claude

review

Review skills: second-opinion reviews from another model, review-fix loops, anti-slop cleanup, and poka-yoke error-proofing.

0 on GitHubby Buck Bradyv0.1.0updated today

Not in a marketplace yet, so it loads for one session with --plugin-dir.

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

What it installs

Skills (4)

  • anti-slop

    Review or revise code, docs, or an implemented UI to strip unsupported complexity, speculative additions, dead artifacts, and generic filler while keeping intentional constraints. Use for "this feels bloated/generic", "cut this down", "de-slop this", or a review that should end smaller and evidence-

  • poka-yoke

    Design or audit code so a mistake cannot be expressed, rather than documenting it. Ranks every hazard on a ladder (control, warning, detection, and docs-only), applies contact, fixed-value, and motion-step lenses, and states what the new design makes impossible. After an incident it separates the de

  • review-loop

    Run a review, fix, re-review loop on a diff until a reviewer approves, with findings kept in one file so each round checks only what was flagged. Use when a finished change needs review plus fixes ("review and fix until clean", "loop review on this branch"), or when a reviewer's findings must be fix

  • second-opinion

    Get a read-only second opinion on a diff or a plan from a different model family (codex/GPT or agy/Gemini), picking the reviewer, model, and effort and splitting big reviews into focused passes, or run a local two-reviewer gate with Agent subagents when no code may leave the machine. Use when review

View source on GitHub

More from Adminhead/claude-plugins

All 308 plugins →

crew

claude

The orchestrated-session crew: 14 subagents (coders, reviewers, debuggers, architect, devops, dba, scribe, browser tester) plus the orchestration main-thread agent, with a read-only Bash gate for the read-only agents, orchestration nudge hooks, and the orchestration system-prompt file. Agents are spawned as crew:<name>.

15 agents · hooks

0

authoring

claude

Skills for authoring Claude Code skills, agent instruction files, architecture decision records, and docs; mapping codebases and domain models; planning agent teams; and auditing documentation and reviewing Claude Code config for bloat and security.

9 skills

0

github

claude

GitHub workflow skills: issues, issue breakdown, triage, pull requests and review comments, shipping commits through merge, and releases, plus the GitHub remote MCP server.

7 skills · 1 agent · 1 MCP server

0

api

claude

Public API design skills: REST contracts, idempotency and retries, webhooks, versioning, gRPC, GraphQL, API keys, and OAuth providers.

8 skills

0

Code search: ripgrep, CodeGraph's local symbol graph with auto-indexing, Context7 library docs, public GitHub code via grep.app, and always-on search guidelines.

4 skills · 3 MCP servers

0

coding-js

claude

JavaScript and TypeScript skills: the languages, React, Vue, Vite, TanStack, and click-path audits of UI flows.

7 skills

0

Maintain review?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins308 plugins