Fetching from the wire…
01
02
03
04
05
06
07
08
Public story · 2026-08-17 · high
A local skill sharing a bundled command's name broke /checkup and /review in -p mode with no error pointing to the cause.
Why now: This shipped in the 2.1.233 changelog covered on August 17, 2026.
Claude Code 2.1.233 fixed bundled commands like /checkup failing with "Unknown command" in -p mode when a local skill shared the name, per the changelog.
Anyone running Claude Code headlessly hit silent failures that looked like a broken command, not a naming conflict. /review had the same bug.
The fix targets one collision: a user or project skill in .claude/skills shadowing a bundled skill with the same name. It also hit sessions with plugins or MCP loaded.
If your automation calls a bundled command headlessly and it stopped working, check .claude/skills for a matching name first.
The same release added a check to claude plugin validate for a bare .claude/skills directory. It now reports SKILL.md files whose frontmatter fails to parse.
The patch fixes this specific alias clash. The namespace itself, where a project's own skill can silently shadow a built-in command, doesn't change. Expect a similar report the next time a plugin or project skill happens to match a built-in name. Watch whether Claude Code adds a load-time warning for the collision instead of patching each alias one by one.
Each link below shares sources, entities, or timing with this story.
One Claude Code release fixed two independent permission-check bypasses on the same day. That's the story. Version 2.1.221, shipped August 4, patches a Bash tool bypass where zsh could execute hidden commands embedded inside [[ ]] regex conditionals. The approval prompt never...
SkillsMetric evaluated 2,266 skills across 16 attack types, hitting F1 of 73.4%±0.5% overall (arXiv 2608.08468). Host destruction via shell commands: 0% detection. Natural-language prompt injection: 42%. If you lint third-party skills before install, this tells you precisely w...
That's an 8x reduction from a single architectural change: don't inline the reference docs, load them when needed. If you write skills, this is the pattern. Check what your SKILL.md costs on load versus what it costs when actually used. (Claude Code changelog)
It scans prompts and tool descriptions for patterns written for older model generations. This targets a real invisible tax: system prompts and MCP tool descriptions accumulate verbose few-shot blocks, defensive formatting instructions, and reasoning nudges that earned their ke...
It now dedupes local CLAUDE.md files against checked-in ones, proposes trimming content it can derive from the codebase, ranks unused skills, MCP servers, and plugins by context cost, and flags slow hooks. Background subagents run by default and, when launched from claude agen...
1. Flip your multi-model pipeline to review-then-generate. Instead of using a reasoning model to plan before code generation, let the specialist generate freely and use reasoning tokens for review. Paper shows 90.2% pass@1 vs 87.2% for the planning pattern. Source 2. Audit you...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.