By pipemind-com
Agentic workflow factory — compile project-specific planners, builders, and specialist agents for any codebase.
npx claudepluginhub pipemind-com/pipemind-marketplace --plugin spec-driven-developmentCompiles the full agentic workflow for a project: CLAUDE.md, docs/, planner, and builder agents. Idempotent — safe to re-run.
Creates lean project-specific builder agent (50-100 lines). Use when setting up implementation agents for a project's agentic workflow.
Creates lean DevOps agent for infrastructure (50-80 lines). Use when adding an infrastructure/CI-CD specialist to a project's agent workflow.
Creates lean project-specific planner agent (50-100 lines). Use when setting up task planning for a project's agentic workflow.
Generates docs/ for progressive disclosure from CLAUDE.md. Use after /compiling-project-settings to create detailed reference documentation that agents load on demand.
Generates lean CLAUDE.md (~50-100 lines) with progressive disclosure. Use when setting up a new project or when CLAUDE.md is missing or bloated.
Creates lean security auditor agent (50-100 lines). Use when adding adversarial red-team security review to a project's agent workflow.
---
Generates behavioral specs from source documents via iterative refinement — writes first, asks questions after. Splits large inputs into epics. Use when asked to 'write a spec,' 'spec this out,' 'create behavioral requirements,' or 'define specs.' Not for test scenarios — use /defining-test-scenarios for that.
Expands behavioral spec features into exhaustive test scenarios. Use after /defining-specs to bridge specs and downstream test-writing agents.
Splits all git changes into atomic commits of related changes. Use when you have uncommitted work ready to commit.
Decomposes features into parallel sub-tasks, plans each via planner agents, builds via parallel builder agents. Use for multi-part features requiring coordinated implementation.
Structured code quality review across 6 axes. Use to review code for purity, testability, abstraction, readability, docs, and robustness.
Generates adversarial property-based tests to prove code is broken. Use after implementing a function to find edge cases and boundary failures.
A marketplace of Claude Code plugins. Install plugins once globally (~/.claude/), then use them across all your projects.
| Plugin | Description | Docs |
|---|---|---|
| spec-driven-development | Self-replicating agentic workflow factory — compiles project-specific agents for any codebase | README |
# Marketplace
claude plugin marketplace add pipemind-com/pipemind-marketplace
# Plugins
claude plugin install spec-driven-development@pipemind-marketplace
claude plugin install scientific-method@pipemind-marketplace
claude plugin install rust-lsp@pipemind-marketplace
claude plugin install typescript-lsp@pipemind-marketplace
For issues with Claude Code itself: https://github.com/anthropics/claude-code
Team-oriented workflow plugin with role agents, 27 specialist agents, ECC-inspired commands, layered rules, and hooks skeleton.
Uses power tools
Uses Bash, Write, or Edit tools
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
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.
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, rules, and legacy command shims evolved over 10+ months of intensive daily use