Follow Discord
Sweep 01 Oct 2026 · 17:27Z Build v2.1.287 508 read Stable v2.1.285 Latest v2.1.287 Next v2.1.287 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeDocsClaude Code CLI 30 Sep 2026
One change · claude-code

Extend Claude with skills changedskills

Nearest release: v2.1.286, published 2 hours before upstream edited the page. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.

Upstream edited this page at 30 Sep 2026 19:23 UTC, give or take a minute or two: the time comes from Anthropic’s own sitemap rather than from a commit. This site recorded the change at 30 Sep 2026 19:37 UTC.

Upstream edited
Recorded here
Lines+9added
Lines−1removed
From line 551 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits56to this page, all time

### Claude stops following a skill

The whole hunk

from line 551, old and new numbered
/
lines
from line 551
551551 
552552[Auto-compaction](/docs/en/how-claude-code-works#when-context-fills-up) carries invoked skills forward within a token budget. When the conversation is summarized to free context, Claude Code re-attaches the most recent invocation of each skill after the summary, keeping the first 5,000 tokens of each. Re-attached skills share a combined budget of 25,000 tokens. Claude Code fills this budget starting from the most recently invoked skill, so older skills can be dropped entirely after compaction if you have invoked many in one session.
553553 
554If a skill seems to stop influencing behavior after the first response, the content is usually still present and the model is choosing other tools or approaches. Strengthen the skill's `description` and instructions so the model keeps preferring it, or use [hooks](/docs/en/hooks) to enforce behavior deterministically. If the skill is large or you invoked several others after it, re-invoke it after compaction to restore the full content.
554If Claude stops following a skill partway through a session, see [Claude stops following a skill](#claude-stops-following-a-skill).
555555 
556556### Pre-approve tools for a skill
557557 
from line 1126
11261126 
112711271. Make the description more specific
112811282. Add `disable-model-invocation: true` if you only want manual invocation
1129 
1130### Claude stops following a skill
1131 
1132If Claude follows a skill in its first response and stops following it later, start with whichever of these cases matches:
1133 
1134* **Claude skipped a rule that must hold every time**: move the rule into a [hook](/docs/en/hooks-guide). Claude Code runs a hook every time its event occurs, such as before each file edit, whether or not Claude is following the skill. To keep the rule with the skill, define the hook in the skill's [`hooks` frontmatter](/docs/en/hooks#hooks-in-skills-and-agents). That hook applies from the time the skill is invoked until the session ends.
1135* **Claude skipped guidance it should apply with judgment**: word the guidance so it applies to the whole task, for example "Run the tests after every edit" rather than "Run the tests". Claude Code adds the skill's content to the conversation when the skill is invoked and [doesn't re-read the file](#skill-content-lifecycle) on later turns.
1136* **The conversation was compacted**: invoke the skill again to restore its full content. After [compaction](/docs/en/how-claude-code-works#when-context-fills-up), Claude Code [can keep only the start of an invoked skill](#skill-content-lifecycle), so put the most important instructions near the top of `SKILL.md`.
11291137 
11301138### Skill descriptions are cut short
11311139 
Feedback