Claude Discovery

← All discoveries

Close-up of a hand holding a smartphone displaying app updates on a light background.
Photo by Andrey Matveev on Pexels
tool

Claude Code 2.1.215 makes /verify and /code-review opt-in again

2026-07-19 ยท source: anthropics/claude-code

Claude Code 2.1.215 stops automatically invoking the /verify and /code-review skills, requiring users to run them explicitly with the /verify or /code-review commands.

What it is

A small point release of Claude Code, the CLI coding agent, following closely on the heels of 2.1.214.

What it does

It removes Claude's ability to decide on its own to run the /verify and /code-review skills mid-session; those checks now only fire when you explicitly type the command.

Why it matters

Silent self-invoked review steps eat tokens and time without you asking for them. Making these opt-in again gives back control over when Claude spends a turn double-checking its own work instead of quietly doing it whenever it feels like it.

How to use it

Update Claude Code to 2.1.215 or later, then run /verify or /code-review manually whenever you want that check; it will no longer happen automatically in the background.

Go to source →
claude-coderelease-notescli
Related discoveries
A young couple sitting together, using a smartphone on a sunny day in the park.
tool

Claude Code v2.1.208 adds screen reader mode and vim insert-mode remaps

Claude Code v2.1.208 introduces an opt-in plain-text screen reader mode and a setting to remap two-key vim insert-mode sequences like jj to Escape.
A classic MS-DOS terminal screen displayed on a laptop keyboard with vivid illumination.
tool

Claude Code v2.1.210: worktree isolation bug fix and safer permission-rule warnings

Claude Code 2.1.210 fixes worktree-isolated subagents being able to run git-mutating commands against the main repo checkout instead of their own worktree.
Laptop displaying a security lock icon on a table with a potted plant and clock.
tool

Claude Code v2.1.211: forwarded subagent text and hardened permission-preview rendering

Claude Code v2.1.211 adds a flag to forward subagent text and thinking into stream-json output and strips hidden characters attackers could use to spoof permission-approval prompts.