From f1b525cec98f44b4b9f831b05b585fe75d73180c Mon Sep 17 00:00:00 2001 From: JB Date: Fri, 4 Sep 2026 10:14:40 -0400 Subject: [PATCH] feat(skills): enforce independent workflow review --- skills/design/implement/SKILL.md | 12 ++-- skills/develop/code-review/SKILL.md | 108 ++++++++++++++-------------- 2 files changed, 57 insertions(+), 63 deletions(-) diff --git a/skills/design/implement/SKILL.md b/skills/design/implement/SKILL.md index 7a0b11f..5145cae 100644 --- a/skills/design/implement/SKILL.md +++ b/skills/design/implement/SKILL.md @@ -1,15 +1,13 @@ --- name: implement -description: "Implement a piece of work based on a spec or set of tickets." +description: "Implement one bounded assignment from an approved plan." disable-model-invocation: true --- -Implement the work described by the user in the spec or tickets. +# Implement -Use /tdd where possible, at pre-agreed seams. +For feature work and other multi-step changes, invoke `develop-workflow`; let its parent orchestrator own approval gates, assignments, commits, independent review, and integration. -Run typechecking regularly, single test files regularly, and the full test suite once at the end. +For one bounded assignment, require the approved plan, acceptance criteria, exclusive owned paths, test seam, allowed commands, and deadline. Use `tdd` where practical. Change only owned paths, run focused checks, and return the diff and command evidence to the parent. -Once done, use /code-review to review the work. - -Commit your work to the current branch. +Leave user interaction, mutation delegation, commits, remediation decisions, review, and integration to the parent orchestrator. diff --git a/skills/develop/code-review/SKILL.md b/skills/develop/code-review/SKILL.md index e40f7fd..cc0d67a 100644 --- a/skills/develop/code-review/SKILL.md +++ b/skills/develop/code-review/SKILL.md @@ -1,87 +1,83 @@ --- 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 Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents 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\"." +description: Review changes since a fixed commit, branch, tag, or merge-base along separate repository-standards and specification axes. Use for branch, PR, work-in-progress, or workflow-record review after implementation and verification. --- -Two-axis review of the diff between `HEAD` and a fixed point the user supplies: +# Code review -- **Standards**: does the code conform to this repo's documented coding standards? -- **Spec**: does the code faithfully implement the originating issue / spec? +Run two independent, read-only reviews over one pinned diff: -Both axes run as **parallel sub-agents** so they don't pollute each other's context, then this skill aggregates their findings. +- **Standards:** repository instructions and documented conventions. +- **Specification:** the originating issue, spec, or approved workflow record. -The issue tracker should have been provided to you. If `docs/agents/issue-tracker.md` is missing, tell the user to run `/configure-skills`. +Keep the axes separate so conformity cannot hide incorrect scope and correct scope cannot hide standards violations. -## Process +## 1. Pin the review bytes -### 1. Pin the fixed point +Require a fixed point; ask when none was supplied. Resolve and record: -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. +- review base commit; +- immutable product HEAD commit, never mutable `HEAD` in the reviewer brief; +- clean status and product tree hash; +- `git log .. --oneline`; +- exact command `git diff --binary --full-index --find-renames ... --`. -Capture the diff command once: `git diff ...HEAD` (three-dot, so the comparison is against the merge-base). Also note the list of commits via `git log ..HEAD --oneline`. +Run that command once in the parent, hash its exact bytes with SHA-256, and record the digest. Stop on a bad ref, dirty product state, or empty diff unless an empty comparison was explicitly expected. -Before going further, confirm the fixed point resolves (`git rev-parse `) and the diff is non-empty. A bad ref or empty diff should fail here, not inside two parallel sub-agents. +## 2. Resolve specification and standards -### 2. Identify the spec source +Accept the first available specification source: -Look for the originating spec, in this order: +1. a caller-supplied approved workflow record or spec path; +2. issue references in commits, using `docs/agents/issue-tracker.md` when configured; +3. a matching file under `docs/`, `specs/`, or `.scratch/`; +4. an explicit user statement that no specification exists. -1. Issue references in the commit messages (`#123`, `Closes #45`, GitLab `!67`, etc.), fetched via the workflow in `docs/agents/issue-tracker.md`. -2. A path the user passed as an argument. -3. A spec file under `docs/`, `specs/`, or `.scratch/` matching the branch name or feature. -4. 