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 v2.1.282 ·

allowManagedPermissionRulesOnly now also withholds allowed-tools from user and project skills

Under allowManagedPermissionRulesOnly, allowed-tools in untrusted skill, command and plugin frontmatter no longer grants tool permissions

Group of 3 You'll notice Improvements
JSON All of v2.1.282
You'll noticeTier: how much it should matter to you
2Useful: my rating, 1 to 5
2Signal: worth watching, 1 to 5
PermissionsArea: what it touches
ImprovementsKind: in v2.1.282,
ImprovementsSection of the release

Unclear Which skill and plugin sources count as trusted, beyond the official skills marketplace, is not settled.

What

When the managed policy setting allowManagedPermissionRulesOnly is on, the allowed-tools list in skill and command frontmatter (the header at the top of a skill file) no longer grants tool permissions unless it comes from a trusted source. Until now the setting covered permission rules from settings files and --allowedTools.

  • Ignored: allowed-tools from skills and custom commands in user, project and --add-dir sources, and from plugins adopted from a .claude-plugin manifest inside those skills directories.
  • Kept, per the setting's description: other plugins, managed skills and bundled skills. Plugins from the official skills marketplace are exempt.
  • Skills and plugin commands now look up their allowed-tools each time they run. When a grant is dropped, a warning is logged, and in text print mode a line on standard error tells you to ask an admin.
  • A plugin command whose frontmatter declares PreToolUse or PermissionRequest hooks gets no allowed-tools at all when policy sets disableAllHooks or allowManagedHooksOnly.
  • The coordinator no longer tells its workers that a skill grants extra tool permissions when the skill's source or plugin is not trusted under this policy.
  • The setting's description now says all of this.

Why

A skill or plugin placed by a user or a repository could previously hand itself tool permissions that the policy meant to keep in the administrator's hands. If you rely on a skill's allowed-tools under this policy, expect permission prompts for those tools, or ask your administrator to add managed rules.

Read from
Names in the bundleallowed-tools
Since it was published

The entry above is what we published on the day. These lines were added later, as Anthropic's own pages caught up, and they sit beside the original rather than replacing it.

Added since A small documentation edit on Extend agents with skills touched a line naming allowed-tools after this was published. In SDK sessions, you can pre-approve tools for a project or personal skill with the skill's [`allowed-tools`](/docs/en/skills#pre-approve-tools-for-a-skill) frontmatter or with the `allowedTools` option (`allowed_tools` in Python) in your … agent-sdk/skills see the edit
Confirmed since Anthropic's documentation has since written up allowed-tools, on Claude Code changelog. * Fixed plugins from marketplaces, claude.ai and npm pre-approving their own tools via `allowed-tools` under managed `allowManagedPermissionRulesOnly`; only plugins from an official Anthropic source or a source that managed settings vouch … changelog see the edit
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 doubtWhich skill and plugin sources count as trusted, beyond the official skills marketplace, is not settled.
Anthropic's documentation agreesAnthropic's documentation has since written up allowed-tools, on Claude Code changelog.
Anthropic's release notes agreeFixed managed settings ignoring a mistyped value for boolean lock keys such as disableClaudeAiConnectors or allowManagedPermissionRulesOnly…

See this entry in the whole of v2.1.282 →

Feedback