Claude Code 2.1.142: new claude agents flags + fast mode defaults to Opus 4.7
Claude Code 2.1.142 adds new claude agents flags for background sessions, switches fast mode to Opus 4.7 by default, and ships a large set of reliability fixes across plugins, MCP, daemon behavior, and OS-specific edge cases.
Editorial Team
The Authority AI Tools editorial team maintains this directory using vendor documentation, dated source checks, product changelogs, and clearly identified hands-on observations where available.
Anthropic’s Claude Code 2.1.142 release adds new configuration flags for dispatched background sessions (via claude agents) and changes fast mode to default to Opus 4.7 (previously Opus 4.6). (https://code.claude.com/docs/en/changelog)
Anthropic's terminal-based AI coding agent with Claude Opus 4.7, /ultrareview, Routines, /ultraplan, and 80.9% SWE-bench
New claude agents flags
The changelog lists new claude agents flags intended to configure dispatched background sessions:
--add-dir--settings--mcp-config--plugin-dir--permission-mode--model--effort--dangerously-skip-permissions
(https://code.claude.com/docs/en/changelog)
Fast mode now defaults to Opus 4.7
Anthropic says fast mode now uses Opus 4.7 by default, and documents an override to pin fast mode to Opus 4.6:
CLAUDE_CODE_OPUS_4_6_FAST_MODE_OVERRIDE=1
(https://code.claude.com/docs/en/changelog)
Reliability and workflow fixes (highlights)
Claude Code 2.1.142 also includes a long list of reliability fixes across:
- background sessions and daemon reconnect behavior (including handling macOS sleep/wake clock jumps),
- MCP tool timeout configuration,
- plugin discovery and plugin-cache behavior, and
- Windows-specific issues (including Ctrl+C and network-drive working directories).
(https://code.claude.com/docs/en/changelog)
Sources
Tools Mentioned in This Article
Free Resource
2026 AI Coding Tools Comparison Chart
Side-by-side comparison of features, pricing, and capabilities for every major AI coding tool.
No spam, unsubscribe anytime.
Workflow Resources
Cookbook
AI-Powered Code Review & Quality
Automate code review and enforce quality standards using AI-powered tools and agentic workflows.
Cookbook
Building AI-Powered Applications
Build applications powered by LLMs, RAG, and AI agents using Claude Code, Cursor, and modern AI frameworks.
Cookbook
Building APIs & Backends with AI Agents
Design and build robust APIs and backend services with AI coding agents, from REST to GraphQL.
Cookbook
Debugging with AI Agents
Systematically debug complex issues using AI coding agents with structured workflows and MCP integrations.
MCP Server
AWS MCP Server
Interact with AWS services including S3, Lambda, CloudWatch, and ECS from your AI coding assistant.
MCP Server
Context7 MCP Server
Fetch up-to-date library documentation and code examples directly into your AI coding assistant.
MCP Server
Docker MCP Server
Manage Docker containers, images, and builds directly from your AI coding assistant.
MCP Server
Figma MCP Server
Access Figma designs, extract design tokens, and generate code from your design files.
Frequently Asked Questions
What is Claude Code 2.1.142: new claude agents flags + fast mode defaults to Opus 4.7?
Related Articles
Codex 0.157.0 adds GPT-6 models, fullscreen transcripts, and smoother sessions
OpenAI Codex CLI 0.157.0 adds GPT-6 Sol and Luna, automatic background-server startup, fullscreen transcripts, conversation forking, and remote-session imports.
Read more →Product UpdatesGemini CLI 0.61.0 hardens sandbox boundaries and prompt-injection defenses
Google’s September 23, 2026 Gemini CLI 0.61.0 release hardens filesystem isolation, blocks indirect prompt injection paths, preserves versioned model IDs, and improves agent-loop reliability.
Read more →Product UpdatesCursor launches Rollouts and Security Review bots for production changes
Cursor’s September 23, 2026 release adds Rollouts for deployment health monitoring and Security Review for exploitable bugs on pull requests.
Read more →