Tidy

The cleanup walk runs in a fresh host-provided reviewer per iteration when reviewer dispatch is available; Edit application stays in the main thread to keep the reviewer bias-free. The skill loops the dispatch + apply cycle until the reviewer returns no more mechanical_edits, max iterations is reached, or a safety rail trips. Designed to be called from non-interactive routines; it never prompts the user.

Scope: invocation targets are arbitrary source files (application code, config, SKILL.md, any text). The skill does not restrict the changed-file set to a fixed directory prefix — any path in the diff is reviewed unless caught by the exclusion list (Step 1 step 3).

Invocation contract

The caller passes these fields in natural language (the skill extracts them from the invocation text):

• Base ref (optional, default <working-tree-vs-HEAD>) — git ref to diff against. When omitted, the skill looks at the working tree's uncommitted + staged + untracked changes (the default scope for a post-implementation cleanup pass). When specified (e.g. Base ref: main), the skill switches to git diff <Base ref> semantics — useful for callers that want to review a stack of already-committed changes between a base branch and HEAD.

  Untracked-file scope asymmetry: the default mode includes untracked new files (collected via git status --porcelain=v1 --untracked-files=all -z), but the explicit Base ref mode reads committed history only and excludes untracked files. A caller passing Base ref: HEAD~5 expecting "everything since base" will silently miss new files added since HEAD~5 that were never committed. If you need untracked files in scope, omit Base ref and rely on the working-tree default.

• Max iterations (optional, default 3) — upper bound on the refinement loop. Cleanup polish typically converges in 1–2 iterations.

• Custom instructions (optional) — free-form text injected into the dispatch payload as additional constraints alongside the cleanup checklist. Orchestrators that carry their own custom_instructions config (e.g. workflow steps that pass project-wide constraints) route that text through this field.

• Model (optional) — model id (sonnet / opus / haiku) applied as the model parameter on the reviewer Agent dispatch in Step 3 (a). An independent optional field (not part of a fixed-arity mode gate); a caller such as dev-workflow passes it to run the cleanup reviewer on a specific model. Because this skill runs a per-iteration dispatch loop, the same value is applied to every iteration's reviewer dispatch. Effective only on the Claude Code Agent-dispatch path; on the reviewer-dispatch-unavailable inline fallback (Step 3 (a)) no Agent is spawned, so the value is moot (the executing agent's own model governs). Validity predicate: a value is valid only if it is exactly one of the closed set {sonnet, opus, haiku} (the ids the Agent model parameter accepts); an absent field or any value outside that set (including a full claude-* id) is invalid → no override; the reviewer Agent inherits the session model (backward-compatible default).