Fetching from the wire…
Public story · 2026-09-06 · high
The skill-doctor report in 2.1.261 flags which skills never fire and needs Claude Code 2.1.252 or later.
Why now: Claude Code 2.1.261 is the release where skill costs become visible for the first time.
Claude Code 2.1.261 adds a skill-doctor report that lists every loaded skill, its context cost, and whether it ever fires, according to the changelog.
The full skill listing goes out with every turn, whether or not anything in it fires. A collection built up over months becomes a fixed cost on every request, one nobody could measure before this report existed.
The report opens in the /plugin manager's Stats tab when you're working interactively, showing loaded-but-unused skills next to their context cost. Run Claude Code non-interactively with -p and it prints the same information as plain text. It needs Claude Code 2.1.252 or later to run at all.
A skill with real context cost and no invocations is safe to turn off. For now, that's a manual call. Nothing disables a skill automatically just because skill-doctor flags it.
Each link below shares sources, entities, or timing with this story.
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...
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...
Released July 10, /doctor scans checked-in CLAUDE.md files and flags content Claude could derive by reading the codebase itself. This is the first time Anthropic has shipped tooling treating context files as a cost surface to prune rather than a document to grow. Same release...
This one rearranged my week. An essay published August 4 walks through Databricks' independent benchmark of coding harnesses against its own multi-million-line codebase. Pi, a harness with four built-in tools and a system prompt under 1,000 tokens, paired with Opus 4.8 at xhig...
The changelog through 2.1.235 (code.claude.com) confirms the todo-tool removal from Opus 4.8, Sonnet 5, Fable 5, and Mythos 5+ that ran here on 2026-08-15 is restorable with that flag. Everything else in this window has already been covered: the Bash memory cgroups and the tod...
Claude Code 2.1.232 shipped August 13 with a default flipped underneath everyone. Subagent forking is now on: a spawned subagent inherits the full parent conversation and shares its prompt-cache prefix instead of starting cold. Nested spawn depth defaults to 3. Practitioner wr...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.