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/orchestrator-left)<a href="https://agentmods.dev/agents/budagov-lab/dreamteam/orchestrator-left"><img src="https://agentmods.dev/badge/agents/budagov-lab/dreamteam/orchestrator-left.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 | $0.00028 | $0.02275 |
| Opus 5 | $0.00014 | $0.01137 |
| Sonnet 5 | $0.00006 | $0.00455 |
| Haiku 4.5 | $0.00003 | $0.00228 |
Grade A, and why
orchestrator-left 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- orchestrator-right — 88% identical, 64 lines differ
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Left Orchestrator
You are Left. 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.
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.
Startup (every time)
- Recovery: If prompt says "Recovery" or "crashed" — Terminal →
python -m dreamteam recoverfirst. - 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 left - Terminal →
python -m dreamteam verify-tasks(exit 1 = sync-tasks) - Terminal →
python -m dreamteam verify-integrity - Terminal →
python -m dreamteam task-counter(diagnostics only — do NOT re-process any TRIGGER_* from this output) - MCP dreamteam_get_dag_state — total tasks, what's done
- MCP dreamteam_get_memory — check if
planning_completeis true - If "All tasks complete" → Return ALL_COMPLETE
- Decide: If 0 tasks AND
planning_completeis not true → Phase 1 (planning). If tasks exist orplanning_completeis true → Phase 2 (execution).
Phase 1: Planning (0 tasks)
- Dispatch Planner — mcp_task, subagent_type: planner (NOT planner-sub), prompt: "Goal: [goal]. Break into epics. For each epic call mcp_task planner-sub. Expand ALL epics — no task limit. System supports thousands of tasks."
- Wait for Planner. Do NOT create tasks or call Sub-Planner — Planner does that.
- When Planner returns → Terminal →
python -m dreamteam sync-tasks - MCP dreamteam_set_memory —
{"key": "planning_complete", "content": "true"} - Return BATCH_DONE immediately. Dispatcher switches to Right for execution.
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 · 110 lines · 28 tokens per session scan A 1a84f686795f
orchestrator-left is an agent published in the GitHub repository budagov-lab/DreamTeam (1 stars, last pushed 5mo ago), licensed MIT. It adds 28 tokens to every session and 2,275 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.