code-review

name

code-review

description

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Intent (does the code match the user prompt, Plannator plan, issue, task, PRD, commit message, or other source of intended behavior?). Runs both reviews in parallel sub-agents when the review is large enough and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

Two-axis review of the diff between HEAD and a fixed point the user supplies:

• Standards — does the code conform to this repo's documented coding standards?
• Intent — does the code faithfully implement the available source of intended behavior?

Intent can come from a user prompt, Plannator plan, issue, task, PRD, commit message, or another explicit source. If no intent source exists, skip this axis and say so.

For large reviews, run the axes as parallel sub-agents so they don't pollute each other's context, then aggregate their findings. For small diffs, you may perform the review directly.

Process

1. Pin the fixed point

Whatever the user said is the fixed point — a commit SHA, branch name, tag, main, HEAD~5, etc. If they didn't specify one, ask for it.

Capture the diff command once: git diff <fixed-point>...HEAD (three-dot, so the comparison is against the merge-base). Also note the list of commits via git log <fixed-point>..HEAD --oneline.

Before going further, confirm the fixed point resolves (git rev-parse <fixed-point>) and the diff is non-empty. A bad ref or empty diff should fail here — not inside two parallel sub-agents.

2. Identify the intent source

Look for the source of intended behavior, in this order:

1. A path, issue, task, Plannator plan, PRD, or spec the user passed as an argument.
2. Explicit instructions in the current conversation.
3. Issue references in the commit messages (#123, Closes #45, GitLab !67, etc.) when the repo has an obvious way to fetch them.
4. A PRD/spec/plan file under docs/, specs/, .scratch/, or similar matching the branch name or feature.
5. Commit messages that clearly describe intended behavior.

If nothing is found, skip the Intent axis and report "intent review skipped: no intent source found". Do not invent a spec.

3. Identify the standards sources

Anything in the repo that documents how code should be written, such as CODING_STANDARDS.md or CONTRIBUTING.md.

On top of whatever the repo documents, the Standards axis always carries the smell baseline below — a fixed set of Fowler code smells (Refactoring, ch.3) that applies even when a repo documents nothing. Two rules bind it:

• The repo overrides. A documented repo standard always wins; where it endorses something the baseline would flag, suppress the smell.
• Always a judgement call. Each smell is a labelled heuristic ("possible Feature Envy"), never a hard violation — and, like any standard here, skip anything tooling already enforces.

Each smell reads what it is → how to fix; match it against the diff:

• Mysterious Name — a function, variable, or type whose name doesn't reveal what it does or holds. → rename it; if no honest name comes, the design's murky.
• Duplicated Code — the same logic shape appears in more than one hunk or file in the change. → extract the shared shape, call it from both.
• Feature Envy — a method that reaches into another object's data more than its own. → move the method onto the data it envies.
• Data Clumps — the same few fields or params keep travelling together (a type wanting to be born). → bundle them into one type, pass that.
• Primitive Obsession — a primitive or string standing in for a domain concept that deserves its own type. → give the concept its own small type.
• Repeated Switches — the same switch/if-cascade on the same type recurs across the change. → replace with polymorphism, or one map both sites share.
• Shotgun Surgery — one logical change forces scattered edits across many files in the diff. → gather what changes together into one module.
• Divergent Change — one file or module is edited for several unrelated reasons. → split so each module changes for one reason.
• Speculative Generality — abstraction, parameters, or hooks added for needs the spec doesn't have. → delete it; inline back until a real need shows.
• Message Chains — long a.b().c().d() navigation the caller shouldn't depend on. → hide the walk behind one method on the first object.
• Middle Man — a class or function that mostly just delegates onward. → cut it, call the real target direct.
• Refused Bequest — a subclass or implementer that ignores or overrides most of what it inherits. → drop the inheritance, use composition.

4. Review in parallel when warranted

For large diffs, make one parallel subagent call with independent Standards and Intent review tasks. For small diffs, review directly. If the intent source is missing, skip the Intent review.

Standards sub-agent prompt — include:

• The full diff command and commit list.
• The list of standards-source files you found in step 3, plus the smell baseline from step 3 pasted in full — the sub-agent has no other access to it.
• The brief: "Report — per file/hunk where relevant — (a) every place the diff violates a documented standard: cite the standard (file + the rule); and (b) any baseline smell you spot: name it and quote the hunk. Distinguish hard violations from judgement calls — documented-standard breaches can be hard, but baseline smells are always judgement calls, and a documented repo standard overrides the baseline. Skip anything tooling enforces. Under 400 words."

Intent sub-agent prompt — include:

• The diff command and commit list.
• The path or contents of the intent source.
• The brief: "Report: (a) requirements the intent source asked for that are missing or partial; (b) behaviour in the diff that wasn't asked for (scope creep); (c) requirements that look implemented but where the implementation looks wrong. Quote the intent source for each finding where possible. Under 400 words."

If the intent source is missing, skip the Intent sub-agent and note this in the final report.

5. Aggregate

Present the two reports under ## Standards and ## Intent headings, verbatim or lightly cleaned. Do not merge or rerank findings — the two axes are deliberately separate (see Why two axes).

End with a one-line summary: total findings per axis, and the worst issue within each axis (if any). Don't pick a single winner across axes — that's the reranking the separation exists to prevent.

Why two axes

A change can pass one axis and fail the other:

• Code that follows every standard but implements the wrong thing → Standards pass, Intent fail.
• Code that does exactly what was asked but breaks the project's conventions → Intent pass, Standards fail.

Reporting them separately stops one axis from masking the other.