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". +A workflow record is a complete specification source and never requires issue-tracker configuration. Ask only when no source or explicit no-spec decision exists. Skip the specification reviewer and report “no specification available” only after that explicit decision. -### 3. Identify the standards sources +Collect applicable `AGENTS.md`, `CLAUDE.md`, contributing, coding-standard, and ADR sources. Add this smell baseline where repository standards do not override it; treat each as a judgment call and skip tooling-enforced issues: -Anything in the repo that documents how code should be written, such as `CODING_STANDARDS.md` or `CONTRIBUTING.md`. +- **Mysterious Name:** a name hides purpose. +- **Duplicated Code:** the same logic shape recurs. +- **Feature Envy:** behavior reaches into another object's data more than its own. +- **Data Clumps:** fields or parameters repeatedly travel together. +- **Primitive Obsession:** primitives stand in for a domain concept. +- **Repeated Switches:** the same type cascade recurs. +- **Shotgun Surgery:** one change requires scattered edits. +- **Divergent Change:** one module changes for unrelated reasons. +- **Speculative Generality:** abstraction exists without a current requirement. +- **Message Chains:** callers navigate long object chains. +- **Middle Man:** code delegates without adding value. +- **Refused Bequest:** an implementation ignores most inherited behavior. -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: +## 3. Enforce reviewer independence -- **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. +List every display name, profile, child/session ID, and ambiguous run that authored or mutated the diff. Select two different reviewer identities outside that set. Require repository read access plus Git-capable `bash`, with no declared `write`, `edit`, or nested-agent capability. -Each smell reads *what it is* → *how to fix*; match it against the diff: +Capture branch, HEAD, status, tree hash, and changed paths before review. Launch the standards and specification reviewers as separate direct subagent calls rather than a wrapped parallel call. Give both the pinned commits, exact diff command, expected digest, commit list, mutator exclusions, and identity-reporting requirement. -- **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. +Require each reviewer to: -### 4. Spawn both sub-agents in parallel +1. regenerate the exact diff and confirm its SHA-256 before analysis; +2. remain read-only and perform no remediation; +3. bind every finding to file/hunk evidence and severity; +4. report display/profile/child/session identity when exposed; +5. stay under 400 words. -**Standards sub-agent prompt** should include: +For standards, include every standards source and the full baseline above. Ask for documented violations separately from baseline judgments. For specification, include the approved source and ask for missing/partial requirements, scope creep, and apparently implemented but incorrect behavior with quoted requirements. -- 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." +Treat missing delivery, digest mismatch, reviewer/mutator identity overlap, or before/after repository mutation as no verdict. Any reviewer mutation also makes that identity a mutator. -**Spec sub-agent prompt** should include: +## 4. Aggregate without reranking -- The diff command and commit list. -- 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 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." +Present the reports under `## Standards` and `## Specification`. Lightly clean formatting only; keep findings and axis severity separate. End with finding counts and the worst issue within each axis, not one combined winner. -If the spec is missing, skip the Spec sub-agent and note this in the final report. +Bind approval to the base, product HEAD, clean status, tree hash, and diff digest. -### 5. Aggregate +## 5. Remediate through non-reviewers -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_). +Validate findings against repository evidence. Assign accepted fixes to an original implementer or another non-reviewer. Rerun affected checks and the full required suite, create a new pinned fingerprint, and launch two fresh independent reviewers. -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. +Escalate after two unsuccessful remediation cycles or when a finding materially changes scope, acceptance criteria, ownership, verification, or architecture. Return material changes to plan approval before production mutation. -## 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 approve the exact verified fingerprint and before/after evidence proves reviewers stayed read-only.