Skip to content

tmcfarlane/oh-my-cursor

Repository files navigation

oh-my-cursor
presents

oh-my-cursor: Team Avatar Agent Orchestration

TEAM AVATAR

Multi-agent philosophy for Cursor subagents. Nothing but config files.
Created by ZeroClickDev

NOW USING UNDOCUMENTED FEATURES OF CURSOR!

License: MIT GitHub Stars

April 14, 2026 — Welcome @bastien70 to Team Avatar! Two fantastic PRs just landed:

  • Composer 2 Fast migration — All default agents now run on Composer 2 Fast, aligning with Cursor's Auto + Composer pool for lower latency and cost (#20)
  • Zuko gets Nana Banana — Zuko now has image generation capabilities powered by Nana Banana, leveling up the Firebender's visual toolkit

These contributions were so solid that @bastien70 has been added as a CODEOWNER — they can now approve PRs from other contributors. Welcome to the project! 🎉

Want to contribute too? Contributions welcome!

Quick Start (One Command)

macOS / Linux:

curl -fsSL https://raw.githubusercontent.com/tmcfarlane/oh-my-cursor/main/install.sh | bash

Windows (PowerShell):

irm https://raw.githubusercontent.com/tmcfarlane/oh-my-cursor/main/install.ps1 | iex

What Is This?

8 agent manifests, 8 slash commands, hooks, and one orchestration rule — themed around Avatar: The Last Airbender. No external runtime, no wrapper CLI — just Cursor's built-in Task subagents and Markdown config files.

Uses undocumented custom model aliases for per-agent model routing. Unofficial — may change.

Contents

The Orchestrator

The orchestrator rule (orchestrator.mdc) rewires how the root thread thinks. The root becomes a pure dispatcher — its only permitted tools are Task, TodoWrite, AskQuestion, and SwitchMode. All work flows through specialist agents.

Here's a real example of the root thread's internal reasoning:

Planning Installation Instructions

I need to follow the orchestrator's guidance, since the root can't use Read directly and must delegate via Task. I have to document this in the README and use iroh, but I'm unsure about the new installation instructions, which might be documented elsewhere. It's critical to know these details, so I could search the repository with iroh/toph for existing install docs. I'll have to organize a plan: dispatch toph to find the installation instructions and have iroh update the README after. Plus, I'll create a to-do list to keep track of everything.

Every sentence maps to an orchestrator rule: agent routing (Iroh for docs, Toph for search), phase chaining (explore → write), and mandatory task tracking via TodoWrite.

Team Avatar -- The Agents

Eight specialized agents, each mapped to an Avatar character with a dedicated model and role. Expand any agent for skills and working screenshots.

Aang   Sokka   Katara   Zuko   Toph   Appa   Momo   Iroh

AangThe Avatar · composer-2-fast

Deep multi-file executor + architecture consultant. Masters all elements.

Master of all four elements — Multi-agent orchestration in action

Skills: design-patterns-implementation · refactoring-patterns · vercel-react-best-practices

Aang working screenshot

SokkaThe Strategist · claude-4.7-opus-max-thinking

Planning, ambiguity analysis, plan review. The brain behind every mission.

Ask First, Dispatch Second — The orchestrator clarifies before sending agents

Skills: architect · planning · technical-roadmap-planning

Sokka working screenshot

KataraThe Healer · composer-2-fast

Disciplined implementation, debugging, methodical fixes. Mends broken code.

Precision Healer — Surgical debugging, smallest possible fix

Skills: debugging · refactoring · refactoring-patterns

Katara working screenshot

ZukoThe Firebender · gemini-3.1-pro

Visual design: image generation, icons, UI mockups. Brings designs to life.

Fire and Finesse — Image generation, icons, and UI mockups

Skills: create-an-asset · implementing-figma-designs · web-design-guidelines

Zuko working screenshot

TophThe Seer · composer-2-fast

Codebase search, external docs, media analysis. Sees everything.

Seismic Sense — Multi-angle codebase search and doc exploration

Skills: codebase-search · exploring-codebases · mgrep-code-search

Toph working screenshot

AppaThe Heavy Lifter · composer-2-fast

Systematic task list execution. Carries the team.

