Plugins

Rook — AI bridge for Rhino 3D & Grasshopper. Skills, hooks, and MCP tools for designing and building parametric definitions, 3D roads, and LLM-powered components via natural language.

IRC-based multi-agent coordination for Claude Code. Run a local IRC server and coordinate multiple Claude sessions via named channels a human operator can join with any IRC client.

Safely audit, install, repair, and validate rootless Docker Engine.

Full-lifecycle incident management: deploy safety, incident response, on-call management, and retrospectives.

Rosetta for Claude - Software Engineering Accelerator instruction set, workflows, and guardrails.

Hosted Rosie MCP plus skills for Alameda County navigation, search QA, and case-manager query evaluation.

Roslyn C#/VB language server for Claude Code: one shared per-workspace server, analyzer shadow-copying so builds never lock, native .slnx and .NET 10, plus a refactoring MCP (solution-wide rename, code actions, find-references, format) and an extension API for live systems.

C# code intelligence via Microsoft's Roslyn language server, bridged through a stdio proxy that injects solution/open so a generic LSP client loads the full workspace.

Guided rote skills — first-run setup, dry-run-first adapter creation, adapter configuration, and updates. The setup/manage companion to the day-to-day rote skill.

Orchestrate a multi-agent adversarial review panel. 4-6 reviewers with distinct personas independently evaluate work, debate findings across 1-3 rounds, then a supreme judge renders the final verdict. Bundles plan-review-integrator for applying findings back into implementation plans. Auto-detected Precise/Exhaustive mode, severity verification, tiered L0/L1/L2 knowledge mining, 10 signal groups with domain checklists. Based on ChatEval, AutoGen, DMAD, CONSENSAGENT, and Trust or Escalate research.

Self-configuring status briefing generator. Learns your communication style from examples, discovers your data sources, and produces draft updates for any audience on demand.

team-ready research briefing skill with asset-scoped model-routing policy metadata.

Package one or more local skills into a working Remote Routine on claude.ai/code/routines: introspect dependencies, extract the credentials it needs, generate setup.sh + .mcp.json, scaffold the repo, and walk through the UI checkpoints. Provides the /package-as-routine command.

Orchestrator skills (meta-skills) that chain leaf skills from account-transaction and position into daily/weekly backoffice routines. Designed for Claude Cowork Desktop scheduled tasks. First routine: daily-btg-offshore-routine.

Minimal context-engineering MCP server for coding agents: fast search, codemaps, curated selections, packaged exports, verified edits, and a context-builder subagent with rp-* skills.

Fix a bug with a reproduction test first, then the fix, then the full suite, then a short report. Requires a clear bug description.

Add a feature strictly by BDD: plan, red tests, green implementation, full suite, docs and examples, linter at the end. Requires a clear feature description.

Create or refresh agent project rules (Cursor .mdc, Claude Code .claude/rules). Layered-cake architecture + BDD, with a mandatory Rules Sync step across agent trees.

Warm up context on a repository: study code, docs and tests, set up the dev environment, run tests, write a short report. No extra brief required.

Engineer and conformance-test Ethereum JSON-RPC (execution-apis) changes across EL clients.

Feature development workflow: arch → plan → implement → review → fix

Research → Propose → Plan → Implement → Verify workflow for Claude Code. Spec-driven development with persistent artifacts under .rpi/.

Full RPI lifecycle — discovery, plan, crank, swarm, implement, council, quick-execute, vibe, validation

from victor-barbera/cc-marketplace

Publicly-shareable plugin — /build + dev tooling, MCP standards, env setup, productivity skills, and generic MCP servers

Teaches Claude to use the rr CLI for syncing code and running commands on remote machines

AIDE²-style recursive self-improvement loop: an outer agent iteratively rewrites an inner tree-search research agent, keeping a rewrite only when it beats the incumbent on private held-out scores under a fixed budget across an optimization / ML-engineering / harness-engineering battery. Standalone /rsi:autoresearch solves tasks by tree search; /rsi:init + /rsi:step + /rsi:run drive the outer loop.

Use RSpec to test Ruby on Rails applications, favouring readability and maintainability over brevity.

Token-optimized CLI proxy using RTK (Rust Token Killer) - 60-90% token savings on dev operations

Transparent token compression for Claude Code via RTK