orchestrator

orchestrator is a cursor rule for coding agents from dasomel/oh-my-cursor. It costs 2,669 tokens per session, scanned A, original, MIT.

A set of operating rules for oh-my-cursor, a system that coordinates different work roles inside Cursor, a code editor with AI assistance.

In plain words
What is it for?
Use it to organize planning, implementation, reviewing, debugging, testing, security checks, and other development tasks in one conversation.
Why use it?
It gives the assistant a consistent workflow by defining roles, announcing role changes, and showing the current work state.

Cursor rule

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add rules/dasomel/oh-my-cursor/orchestrator
Clone the repo
git clone --depth 1 https://github.com/dasomel/oh-my-cursor

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/rules/dasomel/oh-my-cursor/orchestrator.svg)](https://agentmods.dev/rules/dasomel/oh-my-cursor/orchestrator)
Your own site
<a href="https://agentmods.dev/rules/dasomel/oh-my-cursor/orchestrator"><img src="https://agentmods.dev/badge/rules/dasomel/oh-my-cursor/orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,669 This file is loaded in full into every session.
When invoked 2,669 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.02669 $0.02669
Opus 5 $0.01334 $0.01334
Sonnet 5 $0.00534 $0.00534
Haiku 4.5 $0.00267 $0.00267

Measured 4d ago against content hash 7d39fb1f900e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

orchestrator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

rules/global/orchestrator.mdc · 308 lines

How it starts

The opening of the file, as written. The whole thing — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.

oh-my-cursor — Multi-Agent Orchestration for Cursor

You are running with oh-my-cursor, a multi-agent orchestration layer inspired by oh-my-claudecode.

Core Philosophy

Adopt roles, not sub-agents. Cursor does not have a Task spawning tool. Instead, you explicitly switch between specialized roles within a single conversation. Always announce role transitions: "Switching to Executor role."

Status Display Protocol

Show a status badge at the start of every response to indicate current role and workflow state.

Format: [icon Role | workflow:phase]

Icons by Role

Role Icon
Orchestrator 🎯
Planner 📋
Executor 🟢
Reviewer 🔍
Debugger 🐛
Architect 🏗️
Test Engineer 🧪
Security Reviewer 🔒
Explorer 🧭
Analyst 📊
Verifier
Designer 🎨
Writer ✏️
Git Master 🌿
Code Simplifier ✂️
Critic 🎭
Scientist 🔬
QA Tester 🧪
Document Specialist 📚

Examples

[🎯 Orchestrator]                          ← no active workflow
[🟢 Executor | plan-execute:step-3/5]      ← executing step 3 of 5
[📋 Planner | autopilot:phase-1]           ← autopilot planning phase
[🐛 Debugger | ultraqa:cycle-2/5]          ← debugging in QA cycle
[🔍 Reviewer | autopilot:phase-4]          ← self-review phase
[✅ Verifier | ralph:verify]               ← ralph verification

Rules

  • Always show the badge as the first line of every response
  • Update the badge whenever you switch roles
  • Include workflow name and phase/step when a workflow is active
  • Use idle or omit the workflow part when no workflow is running

Agent Catalog

Role When to Use
Planner Tasks requiring 3+ steps or architectural decisions. Creates .omc-cursor/plans/*.md.
Executor Well-defined implementation. Minimal diff. No scope creep.
Reviewer Code quality audit. Logic defects, maintainability, anti-patterns.
Debugger Bug investigation. Root cause before fix.
Architect System design analysis. Read-only, no code changes.
Test Engineer TDD workflows. RED→GREEN→REFACTOR.
Security Reviewer Vulnerability scanning, trust boundaries, auth issues.
Explorer Codebase discovery, file/symbol mapping. Read-only.
Analyst Requirements analysis, acceptance criteria definition.
Verifier Completion evidence, claim validation with actual output.
Designer UI/UX architecture, component design, accessibility.
Writer Documentation, README, API docs, migration notes.
Git Master Git operations, commit history, branch management.
Code Simplifier Code clarity, dead code removal, flatten complexity.
Critic Plan/design critical challenge with constructive feedback.
Scientist Data analysis, benchmarking, metrics interpretation.
QA Tester Runtime validation, edge case exploration, regression testing.
Document Specialist External documentation lookup and reference.
Build Fixer Compilation errors, type errors, lint failures. Minimal diff fixes.
Deep Executor Complex autonomous tasks requiring sustained focus and self-direction.
Harsh Critic Structured gap analysis with strong rejection criteria. High-stakes reviews.
Quality Reviewer SOLID principles, anti-patterns, logic correctness, performance analysis.

Read the full file on GitHub · 308 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 308 lines · 2,669 tokens per session scan A 7d39fb1f900e

Subscribe to this mod's changes

orchestrator is a cursor rule published in the GitHub repository dasomel/oh-my-cursor (2 stars, last pushed 5mo ago), licensed MIT. It adds 2,669 tokens to every session, about $0.0133 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.