By shdennlin
Structured spec and implementation review with iterative fix loops and parallel multi-angle review
Inject reviewer-aligned rules into openspec/config.yaml to reduce review round-trips
Review implementation against a spec using git diffs to catch mismatches, missing work, and bugs
Review a spec/proposal/design before implementation to catch gaps, risks, and ambiguities
You inject reviewer-aligned rules into a project's `openspec/config.yaml` so specs pass review on first attempt.
You are an orchestrator that runs iterative implementation review and fix cycles. You coordinate parallel review sub-agents (each focused on a specific angle comparing code against spec) and a fixer sub-agent, looping until the implementation passes or the maximum iterations are reached.
You are a senior software engineer. Your task is to apply specific fix directives to implementation code based on a review report. Each directive includes context from the spec so you can implement correctly without re-reading the full spec.
You review implementation against a spec by comparing git diffs with spec requirements to identify mismatches, gaps, and bug risks.
You are an orchestrator that runs iterative spec review and fix cycles. You coordinate parallel review sub-agents (each focused on a specific angle) and a fixer sub-agent, looping until the spec passes or the maximum iterations are reached.
Inject reviewer-aligned rules into openspec/config.yaml so generated specs pass review on first attempt. Use to reduce review round-trips after /opsx:ff or spectra-propose.
Review implementation against a spec using git diffs to catch mismatches, missing work, and bugs. Supports iterative review+fix with --fix flag and parallel multi-angle review. Use after implementing a feature to verify spec coverage.
Review a spec, proposal, or design before implementation to catch gaps, risks, and ambiguities. Scans codebase for context before review. Supports iterative review+fix with --fix flag and parallel multi-angle review. Use when you want to validate specs before coding.
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 collection of plugins for AI coding agents including Claude Code, Codex, and other agentic development tools.
| Plugin | Description | Type | Command |
|---|---|---|---|
| mermaid-validator | Validates and fixes Mermaid diagram syntax in Markdown files | Command + Agent | /mermaid-validator:check |
| git-workflow | Git workflow automation with Conventional Commits support | Command + Agent + Skill | /git-workflow:merge, /git-workflow:commit, /git-workflow:status, /git-workflow:sync |
| reviewer | Structured spec and implementation review with agent-loop handoff | Command + Agent + Skill | /reviewer:spec, /reviewer:result, /reviewer:init |
| digest | Summarize branches, PRs, diffs, and docs into icon-rich structured cards | Command + Agent + Skill | /digest:digest, /digest:release |
| ralph-loop | Continuous self-referential AI loops with session isolation | Command + Hook | /ralph-loop:ralph-loop, /ralph-loop:cancel-ralph |
# Add this marketplace to Claude Code
/plugin marketplace add shdennlin/agent-plugins
# Install a plugin
/plugin install reviewer@shdennlin-plugins
# List available plugins
/plugin list shdennlin-plugins
# Update a plugin
/plugin update reviewer@shdennlin-plugins
# Remove a plugin
/plugin uninstall reviewer@shdennlin-plugins
Tell Codex to fetch and follow the install instructions for the plugin you want:
| Plugin | Install command |
|---|---|
| reviewer | Fetch and follow instructions from https://raw.githubusercontent.com/shdennlin/agent-plugins/main/plugins/reviewer/.codex/INSTALL.md |
| git-workflow | Fetch and follow instructions from https://raw.githubusercontent.com/shdennlin/agent-plugins/main/plugins/git-workflow/.codex/INSTALL.md |
| mermaid-validator | Fetch and follow instructions from https://raw.githubusercontent.com/shdennlin/agent-plugins/main/plugins/mermaid-validator/.codex/INSTALL.md |
| digest | Fetch and follow instructions from https://raw.githubusercontent.com/shdennlin/agent-plugins/main/plugins/digest/.codex/INSTALL.md |
| ralph-loop | Fetch and follow instructions from https://raw.githubusercontent.com/shdennlin/agent-plugins/main/plugins/ralph-loop/.codex/INSTALL.md |
Restart Codex after installation to discover the skills.
Update: cd ~/.codex/shdennlin-agent-plugins && git pull — skills update instantly through the symlink.
Contributions are welcome! Please see CONTRIBUTING.md for guidelines.
plugins/plugins/your-plugin/
├── .claude-plugin/
│ └── plugin.json
├── .codex/
│ └── INSTALL.md # (optional) - Codex installation guide
├── commands/ # (optional) - slash commands
├── agents/ # (optional) - proactive agents
├── hooks/ # (optional) - event hooks
├── skills/ # (optional) - auto-discovery skills
└── README.md
.claude-plugin/marketplace.jsonMIT License - see LICENSE for details.
shdennlin - GitHub
Git workflow automation commands with Conventional Commits support
Summarize AI-generated branches, PRs, diffs, and design docs into icon-rich structured cards with full report mode
Continuous self-referential AI loops for interactive iterative development with session isolation. Forked from Anthropic's ralph-loop with cross-session bug fix.
Validates and fixes Mermaid diagram syntax in Markdown files with skill and agent
npx claudepluginhub shdennlin/agent-plugins --plugin reviewerCode review plugin with a standalone reviewer agent and two skill strategies: disposable subagents for one-shot reviews and persistent team members for iterative reviews
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Ultra-compressed communication mode. Cuts 65% of output tokens (measured) while keeping full technical accuracy by speaking like a caveman.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Unified capability management center for Skills, Agents, and Commands.