/review-structure

name: review-structure
description: Repo-wide structural-maintainability review — code-judo restructurings, 1k-line file guard, anti-spaghetti branching, canonical-layer enforcement, anti-magic abstractions, explicit type/boundary contracts.
disable-model-invocation: true

Structural-Maintainability Review

Use this skill for an unusually strict review focused on implementation quality, maintainability, abstraction quality, and codebase health.

Above all, this skill should push the reviewer to be **ambitious** about code structure. Do not merely identify local cleanup opportunities. Actively search for "code judo" moves: restructurings that preserve behavior while making the implementation dramatically simpler, smaller, more direct, and more elegant.

The structural lens is **repo-wide**: read and search any file in the codebase as needed to judge whether canonical helpers already exist, whether file-size budgets are honored, and whether the change makes the codebase easier or harder to live with.

Anti-confabulation (gate 0 — runs before every other gate)

Before issuing **any** verdict — flag, propose a restructuring, or assert a structural claim — you MUST echo the exact artifact you are judging, quoted from a source you read in **this** turn:

• For a code finding: the **file:line** plus the cited code, read freshly now (not recalled from earlier in the session).
• For a structural claim ("no canonical helper exists", "file exceeds 1 000 lines"): the **search pattern + result** or **`wc -l`/read-based count** that backs it.

> The artifact is the only source of truth. **Never** infer what you are reviewing from the branch name, the working directory, surrounding files, or recollection. If your mental model differs from the freshly read source, **the source wins.** A verdict issued without a same-turn echo of its target is invalid — emit the echo first, or do not emit the verdict.

This gate exists because an LLM under contextual priming will confidently flag code that is not in the file. It runs **before** the hard gates below.

Hard gates (sequence)

Advance only when each **pass condition** is objectively satisfied (artifact path, tool output, or labeled capture — not "I checked it mentally"):

| Gate | Pass condition | |------|----------------| | **G1 — Changed-file list** | `git diff --name-only` (or equivalent) returns a non-empty list *or* you exit with an explicit "no changed files" message; the list is recorded before any review step begins. | | **G2 — Full file reads** | Every file in scope has been read in full; for each file you record the path and line count (e.g. `src/foo.ts — 342 lines`). Do **not** proceed to findings until all reads are logged. | | **G3 — Canonical-helper and 1k-line claims verified** | Any finding that asserts "no canonical helper exists" must cite a codebase-search artifact showing the search pattern and result. Any finding that asserts a file exceeds 1 000 lines must cite a `wc -l` or read-based line-count artifact. Findings lacking these artifacts are **blocked** from the report. |

Core Prompt

Start from this baseline:

> Perform a deep structural review of the current branch's changes. > Rethink how to structure / implement the changes to meaningfully improve code quality without impacting behavior. > Work to improve abstractions, modularity, reduce spaghetti code, improve succinctness and legibility. > Be ambitious — if there is a clear path to improving the implementation that involves restructuring some of the codebase, go for it. > Be extremely thorough and rigorous. Measure twice, cut once.

Non-Negotiable Additional Standards

Apply the baseline prompt above, plus these explicit review rules:

0. **Be ambitious about structural simplification.**

• Do not stop at "this could be a bit cleaner."
• Look for opportunities to reframe the change so that whole branches, helpers, modes, conditionals, or layers disappear entirely.
• Prefer the solution that makes the code feel inevitable in hindsight.
• Assume there is often a "code judo" move available: a re-organization that uses the existing architecture more effectively and makes the change dramatically simpler and more elegant.
• If you see a path to delete complexity rather than rearrange it, push hard for that path.

1. **Do not let a PR push a file from under 1k lines to over 1k lines without a very strong reason.**

• Treat this as a strong code-quality smell by default.
• Prefer extracting helpers, subcomponents, modules, or local abstractions instead of letting a file sprawl past 1000 lines.
• If the diff crosses that threshold, explicitly ask whether the code should be decomposed first.
• Only waive this if there is a compelling structural reason and the resulting file is still clearly organized.

2. **Do not allow random spaghetti growth in existing code.**

• Be highly suspicious of new ad-hoc conditionals, scattered special cases, or one-off branches inserted into unrelated flows.
• If a change adds "weird if statements in random places", treat that as a design problem, not a stylistic nit.
• Prefer pushing the logic into a dedicated abstraction, helper, state machine, policy object, or separate module instead of tangling an existing path.
• Call out changes that make the surrounding code harder to reason about, even if they technically work.

3. **Bias toward cleaning the design, not just accepting working code.**

• If behavior can stay the same while the structure becomes meaningfully cleaner, push for the cleaner version.
• Do not rubber-stamp "it works" implementations that leave the codebase messier.
• Strongly prefer simplifications that remove moving pieces altogether over refactors that merely spread the same complexity around.

4. **Prefer direct, boring, maintainable code over hacky or magical code.**

• Treat brittle, ad-hoc, or "magic" behavior as a code-quality problem.
• Be skeptical of generic me