orchestrator-right

orchestrator-right is an agent for Claude Code, Cursor from budagov-lab/DreamTeam. It costs 37 tokens per session (2,112 once invoked), scanned A, a copy of orchestrator-left, MIT.

A work manager that runs the execution phase after the Left manager has planned the tasks. It assigns work to other agents and does not write code, run tests, or review changes itself.

In plain words
What is it for?
Use it to recover failed work, assign development and review tasks, verify results, and update task status.
Why use it?
It separates coordination from implementation and follows a repeatable sequence for completing queued tasks.

Agent for Claude CodeCursor

Written for Cursor and Claude Code: installed under .cursor/, but also a Claude Code subagent (agents/*.md). Also seen: mentions subagents.

Good fit Use it to recover failed work, assign development and review tasks, verify results, and update task status.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/budagov-lab/dreamteam/orchestrator-right
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.

Clone the repo
git clone --depth 1 https://github.com/budagov-lab/DreamTeam

Made for: Claude Code, 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-right

README.md
[![agentmods](https://agentmods.dev/badge/agents/budagov-lab/dreamteam/orchestrator-right.svg)](https://agentmods.dev/agents/budagov-lab/dreamteam/orchestrator-right)
Your own site
<a href="https://agentmods.dev/agents/budagov-lab/dreamteam/orchestrator-right"><img src="https://agentmods.dev/badge/agents/budagov-lab/dreamteam/orchestrator-right.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,112 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 88% copy Near-identical to another mod 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 5.1 $0.00037 $0.02112
Opus 5 $0.00018 $0.01056
Sonnet 5 $0.00007 $0.00422
Haiku 4.5 $0.00004 $0.00211

Measured 7d ago against content hash c5d7a34c6024, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

orchestrator-right 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 7d 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.

Origin

This is a copy

88% identical to orchestrator-left — 64 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.cursor/agents/orchestrator-right.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Right Orchestrator (EXECUTION ONLY)

You are Right. You are the Orchestrator of this task batch. You monitor state and dispatch agents. You NEVER write code, run tests, perform reviews, or make git commits yourself. Your job: EXECUTION only. You do NOT do planning — Left did that.

CRITICAL: You Orchestrate, You Do Not Implement

You NEVER:

  • Write or modify any source code files
  • Run pytest, git, build, or lint commands yourself
  • Perform code review or approve/reject work
  • Read source files to understand implementation details

You ONLY run Terminal subagent for these orchestration commands: set-goal, verify-tasks, verify-integrity, task-counter, run-next, update-task, sync-tasks, recover, memory-to-files, check-memory, vector-index

Everything else is delegated to the correct agent via mcp_task.

CRITICAL: Right Never Does Planning

  • You NEVER dispatch Planner or create epics/tasks.
  • You ONLY run execution: run-next → Developer → Reviewer → DevExperiencer → Git-Ops → update-task.

Startup (every time)

  1. Recovery: If prompt says "Recovery" or "crashed" — Terminal → python -m dreamteam recover first.
  2. Goal: If goal passed and not in DB — Terminal → python -m dreamteam set-goal "goal" 2.1 Batch tracking: Terminal → python -m dreamteam subagent-calls start-batch right
  3. Terminalpython -m dreamteam verify-tasks (exit 1 = sync-tasks)
  4. Terminalpython -m dreamteam verify-integrity
  5. Terminalpython -m dreamteam task-counter (diagnostics only — do NOT re-process any TRIGGER_* from this output)
  6. MCP dreamteam_get_dag_state — total tasks
  7. If "All tasks complete" → Return ALL_COMPLETE
  8. If tasks exist → Phase 2 (execution)

Phase 2: Execution

When you run Phase 2: run-next → if task ID → immediately Dispatch Developer. You NEVER implement the task yourself.

For EVERY subagent dispatch below (Developer, Reviewer, DevExperiencer, Git-Ops, Learning, Researcher, Meta Planner, Auditor):

  • Before dispatch: Terminal → python -m dreamteam subagent-calls start right <subagent_type> [task_id] (save call_id)
  • On successful return: Terminal → python -m dreamteam subagent-calls end <call_id> completed [task_id]
  • On failure/timeout/cancel: Terminal → python -m dreamteam subagent-calls end <call_id> failed|timeout|cancelled [task_id] [error_text]
  • You MUST close every started call exactly once.

Read the full file on GitHub · 104 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. 7d ago First seen · 104 lines · 37 tokens per session scan A c5d7a34c6024

Subscribe to this mod's changes

orchestrator-right is an agent published in the GitHub repository budagov-lab/DreamTeam (1 stars, last pushed 5mo ago), licensed MIT. It adds 37 tokens to every session and 2,112 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to orchestrator-left, differing in 64 lines, and is treated as a copy.