Core — magus
Development tooling: code analysis, terminal control, browser automation, and language toolkits.
magus lists this marketplace before you add it — select it, confirm, and it is registered:
magus
For a team, pin the plugins in .claude/profiles.json and everyone runs
magus install — see Teams and profiles.
Plugin IDs carry the marketplace, so these are name@magus.
| Plugin | Version | What it does |
|---|---|---|
browser-use | 1.9.1 | Full-platform browser automation: live-page JS eval, keyboard and focus primitives, file screenshots, preflight and a configurable agent LLM, on local or cloud browsers. Runs Playwright's own Chromium, never your real Chrome. Adds Magus tools and 6 skills to the upstream Browser Use MCP set. |
bunjs | 0.5.0 | Bun and TypeScript toolkit. A /bunjs:bun index routes any task to the right one of eight task-shaped skills — setup, HTTP, errors, testing, security, production, performance, TUI — each shipping copyable code verified against Bun. Only Bun is tested. |
claudish | 2.3.0 | MCP runtime for external AI models. Proxies OpenRouter, Ollama and LM Studio, runs blind team voting, manages async sessions, streams channel notifications, and shows the session's runs live above the prompt, with stop and live-screen tabs. Required by code-search, dev, multimodel and designer. |
code-search | 8.3.1 | Read-only code search and investigation behind one stable tool surface. Finds code by meaning or structure, traces callers, callees and blast radius, and dispatches an analyze agent for deep dives. The search engine is named in project settings and is swappable. |
designer | 0.10.0 | UI design validation. Compares a rendered screen against its reference by pixel diff, then reviews the result for spacing, hierarchy and design-system consistency. |
dev | 9.1.1 | Universal development assistant. Detects the project stack and routes work to specialist agents for architecture, implementation, debugging, review and research, enforcing design-system guardrails on every UI change. |
dingo | 1.0.4 | BETA — Dingo language toolkit. Idiomatic Result and Option types, error propagation, enums, pattern matching, lambdas and safe navigation, with compiler-verified patterns. Interfaces may still change. |
go | 0.2.0 | Go development toolkit. Ships the go-tui skill for building Charm-stack terminal UIs (Bubble Tea, Lip Gloss, Bubbles, ntcharts), with a colour-accurate screenshot workflow for reviewing a running TUI. |
madbench | 0.9.1 | Toolkit for madbench, MadAppGang's Go harness for benchmarking agentic coding tools. Carries madbench's own skills with /madbench:madbench as the entry point, checks them against the installed madbench, and runs benches in a visible pane through the madbench:bench agent. |
mnemex | 1.1.1 | MCP runtime for semantic code search and AST analysis, ranking symbols by PageRank. Optional engine behind the code-search facade, and usable directly for its full tool surface. |
multimodel | 5.3.1 | Multi-model collaboration and orchestration. Runs a task across several AI models in parallel and aggregates their blind APPROVE/REJECT votes, or delegates it to one model running a full Claude Code session. |
setup | 1.5.1 | Project setup jobs in one plugin. Investigates a repository and provisions it — plugins, tools, framework best-practice references, and a seeded knowledge base — then installs the adaptive statusline and indexes every skill reachable from the project into browsable markdown. |
terminal | 5.3.1 | Slot-addressed terminal control over tmux. Runs interactive commands, dev servers, test watchers, REPLs and TUI apps in numbered helper panes — beside the user or isolated from view — that the server places and owns, so an agent never holds a pane id or targets the user's own session. |
Turn any of them on from the Plugins tab. To give a team the same set, press s to save
your selection as a profile and commit it — see Teams and profiles.
Advanced Usage covers global installs, version pinning and updates.