Claude OPUS 4.7 · AI Automation Society

Nei E Maldaner

2d (edited) • General Discussion 💬

Claude OPUS 4.7

Version 2.1.111 Updates

Model

Command: /model

Model kept as Opus 4.7 (1M context) (default)

Key Highlights

Claude Opus 4.7 xhigh is now availableUse /effort to tune the balance between speed and intelligence.
Auto mode is now available for Max subscribers when using Opus 4.7.
New xhigh effort level for Opus 4.7Positioned between high and max. Available via:

/effort Improvements

Calling /effort without arguments now opens an interactive slider.
Navigate using arrow keys.
Confirm with Enter.

Theme & Interface

New “Auto (match terminal)” themeAutomatically matches your terminal’s light/dark mode.Available via /theme.
/skills menu now supports sorting by estimated token countPress t to toggle.
Ctrl+U now clears the entire input bufferPreviously: deleted to the start of the lineUse Ctrl+Y to restore.
Ctrl+L now:
Transcript footer now shows shortcuts:
The “+N lines” truncation marker is now a full-width rule for better visibility.

New Features & Skills

New skill: /less-permission-promptsScans transcripts for common read-only Bash and MCP tool calls and suggests a prioritized allowlist for .claude/settings.json.
New command: /ultrareviewRuns a comprehensive cloud-based code review using parallel multi-agent analysis.

Auto Mode

Auto mode no longer requires --enable-auto-mode.

Windows, Linux & macOS

Windows: PowerShell tool is rolling out graduallyToggle via:
Linux/macOS: enable with:

Permissions & Prompts

Read-only Bash commands with glob patterns (e.g. ls *.ts)
Commands starting with:

These no longer trigger permission prompts.

Usability Improvements

Suggests closest matching subcommand on typosExample:
Plan files are now named after your promptExample:
Improvements to /setup-vertex and /setup-bedrock:

Logs, Debugging & Stability

Headless --output-format stream-json now includes plugin_errors in the init event when plugins are demoted due to missing dependencies.
New environment variable:
Suppressed noisy messages related to:
Reverted the v2.1.110 retry cap for non-streaming fallbackIt reduced wait times but increased failure rates under API load.

Here’s a clear and concise summary

Claude Opus 4.7 was released as an improved version of 4.6, focusing on better quality, accuracy, and reliability. It brings:

Stronger performance on complex tasks (especially coding)
Better instruction-following
Fewer errors and hallucinations
Ability to self-check and correct reasoning
Improved vision, creativity, and document analysis
Better long-context handling (up to 1M tokens)

A key addition is the “xhigh” effort level, allowing deeper reasoning, along with adaptive thinking.

Previous issues (Opus 4.6)

Users reported that 4.6 had degraded because:

It was “thinking less”
Skipped important steps (like reading files before editing)
Produced more shallow outputs
Made more mistakes and abandoned tasks
Consumed tokens inefficiently

These issues were largely due to configuration changes (reduced effort), not the core model itself.

What changed in 4.7

Opus 4.7 directly addresses these problems:

More consistent and deeper reasoning
Better task execution
More structured and useful outputs
Improved overall reliability

Considerations

May use more tokens (higher cost)
Benchmark improvements don’t always reflect real-world use
Some improvements may come from restoring previous settings rather than entirely new capabilities

Conclusion

Opus 4.7 appears to be a solid upgrade over 4.6, especially for complex workflows.However, real-world testing is still essential to fully validate its performance.

5 comments