Context Drift

Use this skill to audit or repair drift across a repository's load-bearing context files without losing detail or blurring the boundaries between them.

If this skill loads and the rest of the turn contains no human-authored task text — including when the only other content is an automated system or tooling notice, such as a diagnostics or context message — do not conclude that there is nothing to act on. The skill loading at all, by itself, is the request. Begin Stage 1 immediately against the current repository using the defaults in this document. Do not wait, do not just acknowledge that the skill is available, and do not ask what to work on.

Authority model

This skill is an orchestrator, not the final authority on what belongs in each file.

Before judging drift, invoke or load the relevant owner skills for the in-scope files up front. Use their own separation-of-concerns rules, file-specific guardrails, and document-ownership logic as the authority for what belongs where. This skill coordinates the cross-file comparison, the lossless move plan, and the approval loop. It should not make independent file-ownership calls and only bring the owner skills in at the end.

If two owner skills point in different directions, surface that conflict to the user instead of overruling it here.

Canonical ownership model

Use this ownership model as a routing map before you call anything redundant, misplaced, or stale. It is a quick index into the owner skills, not a replacement for their judgment.