Plan Executor — Systematic task list execution, one step at a time

Skills: frontend-builder · vercel-composition-patterns · vercel-react-best-practices

Appa working screenshot

MomoThe Scout · composer-2-fast

Quick focused tasks. Small, agile, independent.

Speed Demon — Parallel micro-tasks, maximum speed

Skills: refactoring · refactoring-patterns · vercel-react-best-practices

Momo working screenshot

IrohThe Storyteller · claude-4.7-opus-max-thinking

Documentation specialist. Sole owner of README, CHANGELOG, and all project docs.

Man of his letters — Iroh spends much of his time writing letters to family.

Skills: crafting-effective-readmes · docs-write · documentation-engineer · documentation-writing

Iroh working screenshot

Model Policy

Default model: Composer 2 Fast (composer-2-fast). See the Composer 2 docs, which also apply to the Fast variant. Higher speed, uses Cursor’s Auto + Composer pool. (#20, #21)

Exceptions:

Agent Model Reason
Sokka claude-4.7-opus-max-thinking Maximum reasoning for complex planning
Iroh claude-4.7-opus-max-thinking Long-form documentation quality
Zuko gemini-3.1-pro Multimodal / visual stack

Coordinator-spawned workers may use Cursor’s fast tier or inherit the coordinator’s model. If a workflow regresses on Composer 2 Fast, change model: in the agent’s markdown file.

How to Install

Requirements: Cursor with agent mode (subagents). No external runtime.

macOS / Linux

curl -fsSL https://raw.githubusercontent.com/tmcfarlane/oh-my-cursor/main/install.sh | bash
More options
bash -s -- --project     # Install to this project only (./.cursor/)
bash -s -- --claude --codex  # Also install for Claude Code and Codex
bash -s -- --no-skills   # Skip skills installation
bash -s -- --dry-run     # Preview changes
bash -s -- --force       # Update/overwrite existing files
bash -s -- --uninstall   # Uninstall
bash -s -- --disable     # Disable orchestration (agents stay)
bash -s -- --enable      # Re-enable orchestration

Append these flags to the curl ... | bash one-liner above. Hacking locally? Clone the repo, then run bash install.sh.

Windows (PowerShell)

irm https://raw.githubusercontent.com/tmcfarlane/oh-my-cursor/main/install.ps1 | iex
More options
# PowerShell 7+ / Windows 11 one-liner with flags:
& ([scriptblock]::Create((irm https://raw.githubusercontent.com/tmcfarlane/oh-my-cursor/main/install.ps1))) -Scope project -Force

# Or clone and run locally (all versions):
git clone https://github.com/tmcfarlane/oh-my-cursor.git && cd oh-my-cursor
.\install.ps1                    # Default (user scope)
.\install.ps1 -Scope project    # Project scope
.\install.ps1 -AlsoClaude -AlsoCodex  # Cross-tool compat
.\install.ps1 -NoSkills         # Skip skills
.\install.ps1 -Force            # Overwrite
.\install.ps1 -Uninstall        # Remove

On Windows PowerShell 5.1, irm | iex only supports default install. For flags, clone the repo.

What Gets Installed

Scope Agents Rules Commands Hooks Skills
--user (default) ~/.cursor/agents/ ~/.cursor/rules/ ~/.cursor/commands/ ~/.cursor/hooks/ ~/.cursor/skills/
--project ./.cursor/agents/ ./.cursor/rules/ ./.cursor/commands/ ./.cursor/hooks/ ./.cursor/skills/
--claude Also .claude/agents/ Also .claude/rules/ Also .claude/commands/ Also .claude/hooks/
--codex Also .codex/agents/ Also .codex/rules/ Also .codex/commands/ Also .codex/hooks/
--no-skills Skipped

First-time rule activation: Cursor may require you to approve the orchestrator rule. Open ~/.cursor/rules/orchestrator.mdc and click "Always Allow" when prompted (one-time step).

Upgrading from v0.1: The installer auto-removes old agent files (hephaestus, prometheus, atlas, etc.).

