---
title: "Skills & Agents -- Workflow Skills and Specialist Agents"
description: "Mantis ships workflow skills, slash-command style deep modes, specialist agents, browser automation, and RTK token compression."
---

# Skills & Agents -- Workflow Skills and Specialist Agents

Mantis ships the skills the controller depends on: research, planning, review, testing, browser automation, frontend design, humanizer/copywriting, media workflows, and specialist agent orchestration. RTK Token Killer saves 82% average on command-output tokens.

## Bundled Workflow Skills

The important thing is not a vanity count. The installed Mantis skill tells Claude or Codex which deeper workflows exist, when to use them, and when to stay fast.

### 1. Superpowers (by Jesse Vincent)

Brainstorming, TDD workflows, systematic debugging, and verification workflows. Upgraded with instant response and embedded skill cores that eliminate external lookups.

### 2. Commit Commands (Anthropic)

Git commit automation, clean branch management, and a combined commit-push-PR workflow. Handles conventional commit formatting and multi-file staging.

### 3. PR Review Toolkit (Anthropic)

6 specialized review agents that run in parallel. Each agent focuses on a different aspect: security, performance, correctness, style, testing, and documentation.

### 4. Feature Dev (Anthropic)

Architecture-first development workflow: explore the codebase, design the solution, implement the code, then review the result. Each phase is a distinct step with its own agent.

### 5. Code Review (Anthropic)

Automated code review against your project's CLAUDE.md guidelines. Checks for consistency with established patterns, naming conventions, and architectural decisions.

### 6. Code Simplifier (Anthropic)

Runs automatically after each coding task to identify simplification opportunities. Reduces complexity, removes dead code, and consolidates redundant logic.

### 7. Frontend Design (Anthropic)

An 842-line skill implementing Hormozi conversion architecture and 2026 design patterns. Covers layout systems, typography, color theory, responsive breakpoints, and conversion-optimized component patterns.

### 8. Greptile

AI-powered code review with pattern detection. Identifies anti-patterns, security vulnerabilities, and inconsistencies across the codebase using structural analysis.

### 9. Context7 (Upstash)

Real-time documentation lookup for any library. Queries up-to-date docs instead of relying on training data. Ensures the AI uses current API signatures, not outdated ones from its training cutoff.

### 10. Test Installer (Built-in)

End-to-end installer testing on a Windows VM via Docker. Compiles the installer, deploys to a fresh VM restored from a golden snapshot, runs verification checks, then performs GUI walkthrough via agent-browser over noVNC. Iterates on failures automatically.

### 11. Agent-Browser

140+ command agentic browser automation platform that replaces Playwright and PinchTab. Uses your real Chrome via direct WebSocket CDP connection -- completely undetectable. Reads page structure in approximately 200 tokens per page (98.5% less than Playwright MCP). Supports parallel sessions, network interception, device emulation, video recording, and visual regression testing. Apache-2.0 open source.

### 12. Humanizer (v2.2.0)

Removes signs of AI-generated writing using 24 detection categories based on Wikipedia's "Signs of AI writing" guide. Two-pass process: draft rewrite, audit for remaining AI patterns, then final rewrite. Detects inflated symbolism, promotional language, em dash overuse, vague attributions, AI vocabulary words, and excessive conjunctive phrases.

### 13. Poe Media

Image and video generation via Poe API models. Smart routing across 9+ image models (including Flux-Kontext, Imagen-4, Nano-Banana), 4 video models (Hailuo-02, Runway-Gen-4.5, Veo-3.1, Kling-2.6-Pro), and upscale models. Supports image-to-image, editing, upscaling, video generation, and prompt chaining.

## Native Workflow Skills

In addition to the bundled skills, the controller includes native workflow skills:

| Skill | What It Does |
|-------|-------------|
| /build | Chains skills for feature development (greenfield, brownfield, TDD, refactor modes) |
| /commit | Git commits with user approval and reasoning capture |
| /continue | Resume work from a previous session's plan |
| /debug | Read-only issue investigation via logs and git history |
| /explore | Codebase exploration at varying depths (quick, deep, architecture) |
| /fix | Bug investigation and resolution orchestrator |
| /tdd | Test-driven development: RED-GREEN-REFACTOR cycle |
| /test | Comprehensive testing: unit tests in parallel with integration, then E2E |
| /review | Parallel code review with specialist agents (critic, plan-reviewer, synthesis) |
| /frontend-design | Production-grade UI generation with creative design direction |
| /help | Interactive workspace discovery |
| /recall | Semantic memory search across past sessions |
| /remember | Store learnings for future recall |
| /test-installer | VM-based installer testing with golden snapshot restore |
| /loop | Run a prompt or slash command on a recurring interval (default 10 minutes) |
| /keybindings-help | Customize keyboard shortcuts, rebind keys, add chord bindings |
| /claude-api | Build apps with Claude API, Anthropic SDK, or Agent SDK |

## Specialist Agents

Agents are purpose-built sub-processes that handle specific tasks. They work in separate contexts so your main conversation stays clean.

| Agent | Purpose |
|-------|---------|
| scout | Codebase exploration and pattern finding |
| oracle | External research and documentation lookup |
| architect | Planning and system design |
| phoenix | Large-scale refactoring plans |
| kraken | Implementation via strict TDD workflow |
| spark | Quick fixes and small changes |
| arbiter | Test execution and validation |
| sleuth | Debugging and root cause analysis |
| profiler | Performance analysis and optimization |
| herald | Release management and changelogs |
| validator | Integration and end-to-end testing |

Additional specialist agents cover documentation, migration, security auditing, dependency management, and more. Each agent has a dedicated system prompt defining its behavior, tools, and constraints.

## Context Protection

Agents work in isolated contexts. When a complex task spawns 3 sub-agents, those agents consume their own context windows -- not yours. Your main conversation remains clean and focused on high-level steering. Agent results are summarized back to you.

## RTK Token Killer

RTK (Rust Token Killer) is a Rust CLI proxy that sits between Claude Code and system tools. It compresses tool output using 12 filtering strategies, achieving 82% average token savings. Overhead is approximately 10ms per call. This means longer conversations before hitting context limits and lower API costs.

## Cross-Terminal Coordination

When running multiple Claude Code sessions in different terminals, a PostgreSQL-backed coordination system provides:

- **Session awareness**: Each terminal registers itself and can see peer sessions
- **File-level locking**: If one session is editing a file, another session receives a warning before touching the same file
- **Real-time heartbeat**: Sessions broadcast heartbeats so the system knows which are still active

This prevents merge conflicts and duplicated work when running parallel Claude sessions on the same project.

## Related

- [Getting Started](https://erebora.org/mantis/docs/getting-started) -- Skills install automatically
- [Safety Gates](https://erebora.org/mantis/docs/safety-gates) -- Skills operate within the gate pipeline
- [Browser Testing](https://erebora.org/mantis/docs/browser-testing) -- Frontend Design skill uses browser verification
- [FAQ](https://erebora.org/mantis/docs/faq) -- Questions about skills and agents
- [Live Documentation](https://erebora.org/mantis/) -- Full product page