do-teams

do-teams is a command for Claude Code from jayminwest/kotadb. It costs 8 tokens per session (4,120 once invoked), scanned A, original, MIT.

A command for splitting a large task among several coding agents working as one team. The lead agent coordinates the work and combines the results.

In plain words
What is it for?
Use it for parallel research, implementation, or review tasks that can be assigned to separate agents.
Why use it?
It reduces the time spent handling independent parts of a task one after another. Team rules help avoid conflicting changes and unclear ownership.

Command for Claude Code

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.

agentmods
npx agentmods add commands/jayminwest/kotadb/do-teams
Clone the repo
git clone --depth 1 https://github.com/jayminwest/kotadb

Made for: Claude Code.

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 do-teams

README.md
[![agentmods](https://agentmods.dev/badge/commands/jayminwest/kotadb/do-teams.svg)](https://agentmods.dev/commands/jayminwest/kotadb/do-teams)
Your own site
<a href="https://agentmods.dev/commands/jayminwest/kotadb/do-teams"><img src="https://agentmods.dev/badge/commands/jayminwest/kotadb/do-teams.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,120 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found 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 $0.00008 $0.04120
Opus 5 $0.00004 $0.02060
Sonnet 5 $0.00002 $0.00824
Haiku 4.5 $0.00001 $0.00412

Measured 5d ago against content hash 0b70a246e300, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

do-teams 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 5d 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.

.claude/commands/do-teams.md · 588 lines

How it starts

The opening of the file, as written. The whole thing — 588 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/do-teams - Team Orchestration

Parallel execution using agent teams. You orchestrate the team: spawn teammates, coordinate their work, and synthesize results. All teammates report directly to you.

Your Role

You are the team lead. Your job:

  1. Create a team
  2. Spawn ALL teammates directly (flat structure — no intermediate leads)
  3. Receive their results (automatically delivered)
  4. Synthesize and report

You do NOT do the work yourself — teammates do. You coordinate.

Official API Constraints

These are hard constraints of the teams system:

Constraint Detail
No nested teams Teammates cannot spawn sub-teams or other teammates
One team per session Only one team can be active at a time
No session resumption Cannot resume a session with in-process teammates
Lead is fixed You (the session creator) are lead for the team's lifetime
Permissions inherited All teammates inherit your permission settings at spawn
File locking Task claiming uses file locking to prevent race conditions

Workflow

Step 1: Create Team

Teammate(
  operation: "spawnTeam",
  team_name: "{domain}-team",
  description: "Working on {requirement summary}"
)

This makes you the team lead. You'll receive messages from teammates automatically.

Step 2: Identify Domain and Load Expertise

Classify the requirement to identify the target domain(s):

Domain Keywords Location
database schema, migration, SQLite, FTS5, query, index, table app/src/db/
api endpoint, route, MCP tool, HTTP, server, OpenAPI app/src/api/, app/src/mcp/
testing test, antimocking, Bun test, SQLite test app/tests/, tests/
indexer AST, parser, symbol, reference, code analysis app/src/indexer/
github issue, PR, branch, commit, gh CLI .github/
claude-config command, hook, settings, .claude .claude/commands/, .claude/hooks/
agent-authoring agent, expert domain, tool selection, registry .claude/agents/
automation ADW, automated workflow, script, CI/CD .claude/commands/automation/
documentation docs, README, API reference, architecture docs web/docs/content/
web homepage, blog, CSS, design system, Liquid Glass, kotadb.io, marketing site web/

Read the full file on GitHub · 588 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. 5d ago First seen · 588 lines · 8 tokens per session scan A 0b70a246e300

Subscribe to this mod's changes

do-teams is a command published in the GitHub repository jayminwest/kotadb (102 stars, last pushed 4mo ago), licensed MIT. It adds 8 tokens to every session and 4,120 once invoked, about $0.0000 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 2026-08-30.