Advertise on podcast: The Claude Code Changelog

This episode covers Claude Code 2.1.289, highlighting fixes to permission rules, sandbox behavior, symlinked file access, and managed machine safeguards. It also breaks down new agent spawn hooks, improved status tracking, and several stability and plugin updates.

This episode covers a fix in Claude Code 2.1.288 that makes path-scoped rules and nested CLAUDE.md files load on Write and Edit, even when a file is created before any read. It also breaks down the new InstructionsLoaded hook details, rule-loading caveats, and a handful of smaller workflow updates in the release.

We break down the new Claude Mods system in Claude Code 2.1.287, including how in-process TypeScript hooks differ from classic JSON hooks, what the built-in You should know mod does, and why security teams are urging caution. Plus: validation tips for third-party mods, team guardrails, 1M context defaults, VS Code updates, and an MCP fix for sign-in prompt changes.

This episode explores Claude Code 2.1.286 and its new verify skill, which runs checks before commits so the agent catches its own mistakes. It also covers related polish like clearer permission prompts, safer transcript actions, background command handling, and a model fallback retry. Show Notes Claude Code changelog - Claude Code Docs: https://code.claude.com/docs/en/changelog

We dig into the latest release updates that make plugin setup far smoother for unattended builds, including install-time config for bundled servers, a command to inspect missing options, and safer ways to pass secrets without exposing them in shell history. Also covered: a fixed bug that silently skipped unconfigured bundled servers, SSH install support that now respects your custom git SSH settings, and a few quality-of-life changes like WebFetch disabling, background command timeouts, and launching Claude Desktop from the terminal.

We unpack Claude Code 2.1.284 and the quiet switch to Sonnet 5.5, from the 1M-token context window and cheaper cache reads to the new 512-token cache minimum. Plus: adaptive thinking defaults, tool-calling changes, keybinding controls, and the token-counting gotchas that could affect your bill.

We dig into Claude Code 2.1.283’s new OTEL logging support, which finally captures MCP, WebFetch, and WebSearch outputs inside trace spans so you can see what your agent actually saw. We also cover the security risks, content limits, and a few welcome MCP quality-of-life fixes like clearer context breakdowns and fewer zombie processes.

Claude Code 2.1.283 changes the default for interactive sessions on Bedrock, Vertex AI, and telemetry-off setups to auto mode, and we break down what that means for approvals, classifier behavior, proxy fallback costs, and how to switch back to manual control. We also cover the new MCP image-saving workflow, prompt file-plus-text options, and a critical PowerShell safety fix for destructive commands.

The hosts break down Claude Code 2.1.283, including the new prompt audit tool that scans CLAUDE.md, skills, subagents, and rules for stale paths, dead commands, and conflicting instructions. They also cover enterprise gateway hint headers and smoother terminal navigation with mouse and page-key support.

We dig into Claude Code 2.1.282, including the new maxProseWidth setting for readable prose on ultrawide monitors, plus self-healing fixes for redacted thinking block errors and broken web search history. We also cover clearer environment diagnostics in claude doctor and /status, along with the new Chrome policy option for managed MCP setups. Show Notes Claude Code changelog - Claude Code Docs: https://code.claude.com/docs/en/changelog

We dig into a frustrating Claude Code bug where MCP tools can silently disappear, then break down how release 2.1.28.1 improves validation by catching dropped .mcp.json entries, undeclared template variables, and insecure HTTP endpoints before they hit production. We also cover a stricter schema gotcha for existing CI pipelines and a handy quality-of-life update for disabling automated Git commit and PR attribution footers.

Claude Code 2.1.280 adds a long-awaited fix for MCP tool descriptions that were silently capped at 2,048 characters, plus a new environment variable to raise or lower the limit as needed. The episode also covers the tradeoffs of larger prompts, a Write tool validation patch, and quality-of-life fixes like improved modal exits and better scrolling.

We break down Claude Code 2.1.277’s enterprise networking fixes, including a new egress-boundary flag that skips local DNS lookups and hands hostname resolution to your forward proxy. We also cover static upstream headers in gateway config, telemetry proxy behavior, streaming gotchas, and a few quality-of-life improvements for worktrees and background tasks.

We break down the latest Claude Code point releases, including the new dynamic boundary for prompt caching that can cut input token costs dramatically, plus practical tips for avoiding cache misses caused by whitespace and line-ending changes. Also covered: automatic prompt sanitization to strip invisible Unicode injection tricks, smoother plugin marketplace registration, and a handy Auto mode status update in slash status.

Claude Code 2.1.277 tackles prompt injection in multi-agent workflows with structural subagent result framing, making it harder for untrusted text to hijack orchestration. The episode also covers better headless error handling, invisible prompt sanitization, and clearer Grep/Glob diagnostics.