review-code

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?
• Spec — does the code faithfully implement the originating spec / PRD?

The two axes are reviewed in isolation so they don't pollute each other, then aggregated side by side.

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 the two reviews.

2. Identify the spec source

Look for the originating spec, in this order:

1. A path the user passed as an argument.
2. A spec under .plan/ — typically .plan/<slug>/spec.md, matching the branch name or feature.
3. A PRD/spec file elsewhere in the repo (docs/, specs/, or similar) matching the branch name or feature.
4. Issue references in the commit messages (#123, Closes #45, etc.) — if the environment has a way to fetch them (e.g. the repo host's CLI), fetch the referenced issue.
5. If nothing is found, ask the user where the spec is. If they say there isn't one, the Spec axis will skip and report "no spec available".

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. Three rules bind it:

• The repo overrides. A documented repo standard always wins; where it endorses something the baseline would flag, suppress the smell.
• The language's paradigm applies. Skip smells that don't fit the language being reviewed — e.g. Refused Bequest in a language without inheritance, Feature Envy where there are no objects to envy.
• 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/pattern-match on the same type recurs across the change. → replace with polymorphism, a dispatch table, or one match site both callers 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. Run both reviews in isolation

If your environment supports spawning subagents, send a single message with two subagent calls (use a general-purpose subagent for both) so the axes run in parallel with isolated context.

Otherwise, run the two axes as sequential, self-contained passes in this session: complete the Standards pass in full and write its findings down before starting the Spec pass, then re-read the diff fresh with only the spec in mind. Don't let one pass's findings leak into the other's brief.

Either way, each axis gets exactly the brief below and nothing else.

Standards brief — 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 — a subagent has no other access to it.
• The instruction: "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, and skip smells that don't apply to the language's paradigm. Under 400 words."

Spec brief — include:

• The diff command and commit list.
• The path or fetched contents of the spec.
• The instruction: "Report: (a) requirements the spec 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 spec line for each finding. Under 400 words."

If the spec is missing, skip the Spec axis and note this in the final report.

5. Aggregate

Present the two reports under ## Standards and ## Spec 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, Spec fail.
• Code that does exactly what the issue asked but breaks the project's conventions → Spec pass, Standards fail.

Reporting them separately stops one axis from masking the other.