code-review

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 issue / spec?

Both axes run as parallel sub-agents so they don't pollute each other's context, then this skill aggregates their findings.

Read configured tracker and project artifacts when the spec requires them; a local spec or the accepted task brief does not require tracker setup. If the spec requires a tracker that was not provided, tell the user to run /setup-matt-pocock-skills. Invoke /swarm for host-native independent review and disclosed fallback.

Process

1. Pin the fixed point

Whatever the user said is the fixed point (a commit SHA, branch name, tag, main, HEAD~5, etc.). Reuse a fixed point already supplied by the invoking workflow. If none is established, propose the repository's actual merge-base; ask only when the intended scope is ambiguous.

Resolve the base and reviewed head to immutable SHAs. For a committed branch use their merge-base diff. For requested working changes include staged, unstaged, and relevant untracked files in a captured snapshot, and record their hashes. Both axes review the same artifact. Also record the commit list for a committed scope.

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.

Invoke /principles in review mode against this exact artifact. Carry selected owners into the Standards rubric and their accepted design decisions into the Spec brief. Review applicability and concrete evidence; loading a principle is not a pass, and the review does not authorize edits.

2. Identify the spec source

Look for the originating spec, in this order:

Issue references in the commit messages (#123, Closes #45, GitLab !67, etc.), fetched via the workflow in the tracker doc.
A path the user passed as an argument.
A spec file under docs/, specs/, or .scratch/ matching the branch name or feature.
Use the accepted request or caller-supplied brief when it is the spec. If no acceptance source exists, disclose "no spec available" and ask only if that missing source prevents the requested assessment.

3. Identify the standards sources

Search the repo for every file that documents how code should be written. When CODING_STANDARDS.md or CONTRIBUTING.md exists, it must be on the list.

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. 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. Spawn both sub-agents in parallel

Use /swarm to issue the two independent briefs within host capacity and collect terminal results. Include resolved rubrics and artifact paths in each brief. If the caller supplies a Pstack adversarial lens, assign it explicitly without replacing either axis; reuse a completed equivalent pass only for the same artifact and scope. Disclose native or sequential fallback.

Standards sub-agent prompt should 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 selected principle owners' resolved instructions and applicable constraints. Apply documented repository exceptions and distinguish an actionable rule violation from an optional design preference.
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."

Spec sub-agent prompt should include:

The diff command and commit list.
The path or fetched contents of the spec.
Accepted principle-driven design decisions and their required proof, supplied by the caller or the current canonical artifacts.
The brief: "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 sub-agent 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, because 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.

Complete when both axes are accounted for against the same artifact, each finding has evidence, and unavailable coverage is explicitly reported. If the invoking workflow changes that artifact after review, refresh the affected axes against its final hashes; preserve unaffected evidence only when its scope remains valid. A review request does not authorize edits or public comments.