By geowa4
Software development productivity commands: autonomous milestone runner, spec compliance reviewer, and quality-gate hooks
npx claudepluginhub geowa4/claude-pluginsInstall a Claude Code stop hook that runs `claude plugin validate .` before allowing Claude to stop. This prevents Claude from finishing a session with an invalid plugin manifest or malformed command files.
Install a Claude Code stop hook that runs `go build`, `go test`, and `go tool golangci-lint run` before allowing Claude to stop. This prevents Claude from finishing a session with broken builds, failing tests, or lint violations.
You are an interactive spec writer. You interview the user to understand their development needs, research the codebase and external documentation as needed, and **must** create a GitHub issue as the final output. The workflow is not complete until a GitHub issue has been created.
Remove a file completely from git history using git-filter-repo.
One-time project setup for the ralphish autonomous milestone runner.
You are a spec compliance reviewer. You verify that every requirement in the spec is fully implemented in the codebase and that `.progress.md` accurately reflects reality. Follow these steps exactly:
You are an autonomous milestone runner. Each session, you implement **one milestone** from the spec, then stop. Follow these steps exactly:
A Claude Code plugin marketplace containing productivity commands for software development.
Commands for autonomous development workflows and quality gates.
| Command | Description |
|---|---|
/create-spec | Interactive spec creator. Interviews you to understand development needs, researches codebase and external docs, then creates a GitHub issue with milestones in /ralphish-compatible format. |
/ralphish-init | One-time project setup for the ralphish workflow. Initializes git repo if needed and adds .progress.md to .gitignore. |
/ralphish | Autonomous milestone runner. Reads a spec from a GitHub issue, tracks progress in .progress.md, and implements one milestone per session with structured commits. Requires /ralphish-init first. |
/ralphish-review | Spec compliance reviewer. Verifies every requirement in a GitHub issue spec is fully implemented, updates .progress.md status, and closes the issue when complete. |
/add-stop-hook-for-go | Installs a Claude Code stop hook that runs go build, go test, and golangci-lint before allowing Claude to stop, preventing sessions from ending with broken code. |
/add-stop-hook-for-claude-plugin | Installs a Claude Code stop hook that validates plugins before allowing Claude to stop. |
For fully automated execution, use ralphish-runner.sh:
./ralphish-runner.sh
This script orchestrates the full ralphish workflow:
/ralphish-init to set up the projectgum choose/ralphish in a loop until all milestones are complete/ralphish-review to verify implementationAdd this marketplace and install the plugin:
/plugin marketplace add geowa4/claude-plugins
/plugin install software-dev@claude-plugins
.
├── software-dev/
│ ├── .claude-plugin/
│ │ └── plugin.json
│ └── commands/
│ ├── add-stop-hook-for-claude-plugin.md
│ ├── add-stop-hook-for-go.md
│ ├── create-spec.md
│ ├── git-purge-file.md
│ ├── ralphish-init.md
│ ├── ralphish-review.md
│ └── ralphish.md
├── ralphish-runner.sh
└── README.md
Spec-driven development using GitHub spec-kit methodology. Constitution-first approach with specify, plan, tasks, and implement phases.
External network access
Connects to servers outside your machine
Runs pre-commands
Contains inline bash commands via ! syntax
Bash prerequisite issue
Uses bash pre-commands but Bash not in allowed tools
Share bugs, ideas, or general feedback.
Skills-first specification-driven development framework with 7 agent skills for planning, implementation, review, and shipping. Natural language activation with intelligent agent orchestration. Includes /plan, /implement, /research commands plus managing-specifications, implementing-features, and reviewing-and-shipping skills.
Meta-prompting and spec-driven development system for Claude Code. Productivity framework for structured AI-assisted development.
Reliability hooks for Claude Code - prevents common mistakes and enforces quality standards
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.