review-cycle

Plugin review-cycle from marketplace oakoss in oakoss/claude-plugins. Commands read from the repo's manifest — today.

Skills (5)

• de-slopify

  Removes AI writing artifacts from documentation and code. Use when editing LLM-generated prose, reviewing READMEs, polishing docs before publishing, or cleaning up AI-generated code. Use for emdash cleanup, formulaic phrase removal, tone calibration, over-commented code, verbose naming, and AI code

• init

  One-time setup for review-cycle. Checks for the optional Codex CLI and multi_agent config, checks that the commit gate can load, and optionally appends the comment, fix-vs-defer, and evidence policies to CLAUDE.md (global or project). Idempotent — safe to run multiple times.

• misses

  Lists the commit gate's refusals, this session's or the ones kept from earlier sessions, of a push, pull request, merge, release or comment on GitHub that the user's message, or the offer it answered, named, and drafts each as a candidate row for review-cycle's consent corpus. Use when the gate refu

• review-pr

  Review a GitHub pull request from your machine — report-only, single pass. Fetches the PR head into a disposable worktree (your checkout is never touched), runs the review cycle's reviewer fan-out in one pass (report-only reviewers included on the full tier) — Codex leg joining when the CLI is insta

• review

  Run the full automated code review cycle on uncommitted changes, before a commit. Canonicalizes the tree, fans out reviewer subagents (plus a Codex leg when the CLI is installed) scaled to the diff, applies fixes inline and loops until a pass applies none, since a commit is admitted only for content

Subagents (7)

• cleanup

  Cleanup agent for review-cycle. Applies the comment policy (clean and minimal), runs the bundled de-slopify methodology against modified files in the current diff, and corrects prose whose claims about tool behavior a run contradicts. Acts directly via Edit tool — produces a summary of changes, not

• code-reviewer

  Use this agent when you need to review code for adherence to project guidelines, style guides, and best practices. This agent should be used proactively after writing or modifying code, especially before committing changes or creating pull requests. It will check for style violations, potential issu

• maintainability-auditor

  Use this agent for an ambitious, structural code-quality audit that looks beyond the diff for ways to make the implementation dramatically simpler. It hunts for "code judo" moves (restructurings that preserve behavior while deleting whole categories of complexity), file-size sprawl, spaghetti-branch

• pr-test-analyzer

  Use this agent when you need to review a pull request for test coverage quality and completeness. This agent should be invoked after a PR is created or updated to ensure tests adequately cover new functionality and edge cases. Typical triggers include the user asking whether tests on a freshly-creat

• silent-failure-hunter

  Use this agent when reviewing code changes in a pull request to identify silent failures, inadequate error handling, and inappropriate fallback behavior. This agent should be invoked proactively after completing a logical chunk of work that involves error handling, catch blocks, fallback logic, or a

• spec-conformance-analyzer

  Use this agent to check a diff against the spec it was supposed to implement — the originating issue, task, or PRD — rather than against code-quality standards. It answers a different question than the other reviewers: not "is this code good?" but "is this the thing we were asked to build?" It repor

• type-design-analyzer

  Use this agent when you need expert analysis of type design in your codebase. Specifically use it (1) when introducing a new type to ensure it follows best practices for encapsulation and invariant expression, (2) during pull request creation to review all types being added, and (3) when refactoring

Similar plugins