Undocumented: Custom Model Aliases

Cursor accepting custom model aliases in agent frontmatter

Cursor’s model: field in agent frontmatter accepts arbitrary model alias strings — not just built-in options. This enables per-agent model routing:

---
model: composer-2-fast # fast agent work
---
---
model: gemini-3.1-pro # multimodal tasks
---

Undocumented — may change without notice. Works as of February 2026. If removed, swap model: to any picker-supported string; the rest of oh-my-cursor still works.

Slash Commands

Type these in Cursor's chat to invoke specific workflows:

Command Agent Purpose
/plan Sokka Full planning pipeline: ambiguity analysis, plan creation, self-review
/build Aang Deep multi-file implementation with verification
/search Toph Multi-angle codebase + docs exploration
/fix Katara Methodical debugging and code healing
/tasks Appa Systematic task list execution
/scout Momo Quick focused tasks
/doc Iroh Documentation generation and updates
/image Zuko Cursor image generation (Nano Banana Pro): icons, mockups, prompts via cursor-image-generation skill
/cactus-juice Swarm Decompose into micro-tasks, spawn up to 10 parallel workers

Image generation (Cursor agent)

The agent can generate images via Google Nano Banana Pro; previews save under assets/ by default. Team Avatar routes visual generation to Zuko, which uses the cursor-image-generation skill (skills/cursor-image-generation/SKILL.md) to rewrite short user requests into full prompts, then iterate. Use /image or delegate Task(zuko) for image-only work.

Two Orchestration Modes

Avatar State (Default)

Coordinated, tiered orchestration. The orchestrator auto-detects which agents to dispatch based on request signals.

Cactus Juice Mode

Activated via /cactus-juice. Trades depth for massive parallelism:

  1. Root decomposes your request into 5–10 independent micro-tasks (single-file scope)
  2. Up to 10 subagents spawn simultaneously using model: fast
  3. Workers write low cognitive complexity code
  4. Root collects results, verifies consistency, fixes integration issues

Cactus Juice mode demo

Architecture

flowchart TD
  U["You (root thread)"] --> R["orchestrator.mdc<br/>(Team Avatar)"]

  R --> IG{"Intent gate<br/>what did the user ask?"}

  IG -->|"search / 'how does X work?'"| T["Task(toph)<br/>Seer"]
  IG -->|"ambiguous / complex scope"| S["Task(sokka)<br/>Strategist"]
  IG -->|"visual assets"| Z["Task(zuko)<br/>Firebender"]

  IG -->|"complex feature"| PLAN["Task(sokka) → plan"]
  PLAN --> IMPL["Task(aang / katara)<br/>Coordinators"]

  IMPL -->|"spawns"| T2["toph (fast)"]
  IMPL -->|"spawns"| M2["momo (fast / inherited)"]

  IG -->|"task list"| AP["Task(appa)<br/>Heavy Lifter"]
  AP -->|"spawns"| M3["momo"]

  IG -->|"quick task"| MO["Task(momo)<br/>Scout"]

  IMPL --> V{"Verification<br/>lints / build / tests"}
  V -->|pass| DONE["Done"]
  V -->|fail| FR["Failure recovery<br/>(retry → aang → user)"]

  subgraph swarmNote ["Swarm Mode (Cursor 2.5+)"]
    N1["Coordinators spawn workers async.<br/>Max depth = 2. Workers are leaf nodes."]
  end
Loading

Async Subagents (Cursor 2.5+)

Two-tier swarm: Coordinators (Aang, Sokka, Katara, Appa) spawn Workers (Toph, Momo) as leaf nodes. Zuko is root-only.

Pattern How It Works
Fire-and-Continue Spawn Toph in background, continue working, collect results later
Fire-and-Collect Spawn multiple Momo workers, wait for all, verify each
Research-then-Act Parallel Toph research, then use findings to guide implementation

Hooks

System-level enforcement that doesn't rely on agents remembering to verify:

Hook Purpose
post-edit-lint.sh Automatically run lints after agent edits
pre-commit-check.sh Enforce hard constraints (as any, empty catches, @ts-ignore) before commits

Prompting Tips

You are Team Avatar. Use @toph to explore the codebase, @sokka to create a plan,
and @aang to implement. Verify with lints/build/tests. Keep going until done.

Or use slash commands: /plan add OAuth support with JWT tokens then /build based on the plan above.

