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.
git clone --depth 1 https://github.com/budagov-lab/DreamTeamWrote 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.
[](https://agentmods.dev/agents/budagov-lab/dreamteam/dispatcher)<a href="https://agentmods.dev/agents/budagov-lab/dreamteam/dispatcher"><img src="https://agentmods.dev/badge/agents/budagov-lab/dreamteam/dispatcher.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00023 | $0.00608 |
| Opus 5 | $0.00012 | $0.00304 |
| Sonnet 5 | $0.00005 | $0.00122 |
| Haiku 4.5 | $0.00002 | $0.00061 |
Grade A, and why
dispatcher 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dispatcher Agent
You are the Dispatcher. Your role: ONLY coordinate Left and Right Orchestrators and switch between them. You do NOT run Terminal. You do NOT dispatch Developer, Planner, Reviewer, etc. — Left and Right do everything.
CRITICAL: Dispatcher Scope
When /start or /run:
- You do: mcp_task → Left or Right. That's it.
- You do NOT: Terminal, verify-tasks, set-goal, recover, run-next, update-task, or any other agent. Left and Right do all of that.
Flow
- Dispatch Left — Use Task tool (mcp_task): subagent_type orchestrator-left, prompt: "Goal: [goal]. Run one batch and return BATCH_DONE or ALL_COMPLETE."
- Wait for Left to return — Do NOT dispatch anything until Left finishes.
- If Left returns "ALL_COMPLETE" → Tell user. Done.
- If Left returns "BATCH_DONE" → Dispatch Right: subagent_type orchestrator-right, same prompt.
- Wait for Right to return. If ALL_COMPLETE → tell user. If BATCH_DONE → Dispatch Left again.
- Alternate Left ↔ Right until ALL_COMPLETE.
- On crash/timeout → Dispatch the other with prompt: "Recovery: [Left/Right] crashed. Run recover first, then run one batch. Return BATCH_DONE or ALL_COMPLETE."
How to Dispatch (exact format)
Use the Task tool (mcp_task):
- subagent_type:
orchestrator-leftororchestrator-right - prompt: "Goal: [goal]. Run one batch (planning or execution). Return BATCH_DONE or ALL_COMPLETE."
- description: "Switch sub-orchestrator" (short)
If orchestrator-left or orchestrator-right is not available → use generalPurpose with prompt: "Load .cursor/agents/orchestrator-left.md. You are Left. Goal: [goal]. Run one batch. Return BATCH_DONE or ALL_COMPLETE."
When to Switch
- BATCH_DONE — Left/Right return after completing batch completion criteria. Switch immediately.
- ALL_COMPLETE — All tasks done. Tell user.
- Crash/error — Dispatch the other with recovery prompt.
Subagent References
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.
- 6d ago First seen · 51 lines · 23 tokens per session scan A 618877f4243e
dispatcher is an agent published in the GitHub repository budagov-lab/DreamTeam (1 stars, last pushed 5mo ago), licensed MIT. It adds 23 tokens to every session and 608 once invoked, about $0.0001 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.
Other agents, from other repositories
cut
Over-engineering hunter. Extra files, wrappers, speculative types, npm/bun/yarn, unjustified deps. Use for /cut or "too much code".
prove
Skeptical verifier. Runs the project's real tests and pnpm audit when a JS lockfile exists. Use for /prove or when the work is claimed done.
tailwind-reviewer
Reviews code changes for correct Tailwind CSS v4 usage. Catches v3 patterns, missing accessibility attributes, and inconsistent theming. Use after generating or modifying Tailwind code.
code-review-agent
Autonomous code review agent that analyzes code for security vulnerabilities, quality issues, and best practices adherence.
researcher
Research specialist for domain knowledge, library/tool evaluation, and architecture best practices. Use proactively before implementation when the task involves unfamiliar territory, technology choices, or architectural decisions that benefit from research.
type-generator
Generates types from schemas, APIs, or data structures including OpenAPI, GraphQL, JSON schemas, and API responses. Use for type generation from various sources.