-friendly updates like Bedrock region settings and clearer spend-limit alerts.
This episode breaks down new proactive messaging for remote Claude Code agents, letting you start conversations across machines with SendMessage and ListAgents. It also covers clearer enterprise gateway warnings, auto mode safety fixes, and the trust prompts that protect background agent workflows.
Show Notes
This episode explores how Claude Code sessions can message each other across terminals using ListAgents and SendMessage, making multi-repo workflows and handoffs far smoother. It also covers the security controls, new archive plugin installs, self-hosted runners, the lifted subagent cap, and a sandbox fix for deny-rule bypasses.
Show Notes
From the publisher's feed