17,650 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
Skill Claude CodeCodex
Review an architecture submission, design proposal, or pattern choice against EA standards and produce structured feedback. Activate whenever someone wants architecture feedback, a design review, or ARB preparation — including: "review this architecture", "is this a good design", "what are the issues with", "prepare…
MuhiminOsim/code-refactoring-skill
Skill Claude Code
Safe, behavior-preserving code refactoring for any language. Detects smells (Bloat, OO, Couplers, Layers), applies Fowler & MVVM/Clean Architecture patterns, and runs tests per step. Triggers: refactor, clean up, extract, rename, simplify, decompose, god class, MVVM, Clean Architecture.
KamakuraCrypto/claude-codex-review
Skill Codex
Use when Claude has written a plan and the user wants codex to verify it against the actual codebase — runs gpt-5.5 and gpt-5.4 at xhigh reasoning in parallel with full shell access, iterates until both converge. Strict prompt-level prohibition on destructive operations. Prefer /codex-review for fast, deterministic…
Skill Claude CodeCodex
Process review comments on an MR, a design doc, or a spec — validate each finding independently with parallel validator subagents, apply fixes for the ones that hold up, and produce a reply report designed to earn reviewer sign-off. The report explains exactly how each confirmed issue was fixed, and for anything not…
GabsFranke/claude-code-github-agent
Skill Claude CodeCodex
Use this skill whenever you need to explore, search, or understand code — including code reviews, PR analysis, architecture review, finding definitions or references, tracing call graphs and dependencies, assessing the impact of changes, discovering API routes or MCP tools, searching by concept, or understanding file…
sbauza/openstack-agentic-workflows
Skill Claude Code
Review Nova code changes for intent correctness, architectural consistency, versioning rules, and testing adequacy. Use when reviewing a Gerrit patch, git diff, or set of modified files in OpenStack Nova.
Skill Claude CodeCodex
Expert code review guidelines with priority levels, core review areas, language-specific checks, and structured output format. Use this when asked to review code, review a PR, or perform a code review.
Plugin Claude Code
Bundles 14 skills, 1 MCP server · 1,463 tokens together
Skills for autonomous story execution (dex orchestrator), adversarial spec review (Codex or local LMStudio), completeness & wiring review (architect-review-pr), whole-repo three-lens audit (review-codebase), pre-task blind-spot discovery (blind-spot), CLAUDE.md minimizer (claude-md-slim), spec-to-PR conductor…
Sierra-Code-Co/internal-speckit-template
Skill Claude Code
Pre-push gate for the current branch's diff. Runs review-plan-v2's deterministic analyzers (gitleaks, markdownlint, actionlint, shellcheck, ruff, structural) with --static-only, then the CodeRabbit CLI for the actual review. No API keys, nothing billed to you, and no diff leaves the machine on the first leg. The…
Plugin Claude Code
Bundles 1 skill, 1 command, 1 agent, 1 hook · 237 tokens together
math-comp / mathcomp-analysis Rocq style guide, validated cleanup patterns, a read-only review command, and a per-file style auditor subagent — rocq-mcp-aware.
Plugin Claude Code
Bundles 3 skills, 3 commands · 294 tokens together
Development toolkit: Git commit review, branch guard, worktree management, code critic, and notification hooks.
Plugin Claude Code
Bundles 20 skills · 2,536 tokens together
Repo-agnostic engineering loop engine: config-driven verification gate, sticky PR-comment delivery, and the review/sweep skill contracts. Repo specifics live in each repo's .claude/verify/config.ts, not here.
Skill Claude Code
Explain what a PR or branch actually does before you review it — the mental model, the execution path, and what to question. Use when the user needs to understand a change they didn't write, or an agent just produced a large diff or PR.
Skill Codex
Use when a verified owner-worker branch is ready to publish, or when an open pull request needs blocking lifecycle management through CI failures, review feedback, conflicts, and merge.
Skill Claude Code needs its repo
Whole-codebase code quality audit system with 9 specialized sub-skills covering security, SOLID principles, architecture, error handling, performance, test quality, code smells, design patterns, and framework best practices. Produces a scored health dashboard (0-100 per category), severity-rated findings (P0-P3) with…
gzhanlei/claude-mob-programming-skill
Skill Claude CodeCodex
A team-based coding workflow that assigns different roles to two or three agents. TDD, or test-driven development, means writing tests before the code that makes them pass.
Plugin Claude Code
Bundles 2 commands, 7 agents · 543 tokens together
Multi-reviewer Claude Code plugin: 6 frontend reviewers dispatched in parallel with isolated context.
Skill Claude CodeCodex
Use when finishing a feature, fixing a bug, before committing React code, or when the user types /doctor, asks to scan, triage, or clean up React diagnostics. Covers lint, accessibility, bundle size, architecture. Includes a regression check and a full local-triage workflow that fetches the canonical playbook.
Command Claude Code
You are an experienced .NET software engineer conducting a thorough code review. Focus exclusively on the changes being introduced (the diff), not on pre-existing code unless it's directly affected by the changes.
Agent Claude Code needs its repo
An end-to-end assistant workflow for developing NuttX device drivers, reviewing them, creating tests, or adapting AUTOSAR MCAL modules. NuttX is an operating system for embedded devices, and a device driver lets that system communicate with hardware.
Command Claude Code
name: issue description: Smart DevOps workflow that handles both new issues and existing PRs with review feedback params.
Skill Claude CodeCodex
Perform a security audit on code, checking for common vulnerabilities including injection, auth bypass, secrets leakage, and unsafe dependencies.
Skill Claude CodeCodex
Use when reviewing a pull request or code changes.
Cumulocity-IoT/cumulocity-skills
Skill Claude CodeCodex
Analyze Angular / Cumulocity Web SDK code for anti-patterns, bugs, and quality issues. Use when reviewing components, services, or modules for code quality, maintainability, performance, and correctness. Covers TypeScript best practices, Angular idioms, C8Y SDK usage patterns, and project-specific conventions.…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: