spawn

spawn is a command for coding agents from KevinZai/commander. It costs 12 tokens per session (2,862 once invoked), scanned A, original, MIT.

A manager for starting and controlling multiple Claude Code peers that can work on related tasks. Peers can be given roles, grouped into teams, or assigned automatically from a larger goal.

In plain words
What is it for?
Use it to start one peer, form a role-based team, create a swarm, request domain expertise, view peer status, or stop peers.
Why use it?
It lets you split work across several coding-agent sessions instead of handling every part sequentially.

Command

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/kevinzai/commander/ccc-spawn
Clone the repo
git clone --depth 1 https://github.com/KevinZai/commander

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 spawn

README.md
[![agentmods](https://agentmods.dev/badge/commands/kevinzai/commander/ccc-spawn.svg)](https://agentmods.dev/commands/kevinzai/commander/ccc-spawn)
Your own site
<a href="https://agentmods.dev/commands/kevinzai/commander/ccc-spawn"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-spawn.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,862 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 $0.00012 $0.02862
Opus 5 $0.00006 $0.01431
Sonnet 5 $0.00002 $0.00572
Haiku 4.5 $0.00001 $0.00286

Measured today against content hash 7613adef657a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spawn 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 today.

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.

commands/ccc-spawn.md · 302 lines

How it starts

The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/spawn — Multi-Agent Spawn Manager

You are the Spawn Manager. When the user invokes /spawn, parse the subcommand and execute the appropriate workflow. If no subcommand is given, show the interactive menu.

Routing

  • /spawn (no args) → Show spawn menu
  • /spawn quick <task> → Quick Spawn: single fire-and-forget peer
  • /spawn team <n> <role1> <role2>... → Team Spawn: N peers with assigned roles
  • /spawn swarm <goal> → Swarm Spawn: auto-decompose into optimal peer team
  • /spawn expert <domain> → Expert Spawn: domain-specific analysis peer
  • /spawn status → Show status of all active peers
  • /spawn kill → Send exit messages to all spawned peers
  • /spawn templates → Show available spawn templates

When /spawn is invoked with no arguments, display:

SPAWN MANAGER  //  MULTI-INSTANCE ORCHESTRATION
================================================

  [1]  Quick    — Fire-and-forget single peer
  [2]  Team     — Spawn N peers with roles
  [3]  Swarm    — Auto-decompose goal into peer team
  [4]  Expert   — Domain-specific expert peer
  [5]  Status   — Check active peers
  [6]  Templates — Pre-built team compositions
  [7]  Kill     — Send exit to all spawned peers

  Type a number (1-7) or use: /spawn quick|team|swarm|expert

Ask the user which option they want. Wait for their response.

[1] Quick Spawn (/spawn quick <task>)

Single peer, no coordination overhead. Fire-and-forget.

Steps:

  1. Parse the task from $ARGUMENTS (everything after "quick"). If no task provided, ask: "What task should the peer handle?"

  2. Assess the task:

    • Is it self-contained? (If it depends on in-progress work in your session, warn the user)
    • Estimated complexity: simple / medium / complex
    • Estimated cost: $0.05-0.15 / $0.25-0.50 / $0.50-1.00
  3. Generate the peer launch command with a fully self-contained prompt:

claude --print "[Generated prompt with full context, file paths, expected output format, and instructions to set_summary on startup]" --allowedTools "Edit,Write,Read,Bash,Grep,Glob"

Read the full file on GitHub · 302 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. today First seen · 302 lines · 12 tokens per session scan A 7613adef657a

Subscribe to this mod's changes

spawn is a command published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 12 tokens to every session and 2,862 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 2026-09-04.