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.
npx agentmods add rules/budagov-lab/dreamteam/subagentsgit clone --depth 1 https://github.com/budagov-lab/DreamTeamWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00354 |
| Opus 5 | $0.00000 | $0.00177 |
| Sonnet 5 | $0.00000 | $0.00071 |
| Haiku 4.5 | $0.00000 | $0.00035 |
Grade A, and why
subagents 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 yesterday.
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.
What it actually says
Subagent Dispatch
When Left or Right need to dispatch a subagent:
Load the appropriate agent prompt from .cursor/agents/ — each agent has its own file.
Full dispatch rules and agent list: .cursor/AGENTS.md
Dispatch via mcp_task
Use mcp_task with the correct subagent_type:
| Agent | subagent_type |
|---|---|
| Developer | developer |
| Reviewer | reviewer |
| Git-Ops | git-ops |
| Planner | planner |
| Sub-Planner | planner-sub (Planner only, not Left/Right) |
| Researcher | researcher |
| Meta Planner | meta-planner |
| Auditor | auditor |
| Learning | learning |
| FixPlanner | fix-planner |
| DevExperiencer | dev-experiencer |
| Terminal | shell |
| Left | orchestrator-left (Dispatcher only) |
| Right | orchestrator-right (Dispatcher only) |
Left/Right Terminal Commands (Orchestration Only)
Left and Right run Terminal (shell) subagent ONLY for:
set-goal, verify-tasks, verify-integrity, task-counter, run-next, update-task, sync-tasks, recover, memory-to-files, check-memory, vector-index, subagent-calls
All other work goes to the appropriate specialized agent.
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.
- yesterday First seen · 41 lines · 0 tokens per session scan A 3805c11d2f70
subagents is a cursor rule published in the GitHub repository budagov-lab/DreamTeam (1 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 354 tokens. 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.
Other cursor rules, from other repositories
data-science
Rules for data science, ML, and Jupyter notebook work.
nextjs
Rules for Next.js projects (App Router and Pages Router).
java-kotlin
Rules applied when working in Java or Kotlin files (incl. Android).
php
Rules applied when working in PHP files (incl. Laravel, Symfony, WordPress).
vue
Rules for Vue (2 and 3) single-file components.
cursorrules
40 lines, or explicitly requested.