By rbergman
Workflow tools: spec refinement, compression, peer review, competitive generation, and subagent delegation
Generate a second-opinion brief for an external agent with no prior context
Review and align steering files (CLAUDE.md, AGENTS.md) with Claude Opus 4.6 prompting best practices
Decompose an epic or external specification into implementable task beads with complexity-based labeling.
Spawn N agents on the same spec in isolated worktrees, compare by objective metrics, pick winner
Compress a document or artifact for agent-optimized token density while preserving effectiveness
Use when the user wants to explore approaches or discuss design before implementation. Explores intent, requirements, and design through collaborative dialogue.
QA web applications using Chrome DevTools MCP. Use when testing running apps, verifying acceptance criteria against a live UI, checking for console errors, evaluating UI behavior, or running regression checks. Requires the chrome-devtools MCP server to be connected. Complements dm-work:review (code-level) with runtime verification.
Power CLI tools (fd, rg, jq, yq, sd, xargs, bat, delta) for when built-in tools are insufficient. Use for complex file ops, data manipulation, or parallel execution.
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes. Requires root cause investigation before any fix attempts. Random fixes waste time and create new bugs.
Transform ambiguous specs into implementable work items through adversarial refinement. Use when receiving specs, claiming epics, or starting complex (l/xl) tasks. Use /breakdown for spec→tasks decomposition, /refine for sharpening individual items.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
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 personal Claude Code plugin marketplace for workflows, skills, and agents that I use daily.
This is my personal repo. It reflects my workflows, preferences, and experiments. YMMV.
If something here is useful to you, great. If not, no worries.
# Add the marketplace
claude plugin marketplace add rbergman/dark-matter-marketplace
# Install plugins
claude plugin install dm-work@dark-matter-marketplace
claude plugin install dm-lang@dark-matter-marketplace
# ... or any other dm-* plugin
# Update after changes
claude plugin marketplace update dark-matter-marketplace
All components use the dm-* plugin prefix with semantic groupings:
| Plugin | Prefix | Example |
|---|---|---|
| dm-arch | Architecture patterns | dm-arch:solid-architecture |
| dm-team | Agent Teams patterns | dm-team:lead |
| dm-game | Game development | dm-game:game-design |
| dm-lang | Language expertise | dm-lang:typescript-pro |
| dm-tool | Tool design patterns | dm-tool:agent-dx-cli |
| dm-work | Workflow tools | dm-work:orchestrator |
Commands use /dm-work:command format (e.g., /dm-work:rotate).
dark-matter-marketplace/
├── plugins/ # Installable Claude Code plugins
│ ├── architecture/ # dm-arch: SOLID, data-oriented patterns
│ ├── game-dev/ # dm-game: design methodology, perf optimization
│ ├── language-pro/ # dm-lang: Go, Rust, TypeScript, Python, just
│ ├── teams/ # dm-team: Agent Teams orchestration and collaboration
│ ├── tooling/ # dm-tool: CLI/MCP/API design for agents
│ └── workflow/ # dm-work: orchestration, specs, subagents
├── references/ # Non-installable reference materials
│ ├── CLAUDE.md # Global Claude instructions
│ ├── workflow.md # Human guide to the dev loop
│ ├── official-plugins.md # Official Anthropic plugins guide
│ ├── lsp-setup.md # LSP configuration and troubleshooting
│ ├── lang-skill-adaptation.md # Adapting skills + DX testing
│ ├── multi-agent-coordination.md # Three tiers: subagents vs Agent Teams vs Gastown
│ └── testing-agent-teams.md # Testing guide for dm-team plugin
└── README.md
SOLID principles and data-oriented design patterns.
| Component | Type | Purpose |
|---|---|---|
dm-arch:solid-architecture | Skill | SOLID principles, composition patterns, module organization, side-effect boundaries |
dm-arch:data-oriented-architecture | Skill | Registry-based dispatch, capability composition, infrastructure-first development |
Workflow tools for spec refinement, context management, and subagent delegation.
npx claudepluginhub rbergman/dark-matter-marketplace --plugin dm-workExpert language skills: Go, Rust, TypeScript, Python, Just - idiomatic patterns, type systems, and build tools
Architecture patterns: SOLID principles, composition, data-oriented design, and module organization
Agent Teams patterns for multi-agent coordination, deliberation, and collaborative workflows. Experimental — requires CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS.
Comprehensive game development skills: vision, systems architecture, mechanics evaluation, balance, economy, motivation, encounters, narrative, multiplayer, accessibility, audio, data-driven design, experience design, player UX, progression, game feel, playtest methodology, per-frame performance, and PixiJS 8 bootstrapping
11 agents, 35 skills, 18 commands, 9 hooks — spec-driven multi-agent orchestration for Claude Code, with optional cross-device semantic memory.
This skill should be used when the model's ROLE_TYPE is orchestrator and needs to delegate tasks to specialist sub-agents. Provides scientific delegation framework ensuring world-building context (WHERE, WHAT, WHY) while preserving agent autonomy in implementation decisions (HOW). Use when planning task delegation, structuring sub-agent prompts, or coordinating multi-agent workflows.
Use this agent for optimizing human-agent collaboration workflows and analyzing workflow efficiency. This agent specializes in identifying bottlenecks, streamlining processes, and ensuring smooth handoffs between human creativity and AI assistance. Examples:\n\n<example>\nContext: Improving development workflow efficiency
Multi-agent /workflow development pipeline (planner → plan-review → coder → code-review) with typed handoff contracts, lifecycle hooks, and MCP servers.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows