Claude Code 2.1.308 has been released. 1 CLI change Highlights: • CLI bug fixes and reliability improvements that reduce failures and produce smoother, more stable behavior Further details in thread ↓

Claude Code 2.1.307 system prompt updates Notable changes: 1) Claude’s tool-hook guidance is cleaned up: the Harness bullet now ends after “treat hook output as user feedback” instead of the malformed “feedback.Response”. This reduces ambiguity/noise in how Claude interprets hook output during tool use. Links: 1) github.com/marckrenn/claude-…

Claude Code 2.1.307 has been released. 43 CLI changes, 1 system prompt change Highlights: • Added /claude-api api-version to switch Claude API code to 2026-10-21, enabling updated API behavior • Stop double HTTP MCP sends on disconnect; only idempotent/read-only tools retried to avoid duplicates • The /clear command now makes cleared conversations persist across restarts, preventing them from reappearing Full details are in thread ↓

Claude Code 2.1.306 is now available. 2 CLI changes Highlights: • Fixed claude -p reporting 'Not logged in' in cloud sessions without env vars, restoring login status • Fixed API errors being replaced by 'prompt is too long' in MCP-heavy sessions, showing original API errors More details in thread ↓

Claude Code 2.1.305 has been released. 38 CLI changes Highlights: • Executes a provided Bash command and returns its output so callers can directly capture shell results • System starts a new agent for complex tasks, delegating long workflows to dedicated subagents so they continue • Sandbox allows nested user namespaces on Linux, enabling Chromium and rootless podman to run there Complete details in thread ↓

Claude Code 2.1.304 has been released. 76 CLI changes Highlights: • tool.check decider:\"person\" makes a mod require human approval; unapproved asks are refused with mod reason • Added /auto-mode-setup: guided scan of project and history so Auto Mode learns environment for smarter actions • Added /claude-api managed-agents-secure: read-only check flags Managed Agents deviations vs Anthropic guide Full details available in thread ↓

Claude Code 2.1.303 has been released. 1 CLI change Highlights: • CLI bug fixes reduce crashes and command failures, improving workflow reliability and predictability Complete details in thread ↓

Claude Code 2.1.302 has been released. 63 CLI changes Highlights: • Read tool refuses image sources over 128 MB to avoid loading large files into memory and crashing • Prompt suggestions omit credit-billed models after a credit-billed reply, avoiding unexpected credit use • Added 'Idle compaction' on/off in /config; post-compaction notices now show how to disable it Complete details in thread ↓

Claude Code 2.1.301 system prompt updates Notable changes: 1) Claude is now explicitly scoped to authorized security testing/defensive work/CTFs/education. It must refuse destructive techniques (incl. DoS, mass targeting, supply chain compromise, malicious detection evasion) and require clear authorization context for dual-use tooling. Links: 1) github.com/marckrenn/claude-…

Claude Code 2.1.301 is now available. 51 CLI changes, 1 system prompt change Highlights: • System prompt adds security-testing scope and must refuse out-of-scope probes, blocking unauthorized testing • Unattended retry mode now aborts requests when the next usage-limit reset is far in the future Complete details in thread ↓

Claude Code 2.1.300 system prompt updates Notable changes: 1) Claude no longer receives the explicit "AskUserQuestion" directive. In its place, the prompt now injects a "claude-mermaid-runtime-begin" marker right before the Harness block, shifting behavior away from forced question-asking and toward a runtime-wrapped/flagged instruction section (likely tied to Mermaid handling). Links: 1) github.com/marckrenn/claude-…

Claude Code 2.1.300 has been released. 88 CLI changes, 1 system prompt change Highlights: • Added virtualText: prompt-box text excluded from draft/submitted prompt, so it stays out of model input • $.ui.view({agentId}) shows agent transcript in main view; $.ui.view({}) returns to prior view for quick review • prompt.change hook fires on non-typed prompt edits (history/clear/undo/plugin fill), lets mods react Complete details in thread ↓

Claude Code 2.1.299 has been released. 190 CLI changes, 1 system prompt change Highlights: • Added --disallow-tools to claude plugin eval to block specified built-in tools during runs and avoid tool bias • Model accepts security-testing/dual-use prompts and uses AskUserQuestion to clarify, so they are not refused • Idle compaction compacts chats over 200K tokens after ≈54m idle, preventing full reprocessing on resume Full details are in thread below