Follow Discord
Sweep 22 Oct 2026 · 21:04Z Build v2.1.309 528 read Stable v2.1.308 Latest v2.1.309 Next v2.1.309 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.309 ·

Nested skills allowed only by full name are handled separately

Nested skills now carry an allowlistedByFullNameOnly mark when only their full name is allowlisted, and such commands are filtered like MCP prompts

Group of 2 You'll notice Improvements
JSON All of v2.1.309
You'll noticeTier: how much it should matter to you
1Useful: my rating, 1 to 5
1Signal: worth watching, 1 to 5
SkillsArea: what it touches
ImprovementsKind: in v2.1.309,
ImprovementsSection of the release

Unclear Whether a nested skill listed in an allowlist by its plain name is still covered is not clear.

What

Skills are reusable instructions Claude can run, and they can sit in nested folders, which gives them a scoped full name as well as a plain name. A skill now carries allowlistedByFullNameOnly when its full name differs from the plain name that appears in the allowlist.

A prompt-type command with allowlistedByFullNameOnly set is now left out by the same check that already left out prompts from memory stores and MCP servers.

Forked commands also work out which MCP read tools a hidden built-in can use.

Why

This affects whether allowed-tools rules apply to skills in nested folders, and may change which skills or commands are shown or listed.

How sure we are
Something disagreesSomething we can check disagrees with this entry, or the writer said they could not settle it.
The writer flagged doubtWhether a nested skill listed in an allowlist by its plain name is still covered is not clear.

See this entry in the whole of v2.1.309 →

Feedback