MadAppGang/magus

agent-model

Picks the browser-use agent brain LLM per task. Use when choosing a model for retry_with_browser_use_agent or a cloud session, or the user mentions a cheap, slow, or smart model.

core-api

Reference for the Browser Use MCP tools — parameters, returns, session lifecycle. Use when navigating, clicking, typing, evaluating JS, or extracting page content.

debug-ui

Visual UI debugging — screenshot capture and analysis, responsive layout checking at multiple viewport sizes, CSS validation via DOM state, visual regression detection, before/after state comparison.

hybrid-debugging

Combines Browser Use (DOM, clicks, screenshots) with claude-in-chrome (console, network, JS) for full-spectrum debugging. Use when investigating console errors or network requests.

navigation-patterns

URL navigation, multi-tab orchestration, session creation and management, back/forward navigation, browser profile persistence, session export/import for authentication reuse.

web-scraping

Structured data extraction from web pages — pagination patterns, dynamic SPAs, authenticated scraping, rate limiting, anti-bot handling, JSON/CSV output.

mnemex-orchestration

Use when orchestrating multi-agent code analysis with mnemex. Run mnemex once, share output across parallel agents. Enables parallel investigation, consensus analysis, and role-based command mapping.

browser-use-integration

Detects the browser-use@magus plugin and captures screenshots of URL-based references. Use when designer agents need browser screenshot capture and claude-in-chrome is unavailable.

compare

Provides the compare.ts CLI invocation pattern, semantic comparison prompt template, severity thresholds, and model selection guide for UI design comparison.

design-references

Provides design system references — Material 3, Apple HIG, Tailwind UI, Ant Design, Shadcn/ui. Use when reviewing UI against an established design system.

ui-analyse

Analyzes UI visually using Gemini 3 Pro — prompting patterns, severity guidelines, analysis-only. Use when reviewing UI visuals; pair with dev:frontend-implement to apply.

ui-design-review

Prompting patterns and review templates for UI design analysis with Gemini multimodal capabilities. Use when conducting design reviews, accessibility audits, or design system validation.

ui-style-format

Specifies the UI design style file format and schema for .claude/design-style.md and .claude/design-references/. Use when creating, validating, or parsing project design styles.

architecture

Router for architecture knowledge — 7 architectural styles (layered, hexagonal, clean, modular monolith, microservices, event-driven, CQRS) and the 22 GoF design patterns. Names which file to read; loads none of them.

task-management

Manages Claude Code Tasks across multi-phase workflows — phase tracking, stale cleanup, optional GTD persistence. Use when orchestrating phased work.

dingo-developer

Generates and reviews Dingo meta-language code with Go boundary handling. Use when the user mentions Dingo, .di files, or Dingo-to-Go transpilation.

madbench-evals

Authors, runs, and debugs madbench evals — bench YAML, checks, red-state testdata, expectation tuning. Use when creating or reviewing a madbench.yaml, choosing checks, or debugging a failing bench.

agent-enforcement

Multi-agent orchestration enforcement for /team command. Validates session directory paths and ensures /team Tasks use a valid agent from the routing whitelist. Use when debugging /team orchestration failures.

batching-patterns

Batches related operations into single messages for maximum parallelism. Use when launching multiple agents, reading many files, or removing sequential execution bottlenecks.

claudish-usage

Routes Claudish between MCP tools (team, create_session for /team and /delegate) and the CLI for direct usage. Use when the user mentions claudish, OpenRouter, or external AI models.

delegate-patterns

Delegating plugin commands and tasks to external models via claudish — capability discovery, pre-flight question gathering, and prompt assembly. Use when routing work to an external model.

error-recovery

Handle errors, timeouts, and failures in multi-agent workflows. Use when dealing with external model timeouts, API failures, partial success, user cancellation, or graceful degradation.

hierarchical-coordinator

Prevents goal drift in long multi-agent runs by validating outputs against the original objective at checkpoints. Use when orchestrating 3+ agents or multi-phase work.

hooks-system

Lifecycle hook patterns — PreToolUse, PostToolUse, UserPromptSubmit, Stop, SubagentStop. Use when configuring hooks, writing validation, auto-format on save, stdin payloads, exit-2 blocking, or debugging a hook.

model-tracking-protocol

MANDATORY tracking protocol for multi-model validation. Creates structured tracking tables BEFORE launching models, tracks progress during execution, and ensures complete results presentation. Use when running 2+ external AI models in parallel.

multi-agent-coordination

Coordinate multiple agents in parallel or sequential workflows. Use when running agents simultaneously, delegating to sub-agents, switching between specialized agents, or managing agent selection.

multi-model-validation

Runs the same task across multiple AI models in parallel and aggregates verdicts. Use when the user wants a second opinion, multi-expert validation, or consensus from Grok, Gemini, GPT-5, or Kimi.

performance-tracking

Track agent, skill, and model performance metrics for optimization. Use when measuring agent success rates, tracking model latency, analyzing routing effectiveness, or optimizing cost-per-task.

proxy-mode-reference

Reference guide for using external AI models via claudish MCP tools and CLI. Orchestration workflows (/team, /delegate) use MCP tools. Direct usage uses CLI. Includes model routing and error handling patterns.

quality-gates

Implement quality gates, user approval, iteration loops, and test-driven development. Use when validating with users, implementing feedback loops, classifying issue severity, running test-driven loops, or building multi-iteration workflows.

session-isolation

Use when orchestrating workflows that generate multiple files (designs, reviews, reports) to prevent file collisions across concurrent or sequential sessions with unique session directories.

task-complexity-router

Routes tasks to model tiers (haiku/sonnet/opus) by complexity. Use for model selection, complexity routing, picking a tier, or optimizing API cost.

task-external-models

Quick reference for running external models in orchestration. They are invoked via claudish MCP tools (team, create_session), never the CLI. Use when unsure how to specify an external model.

task-orchestration

Track progress in multi-phase workflows with Tasks system. Use when orchestrating 5+ phase commands, managing iteration loops, tracking parallel tasks, or providing real-time progress visibility.

statusline-customization

Configuration reference and troubleshooting for the statusline plugin — sections, themes, bar widths, and script architecture

framework-signals

Provides pass/fail/running/idle output markers for 15+ test, build, and deploy tools. Use when monitoring terminal output for jest, vitest, pytest, go test, cargo, webpack, vite, or vercel.

tdd-workflow

Drives a Red-Green-Refactor state machine for TDD with terminal test watchers. Use when running TDD in watch mode or iterating on failing tests with jest, vitest, cargo watch, or pytest-watch.

terminal-interaction

Provides tmux-mcp tool API patterns for interactive terminal access. Use when running interactive commands, starting dev servers, watching test output, querying databases, or splitting panes.

tui-navigation-patterns

Provides key sequences and navigation patterns for common TUI apps. Use when navigating vim, nano, htop, less, psql, lazygit, k9s, tig, btop, or sending keystrokes to a database shell.

workspace-setup

Orchestrates tmux workspaces — sessions, dashboard layouts, watch/entr monitors, synced panes. Use when setting up a project session, building a multi-pane dashboard, or syncing panes.