By numanumanuma
Set up agent-legible documentation for any codebase: slim CLAUDE.md, hierarchical docs, subdirectory rules, lint-as-taste, and doc gardening
Custom Claude Code plugins for agent-first development workflows.
# Register the marketplace (one-time)
/plugin marketplace add NumaNumaNuma/claude-plugins
# Install plugins
/plugin install dream-team@numa-plugins
/plugin install lean-docs@numa-plugins
/plugin install the-rat@numa-plugins
dream-team requires the experimental agent teams feature. Add to ~/.claude/settings.json:
{
"env": {
"CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1"
}
}
Multi-agent collaborative workflow for planning, implementing, and reviewing features.
/dream-plan — Launch specialist agents to collaboratively design an implementation plan/dream-implement — Architect scan, implement step-by-step, post-implementation review/dream-review — Multi-agent code review with severity classification/sprint-runner — Autonomous sprint execution with checkpoint-based progress trackingscripts/run-task.sh — Headless runner for overnight/unattended sprintsUses official feature-dev and pr-review-toolkit agents when available, falls back to general-purpose with specialist prompts.
Set up and maintain agent-legible documentation for any codebase.
/lean-docs — Guided 9-step setup for a new project/lean-docs audit — Check existing docs against the playbookdocs/, subdirectory CLAUDE.md files, link-don't-duplicateDeliver the pizza first, dress up later. The Rat is a coding philosophy for startups that prioritizes shipping over polish.
/ratify — Run the Ratman agent on any plan to check if it's lean enough to ship/rat-retrospective — Score shipped features retroactively: was the costume worth it?For best dream-team results, also install:
code-architect, code-reviewer, code-explorer agentssilent-failure-hunter, type-design-analyzer, pr-test-analyzer agentsOwn 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 numanumanuma/claude-plugins --plugin lean-docsMulti-agent collaborative workflow for planning, implementing, and reviewing features with autonomous sprint execution
The Rat coding philosophy — deliver the pizza first, dress up later. MVP-on-steroids approach to shipping features fast.
Make your AI agent code with your project's architecture, rules, and decisions.
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.
Build and maintain an LLM-curated personal knowledge base in your project — Andrej Karpathy's LLM Wiki pattern, designed to scale to thousands of pages without becoming a context bottleneck. Now with an optional compiled graph layer for typed, provenance-backed relationships.
AI-powered wiki generator for code repositories. Generates comprehensive, Mermaid-rich documentation with dark-mode VitePress sites, onboarding guides, deep research, and source citations. Inspired by OpenDeepWiki and deepwiki-open.
Claude + Obsidian knowledge companion. Sets up a persistent, compounding wiki vault (Karpathy's LLM Wiki pattern). v1.7 "Compound Vault" + v1.8 methodology modes close 5 of 5 priority gaps from the May 2026 compass artifact. Ships: substrate alignment with kepano/obsidian-skills, default Obsidian CLI transport, hybrid retrieval (contextual prefix + BM25 + cosine rerank per Anthropic's Sept 2024 research), per-file advisory locking for multi-writer safety, pre-commit verifier agent, AND methodology modes (LYT / PARA / Zettelkasten / Generic) for first-class organizational support no other Claude+Obsidian competitor offers. v1.7.x audit closure: every BLOCKER + HIGH + MEDIUM + LOW finding from the v1.7.0 audit is CLOSED or DEFERRED-with-rationale. Optional DragonScale Memory extension (log folds, deterministic addresses, semantic tiling lint, boundary-first autoresearch).
Complete AI coding workflow system. Self-correcting memory + persistent FTS5-indexed research wikis + auto-research loop + multi-LLM council on a single SQLite store. 33 skills, 8 agents, 22 commands, 37 hook scripts across 24 events. Cross-agent via SkillKit.