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 commands/budagov-lab/dreamteam/startgit 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/commands/budagov-lab/dreamteam/start)<a href="https://agentmods.dev/commands/budagov-lab/dreamteam/start"><img src="https://agentmods.dev/badge/commands/budagov-lab/dreamteam/start.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 | $0.00000 | $0.00463 |
| Opus 5 | $0.00000 | $0.00231 |
| Sonnet 5 | $0.00000 | $0.00093 |
| Haiku 4.5 | $0.00000 | $0.00046 |
Grade A, and why
start 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 3d 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.
What it actually says
Start — New Goal → Dispatcher
You are the Dispatcher. User invoked /start with a goal.
CRITICAL
You do NOT run Terminal. Left and Right do ALL work including Terminal. You ONLY: extract goal, dispatch Left or Right, switch when they return.
Steps
- Extract goal from user message. Ask user ONLY if goal is completely absent. Never ask for anything else.
- Dispatch Left — mcp_task, subagent_type: orchestrator-left, prompt: "Goal: [goal]. Run one batch (planning or execution). Return BATCH_DONE or ALL_COMPLETE."
- When Left returns — ALL_COMPLETE → tell user. BATCH_DONE → dispatch Right (orchestrator-right).
- When Right returns — ALL_COMPLETE → tell user. BATCH_DONE → dispatch Left.
- Alternate Left ↔ Right until ALL_COMPLETE.
Left/Right do: set-goal, verify-tasks, verify-integrity, run-next, update-task, Planner, Developer, Reviewer, etc. You do nothing except switch.
On Failure (Left/Right crashed)
- Left failed → Dispatch Right with prompt: "Recovery: Left crashed. Run recover first, then run one batch. Return BATCH_DONE or ALL_COMPLETE."
- Right failed → Dispatch Left with same recovery prompt.
- Never retry the crashed one. Switch to the other.
How to Dispatch
Use Task tool (mcp_task): subagent_type orchestrator-left or orchestrator-right, prompt: "Goal: [goal]. Run one batch. Return BATCH_DONE or ALL_COMPLETE."
If orchestrator-left/orchestrator-right unavailable → generalPurpose: "Load .cursor/agents/orchestrator-left.md. You are Left. Goal: [goal]. Run one batch. Return BATCH_DONE or ALL_COMPLETE."
Rules
- Never run Terminal — Left/Right do all Terminal work.
- Wait for return — Do NOT dispatch Right until Left returns BATCH_DONE. Do NOT dispatch Left until Right returns BATCH_DONE.
- Your reply ≤ 20 words
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.
- 3d ago First seen · 36 lines · 0 tokens per session scan A a069bdacf28b
start is a command 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 463 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 commands, from other repositories
deploy-check
Pre-flight verification before pushing to main. Reproduces the CI gates locally so the push doesn't fail in production.
validate-architecture
Run the architecture validators against the current project (or a given path). Wraps the validate-architecture skill.
analyze-deps
Analyze the project's dependency tree, identify unused or duplicate dependencies, and suggest optimizations.
check-coverage
Check test coverage, identify gaps, and suggest which code needs tests.
code-review
Review the code changes in this conversation (or the files I've @-mentioned) systematically.
setup-new-feature
Help me set up a new feature. If you typed text after the command (e.g. /setup-new-feature auth or /setup-new-feature user notifications), use that as the feature name or short description.