[waleedlatif1]

Summary

• The add-integration skill's token-credential steps name the typed-URL guard refuseUrlCredentials, which was renamed to refuseUnsafeTypedUrl before feat(credentials): saved credentials for 21 token-and-host blocks on one host-aware check factory #9849 merged. This points the skill at the helper that exists. Raised in review on the v0.9.53 release PR.

Type of Change

• Documentation

Testing

Docs-only change to .agents/skills/add-integration/SKILL.md; git grep refuseUrlCredentials now returns nothing.

Checklist

• Code follows project style guidelines
• Self-reviewed my changes
• Tests added/updated and passing (new tests pass the test-audit authoring gate)
• No new warnings introduced
• I confirm that I have read and agree to the terms outlined in the Contributor License Agreement (CLA)

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated
docs	Ready	Preview	Nov 11, 2026 2:19am UTC

[cubic-dev-ai]

No issues found across 1 file

Confidence score: 5/5

• Automated review surfaced no issues in the provided summaries.
• No files require special attention.

_{Turn on auto-fix | Re-trigger cubic}

[greptile-apps]

Confidence Score: 5/5

[Low impact] This documentation-only correction appears safe to merge.

Summary

Corrects the token-credential steps in the add-integration skill to name refuseUnsafeTypedUrl instead of refuseUrlCredentials.

• The integration guide names the typed-URL guard used by the code.

_{Reviews (1) · Last reviewed commit: "docs(skills): name refuseUnsafeTypedUrl ..." · Reviewed by Greptile}