By rube-de
CI-optimized code review: multi-agent parallel review with confidence scoring and atomic GitHub PR review posting via gh api
Bug detection agent for CI: analyzes PR diffs for logic errors, null/undefined handling, race conditions, off-by-one errors, and edge cases. Uses git blame for historical context.
Code quality agent for CI: identifies code duplication, unnecessary complexity, dead code, readability issues, and opportunities for simplification in PR diffs.
Comment accuracy agent for CI: verifies that code comments, docstrings, and inline documentation in PR diffs accurately reflect the actual code behavior. Identifies misleading or stale comments.
Confidence scoring agent for CI review: independently evaluates each review finding with a 0-100 confidence score. Filters false positives, pre-existing issues, and low-signal noise.
Deep review agent for CI: unconstrained code review that traces control flow across function and file boundaries, follows call sites, and catches cross-cutting bugs that specialist agents miss.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A monorepo of Claude Code plugins and agent skills.
| Plugin | Category | Install | Description |
|---|---|---|---|
| council | Code Review | Plugin or Skill | Orchestrate Gemini, Codex, Qwen, GLM-5.1, and Kimi K2.5 for consensus-driven reviews |
| cdt | Development | Plugin only | Multi-agent dev team with four modes: plan, dev, full, and auto via Agent Teams |
| project-manager | Productivity | Plugin or Skill | GitHub issue lifecycle: create, triage, and audit issues for LLM agent teams |
| plugin-dev | Development | Plugin or Skill | Scaffold plugins, validate SKILL.md frontmatter, audit hooks |
| temporal | Development | Plugin or Skill | Temporal durable execution: CLI, SDK patterns, workflow orchestration |
| doppler | DevOps | Plugin or Skill | Doppler secrets management: CLI, secrets injection, CI/CD integrations |
| oasis-dev | Development | Plugin or Skill | Oasis Network: Sapphire confidential EVM, ROFL apps, CLI, SDK patterns |
| ci-review | Code Review | Plugin or Skill | CI-optimized multi-agent code review with confidence scoring and atomic GitHub PR review posting |
| jules-review | Code Review | Plugin or Skill | Review Jules AI agent PRs using council with smart quick/full mode |
| dlc | Quality | Plugin or Skill | Dev Life Cycle quality gates: security scans, code quality, performance analysis, test coverage, and PR review compliance |
Plugin vs Skill: Plugins use the full Claude Code plugin system (hooks, agents, commands, scripts). Skills install only SKILL.md definitions via skills.sh. Plugins that rely on hooks, commands, or agent definitions need plugin install. See each plugin's README for details.
| Requirement | Check | Install |
|---|---|---|
| Claude Code CLI | claude --version | Getting Started |
Open Claude Code and type /plugin — this opens an interactive UI where you can add marketplaces, browse, install, and update plugins. Add the marketplace using the GitHub repo rube-de/cc-skills, then install the plugins you want.
claude plugin marketplace add rube-de/cc-skills
This clones the marketplace to ~/.claude/plugins/marketplaces/rube-cc-skills/.
[!TIP] After installing, restart Claude Code (fresh session) to activate the plugins. Type
/and look for/council,/cdt,/pm,/dlc, etc.
# Install individual plugins
claude plugin install council@rube-cc-skills
claude plugin install cdt@rube-cc-skills
claude plugin install project-manager@rube-cc-skills
claude plugin install plugin-dev@rube-cc-skills
claude plugin install temporal@rube-cc-skills
claude plugin install doppler@rube-cc-skills
claude plugin install oasis-dev@rube-cc-skills
claude plugin install jules-review@rube-cc-skills
claude plugin install ci-review@rube-cc-skills
claude plugin install dlc@rube-cc-skills
# Or install all at once
for p in council cdt project-manager plugin-dev temporal doppler oasis-dev ci-review jules-review dlc; do claude plugin install "$p@rube-cc-skills"; done
# Restart Claude Code to activate
claude
For cloud agents or shared teams, use --scope project instead — see Installation Scopes.
[!WARNING] We recommend installing via the plugin system instead of
npx skills. The plugin system gives you the full experience — hooks, agents, commands, and scripts.npx skillsinstalls only bare SKILL.md definitions, which means you lose preflight hooks, JSON validation, agent definitions, and command-based interfaces. Several plugins (likecdt) don't work at all as standalone skills.
If you still want standalone skill definitions (no marketplace required):
By default, npx skills installs skills at project scope (.claude/ in the current directory). Use -g for global (user-level) install, or -a claude-code to install specifically for Claude Code:
# List available skills
npx skills add rube-de/cc-skills --list
# Install specific skills (project scope by default)
npx skills add rube-de/cc-skills --skill project-manager
npx skills add rube-de/cc-skills --skill council
npx claudepluginhub rube-de/cc-skills --plugin ci-reviewGitHub issue lifecycle: brainstorm design approaches, create structured issues for LLM agent teams, triage and recommend next issues, audit and clean up stale backlogs, and deep-validate individual issues against the codebase
Oasis Network development: Sapphire confidential EVM, ROFL off-chain apps, CLI operations, SDK patterns (Rust, Go, TypeScript, Python), and ParaTime development
AI Council - Orchestrate multiple AI consultants (Gemini 3.5 Flash, Codex, Qwen, GLM-5.2, Kimi K2.5) for consensus-driven code reviews, plan validation, and architectural decisions
Review Jules AI agent pull requests using council review with smart quick/full mode selection and GitHub PR review posting
Multi-agent development workflow with five modes: plan, dev, full, auto, and bugfix. Uses Agent Teams for collaborative roles (Architect, PM, Developer, Tester, Reviewer) and a Researcher subagent for documentation lookups via Context7.
Automated code review for pull requests using multiple specialized agents with confidence-based scoring
Review Jules AI agent pull requests using council review with smart quick/full mode selection and GitHub PR review posting
Multi-agent code review for Claude Code — parallel review by Codex (GPT-5.5), Gemini 3.1 Pro, and five Claude specialist subagents (one run blind), then verified synthesis.
Review pull requests with structured analysis and approve with confidence
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems