Claude Code v2.1.142: New claude agents flags, Opus 4.7 default, and bug fixes

Anthropic released Claude Code v2.1.142 with significant updates to the claude agents subsystem, a default model change in fast mode, and a long list of bug fixes.
New claude agents flags
Eight new flags are available to configure dispatched background sessions:
--add-dir— additional directories--settings— settings file path--mcp-config— MCP configuration--plugin-dir— plugin directory--permission-mode— permission mode for the session--model— model override--effort— effort level--dangerously-skip-permissions— skip permission prompts
Previously these were only configurable via environment variables or the daemon configuration file; now they can be passed directly when starting a background agent.
Fast mode defaults to Opus 4.7
Fast mode now uses Opus 4.7 by default, replacing Opus 4.6. If you need to pin fast mode to Opus 4.6, set the environment variable:
CLAUDE_CODE_OPUS_4_6_FAST_MODE_OVERRIDE=1Plugin improvements
Plugins with a root-level SKILL.md and no skills/ subdirectory are now correctly surfaced as a skill. The /plugin details pane and claude plugin details command now display the LSP servers a plugin provides.
Notable bug fixes
- MCP_TOOL_TIMEOUT — fixed so it actually raises the per-request fetch timeout for remote HTTP and SSE MCP servers. Previously, tool calls were capped at 60 seconds regardless of the configured value.
- macOS sleep/wake — background sessions no longer disappear after sleep/wake. The daemon now detects clock jumps instead of treating them as elapsed idle time.
- Daemon upgrade — the daemon now exits cleanly after the binary is upgraded (e.g.,
brew upgrade), preventing dispatched agents from crash-looping on the deleted binary path. - Windows network drives — background agents no longer deadlock when working directories are on network drives; Ctrl+C now works during startup.
- Editor detection —
claude agents"v to open in editor" now uses your shell's$EDITOR/$VISUALinstead of the daemon's default editor. - Terminal color bleed — fixed background-color bleed when attaching to a session from Apple Terminal or other 256-color-only terminals.
- Permissions persistence —
claude --bg --dangerously-skip-permissionsnow persists across retire/wake cycles. - Plugin cache — no longer deletes the active plugin version directory when installation metadata is missing.
Other improvements
- Reactive compaction — the first summarize attempt now seeds from the original request's overflow size, avoiding a wasted near-full-context retry.
- Hook configuration — configuring a prompt- or agent-type hook for
SessionStart/Setup/SubagentStartnow shows a clear error suggesting to use a command-type hook instead. - Removed stale
/model claude-sonnet-4-20250514suggestion from Usage Policy refusal messages.
📖 Read the full source: GitHub Claude-Code
👀 See Also

Keyoku Plugin Replaces OpenClaw's Static Heartbeat with Memory-Driven Autonomy
Keyoku is a free OpenClaw plugin that changes the agent's heartbeat from reading a static HEARTBEAT.md file to scanning the agent's actual memory store for stalled work, dropped commitments, conflicting information, and quiet relationships. It uses a local Go engine with SQLite + HNSW and offers three autonomy levels: observe, suggest, and act.
Terry Tao Ports 24 Java Applets to JavaScript with LLM Agent — Finds Bugs in Original Code
Terence Tao used an LLM coding agent to port his 1999 Java applets to JavaScript in hours. The agent found two bugs in the original code and introduced only one minor drag-handling issue.

audio-analyzer-rs: An MCP Server for Audio Analysis with Claude
A developer built audio-analyzer-rs, an MCP server in Rust that gives Claude direct access to audio file analysis including spectral, harmonic, rhythm, LUFS loudness (EBU R128), and dynamic range measurements. The tool is token-efficient, with Claude starting at low resolution and zooming in on small chunks as needed.

OpenClaw users report planning and review bottlenecks with AI agents
OpenClaw users describe planning and review workflows as 'MS-DOS-like' despite effective code generation, citing manual intervention, document fragmentation, and loss of reasoning during agent collaboration. Some are experimenting with agent-native document editors like comment.io and Proof by Every.