kehwar Two-axis review of the current code state in the checkout:
- Standards — does the code conform to this repo's documented coding standards?
- Spec — does the code faithfully implement the originating issue / PRD / spec?
Both axes run as parallel sub-agents so they don't pollute each other's context, then this skill aggregates their findings.
The issue tracker should have been provided to you — use the /issue-tracker skill if it's missing.
Process
1. Establish the review subject
Use the spec and the user's description to identify the feature or area under review. The review subject is the current code state.
Read the relevant implementation, tests, configuration, and documentation in the current checkout, including code that was not recently changed.
Before going further, confirm that you can name the implementation paths and behaviour covered by the review. If the feature or code area cannot be identified, ask the user for its scope.
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.) — fetch via the workflow in /issue-tracker. - A path the user passed as an argument.
- A PRD/spec file under
docs/,specs/, or.scratch/matching the branch name or feature. - If nothing is found, ask the user where the spec is. If they say there isn't one, the Spec sub-agent 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. 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 relevant current code:
- 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 relevant file or code path. → 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 relevant code. → replace with polymorphism, or one map both sites share. - Shotgun Surgery — one logical behaviour is scattered across many files or modules. → gather what changes together into one module.
- Divergent Change — one file or module is responsible for several unrelated reasons to change. → 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
Send a single message with two Agent tool calls. Use the general-purpose subagent for both.
Standards sub-agent prompt — include:
- The review subject and current implementation paths.
- 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/location where relevant — (a) every place the current code violates a documented standard: cite the standard (file + the rule); and (b) any baseline smell you spot: name it and quote the relevant code. 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 — include:
- The review subject and current implementation paths.
- The path or fetched contents of the spec.
- The brief: "Report: (a) requirements the spec asked for that are missing or partial; (b) behaviour in the current implementation that wasn't asked for (scope creep); (c) requirements that look implemented but where the implementation looks wrong. Quote the spec line and cite the relevant code location 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 — 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 current implementation 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 spec asks but breaks the project's conventions → Spec pass, Standards fail.
Reporting them separately stops one axis from masking the other.