By shawn-sandy
Stress-test implementation plans with structured multi-round interviews before coding begins
Walk each decision branch in an implementation plan with focused questions and codebase exploration
Scan plan directories for randomly-named files and rename them to descriptive kebab-case names based on content headings
Stress-test a plan through a structured conversational interview before implementation begins.
Check and update the lifecycle status of a plan file (todo, in-progress, completed) with type classification (standard, artifact)
Review plan files and rename any whose filename doesn't match the plan's intent.
Use when the user asks to deep grill a plan, walk through each decision branch, examine design-tree branches, or stress-test individual decisions in an implementation plan.
Use when the user asks to stress-test, validate, critique, or find gaps and risks in an implementation plan. Does not execute the plan or apply fixes.
Use when the user asks to check, update, or determine the status of a plan file, when entering or exiting plan mode, when creating or updating plans, or when working with plan files in any capacity — not for stress-testing, validating, or critiquing plan content.
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 marketplace system for Claude Code plugins, enabling discovery, distribution, and installation of plugins that extend Claude's capabilities.
Install from GitHub (recommended):
# Register the agentics-kit marketplace
/plugin marketplace add shawn-sandy/agentics
# Install any plugin by name
/plugin install code-review@agentics-kit
/plugin install git-agent@agentics-kit
Or load a plugin directly for local testing:
git clone https://github.com/shawn-sandy/agentics.git
cd agentics
claude --plugin-dir ./kit/plugins/code-review
# Then ask: "Review this code for issues"
The agentics project provides:
agentics-kit marketplace for testing plugin discovery and installation# Verify installation
claude --version
gh) — For the git-agent plugin's PR creationagentics/
├── kit/
│ ├── .claude-plugin/
│ │ └── marketplace.json # Marketplace manifest (agentics-kit)
│ └── plugins/ # Example plugins
│ ├── code-review/ # Code review skill
│ ├── plan-interview/ # Plan stress-test (command + skill)
│ ├── claude-md-optimizer/ # CLAUDE.md audit and optimization
│ ├── wcag-compliance-reviewer/ # WCAG 2.2 accessibility compliance
│ ├── skill-reviewer/ # Skill authoring review and testing
│ ├── code-testing-agent/ # Test suggestion and review
│ ├── git-agent/ # Automated git commit and PR creation
│ ├── agent-creator/ # Agent-based plugin scaffolding
│ ├── react-perf-analyzer/ # React performance analysis
│ ├── marketplace-builder/ # Marketplace scaffolding
│ └── agentic-plugin-dev/ # Plugin creation and management
├── tests/
│ └── fixtures/ # Test plugin fixtures
└── README.md # This file
Clone the repository:
git clone https://github.com/shawn-sandy/agentics.git
cd agentics
Load a plugin directly:
# Test with code-review plugin
claude --plugin-dir ./kit/plugins/code-review
# This starts an interactive Claude Code session.
# Once Claude responds, ask naturally:
# "Review this code for issues"
Verify the plugin loaded:
# In the Claude interactive session, list available commands:
/help
Note: You can test plugins immediately without installing any dependencies. The --plugin-dir flag loads plugins directly from your local filesystem and starts an interactive session.
The Claude Code CLI is not installed or not in your PATH.
Solution:
claude --version~/.local/bin or the installation directory is in your PATHThe plugin directory may not exist or the path is incorrect.
Solution:
ls -la ./kit/plugins/code-reviewclaude --plugin-dir /full/path/to/agentics/kit/plugins/code-review
.claude-plugin/plugin.json exists in the plugin directoryThe plugin directory or files may not be readable.
Solution:
ls -la ./kit/plugins/code-reviewchmod -R +r ./kit/plugins/code-reviewchown -R $USER:$USER ./kit/plugins/You see an error like: Error: Input must be provided either through stdin or as a prompt argument when using --print
npx claudepluginhub shawn-sandy/agentics --plugin plan-interviewReview and plan Claude Code skills, and run tests for changed files — audit SKILL.md files, scaffold new skills, and verify test coverage
Automated git commit and PR creation — stage, commit with conventional messages, and create PRs in one shot
Analyze code and suggest specific, purpose-driven tests tied to actual behavior and intent — not arbitrary coverage
Systematic code review across quality, bugs, security, and best practices
Review HTML/CSS and React/TypeScript code for WCAG 2.2 Level AA accessibility compliance
Interview-driven planning and clarification using AskUserQuestion
Adversarial plan review using red-team/blue-team agents -- generates what-if questions and grounds answers in plan artifacts with configurable tool scope
Refine project plans through in-depth Socratic questioning. Interview about technical implementation, UI/UX, concerns, and tradeoffs to produce comprehensive specs.
AI-assisted deep planning with research, interview, external LLM review, and TDD approach
Autonomous Claude + Codex review loop. Plan a feature with adversarial pushback, or audit code, all in one window.
Codex, Gemini, Claude の3つの AI で Plan ファイルを並列レビュー。実装計画の妥当性、抜け漏れ、リスクを分析する