By aaronbassett
Guide users through creating complete, unambiguous feature specifications using a discovery-driven process.
Build. Ship. Repeat. A collection of Claude Code plugins for devs.
| Plugin | Description |
|---|---|
| constitution | Create, validate, and enforce project constitutions with living governance |
| dev-specialisms | Niche developer skills (deployment, frontend vibes, Hashbrown) |
| devs | Specialist coding agents and skills for Python, Rust, TypeScript, React, and security |
| flutter-core | Flutter and Dart development toolkit covering UI/UX, state management, testing, and ServerPod |
| git-lovely | Lovely Git workflows with conventional commits and GitHub CLI integration |
| ideas | Turn vague ideas into sharp vision documents through structured creative collaboration |
| image-gen | AI-powered image generation using Google Gemini models via nanobanana MCP server |
| pr-tools | Parallel PR review agents for code quality, SDD task verification, and TODO tracking |
| readme-and-co | Generate README, LICENSE, CONTRIBUTING, SECURITY, and GitHub templates |
| sandbox | Isolated Docker-based development environments for Claude Code |
| sdd | Specification-Driven Development: specs, plans, tasks, codebase mapping, and quality gates |
| settings-presets | Powerline status line and attribution configuration presets |
| spec-writer | Guided discovery process for writing complete feature specifications |
| utils | Plugin management utilities: dependency checking, scanning, and root resolution |
| worktrees | Git worktree workflows for parallel AI development |
Add the marketplace, then install individual plugins:
claude mcp add-marketplace aaronbassett/agent-foundry
claude plugin install sdd@agent-foundry
Or install a plugin directly from the repo:
claude install-plugin https://github.com/aaronbassett/agent-foundry/tree/main/plugins/sdd
This repository uses lefthook for git hooks.
lefthook --versionlefthook installAutomatic validation:
Manual validation:
scripts/validate-marketplace.shscripts/validate-plugin.sh <plugin-name>scripts/ci/validate.shBypassing hooks:
Use git commit --no-verify or git push --no-verify when:
Note: GitHub Actions will still validate all changes.
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.
npx claudepluginhub aaronbassett/agent-foundry --plugin spec-writerExplore, develop, and refine ideas through creative collaboration — from open-ended riffing to structured ideation to ruthless refinement — before any design or implementation work begins.
AI-powered image generation using Google Gemini models via the nanobanana MCP server. Generate, edit, and manage images with intelligent model selection, aspect ratio control, and multi-model support.
Create isolated Docker-based development environments for running Claude Code safely
Configuration toolkit for streamlining Claude Code project setup with powerline status line and attribution settings
Comprehensive PR review plugin that launches specialist agents in parallel to perform deep code reviews, detect issues, verify SDD tasks, and post consolidated findings as PR comments. Includes brainstorming workflow for addressing review findings.
Spec Driven Development toolkit - structured specification, planning, and implementation workflows for systematic feature development
Spec-driven development using GitHub spec-kit methodology. Constitution-first approach with specify, plan, tasks, and implement phases.
GitHub Spec-Kit integration for constitution-based spec-driven development (7-phase workflow)
Specification-Driven Development with Process Discipline for Claude Code
Spec-driven development methodology for Claude Code. Provides skills for requirements engineering (EARS format), design documentation, task breakdown, AI prompting strategies, quality assurance, and troubleshooting.
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.