Skills

19 bundled skills vendored from the community. Each is a SKILL.md directory that Cursor auto-discovers and presents to agents as domain knowledge. Bundled in-repo for security (no fetching third-party files at install time) and efficiency (single file copy). Installed by default; use --no-skills to skip.

Bundled skills

Skill Source Agents What it provides
architect thebushidocollective/han Sokka System architecture and high-level technical design
codebase-search supercent-io/skills-template Toph Systematic search strategies for navigating large codebases
create-an-asset anthropics/knowledge-work-plugins Zuko Generate tailored sales assets (landing pages, decks, one-pagers)
crafting-effective-readmes community Iroh Templates and guidance for writing effective READMEs matched to project type
debugging oimiragieo/agent-studio Katara Systematic 4-phase debugging with root cause investigation
design-patterns-implementation aj-geddes/useful-ai-prompts Aang Apply design patterns (Singleton, Factory, Observer, Strategy, etc.)
docs-write metabase/metabase Iroh Documentation following Metabase's conversational, user-focused style
documentation-engineer charon-fan/agent-playbook Iroh Technical documentation for creating clear, comprehensive docs
documentation-writing rysweet/amplihack Iroh Clear, discoverable docs following the Eight Rules and Diataxis framework
exploring-codebases community Toph Semantic search using AST-aware expansion for full context
frontend-builder daffy0208/ai-dev-standards Appa Modern React/Next.js frontend patterns and component architecture
implementing-figma-designs onekeyhq/app-monorepo Zuko Implement Figma designs 1:1 using component libraries
mgrep-code-search intellectronica/agent-skills Toph Semantic code search using mgrep for efficient exploration
planning thebushidocollective/han Sokka Technical implementation planning and architecture design
refactoring eyadsibai/ltk Katara, Momo Code restructuring, renaming, extraction, and migration
refactoring-patterns wondelai/skills Aang, Katara, Momo Named refactoring transformations to improve code structure
technical-roadmap-planning aj-geddes/useful-ai-prompts Sokka Comprehensive technical roadmaps aligned with business goals
vercel-composition-patterns vercel-labs/agent-skills Appa React composition patterns that scale
vercel-react-best-practices vercel-labs/agent-skills Aang, Appa, Momo React and Next.js performance optimization from Vercel Engineering
web-design-guidelines vercel-labs/agent-skills Zuko Web Interface Guidelines compliance for UI review

Custom skills: Create a SKILL.md directory under .cursor/skills/ (project) or ~/.cursor/skills/ (user). Cursor auto-discovers it.

FAQ

Do I need to manually choose agents?

No — the orchestrator auto-delegates. Slash commands (/plan, /build, /fix, etc.) give explicit control when you want it.

Will this work on any Cursor plan?

Yes, if your plan supports agent mode / subagents.

How do I update?

Re-run the install command with --force (or -Force on Windows).

How do I uninstall?

Re-run with --uninstall (or -Uninstall on Windows).

Claude Code / Codex?

Yes — install with --claude --codex (or -AlsoClaude -AlsoCodex).

Origin Story

Upgraded to Cursor Ultra with 9 days left to burn ~$300 in tokens. Built agent swarms to do real work while responsibly (irresponsibly) optimizing token burn. Turns out all it takes is dropping Markdown config files into Cursor + one orchestration rule.

Inspiration

Adapted from oh-my-opencode (32k+ stars) — agent specialization, parallel dispatch, phased orchestration — applied to Cursor's native Task subagents. No plugin system, no wrapper CLI.

Star History

Star History Chart

Contributing

Contributions that improve clarity, behavior, or docs are welcome. See CONTRIBUTING.md for guidelines.

Local development: Clone the repo and run bash install.sh (macOS/Linux) or .\install.ps1 (Windows) to install from source. Changes to agents, rules, commands, or hooks take effect after reinstalling.

Security

To report a vulnerability, see SECURITY.md.

License

MIT. See LICENSE - Steal It Respectfully!

About

Like “oh-my-opencode”, but for Cursor IDE. Multi-agent orchestration, natively, using nothing but a few config files.

Resources

License

Contributing

Security policy

Stars

Watchers

Forks

Contributors