coordination:agent-spawn

coordination:agent-spawn is a command for Claude Code from monoes/monomind. It costs 20 tokens per session (535 once invoked), scanned A, original, Apache-2.0.

A command that records an agent in an agent store without starting it. You can specify its role, name, task, model provider, model, timeout, and tool settings.

In plain words
What is it for?
Use it to register coder, researcher, analyst, tester, coordinator, or architect agents for later execution.
Why use it?
It separates defining an agent from running one, so you can set up a team of agents before deciding how or when they should execute work.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code.

Good fit Use it to register coder, researcher, analyst, tester, coordinator, or architect agents for later execution.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/monoes/monomind/agent-spawn
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.

Clone the repo
git clone --depth 1 https://github.com/monoes/monomind

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 coordination:agent-spawn

README.md
[![agentmods](https://agentmods.dev/badge/commands/monoes/monomind/agent-spawn/github.svg)](https://agentmods.dev/commands/monoes/monomind/agent-spawn)
Your own site
<a href="https://agentmods.dev/commands/monoes/monomind/agent-spawn"><img src="https://agentmods.dev/badge/commands/monoes/monomind/agent-spawn/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for coordination:agent-spawn

Your own site · 80×15
<a href="https://agentmods.dev/commands/monoes/monomind/agent-spawn"><img src="https://agentmods.dev/badge/commands/monoes/monomind/agent-spawn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 535 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00020 $0.00535
Opus 5.5 $0.00008 $0.00214
Sonnet 5.5 $0.00004 $0.00107
Haiku 4.5 $0.00002 $0.00053

Measured yesterday against content hash 76d60bb2d7d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

coordination:agent-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 yesterday.

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/coordination/agent-spawn.md · 69 lines

What it actually says

agent-spawn

Record a new agent in the agent store. No process is started: to run agent work, spawn it with Claude Code's Task tool, run one turn with monomind agent exec, or run an org with monomind org run.

Usage

npx monomind agent spawn [options]

Options

  • --type, -t <type> - Agent type: coder, researcher, analyst, tester, coordinator, architect
  • --name, -n <name> - Custom agent name/identifier
  • --task <description> - Initial task for the agent
  • --provider <name> - Provider: anthropic, openrouter, ollama
  • --model <id> - Specific model to use
  • --timeout <seconds> - Agent timeout in seconds
  • --auto-tools - Enable automatic tool selection

Examples

# Spawn a coder agent
npx monomind agent spawn --type coder --name bot-1

# Spawn researcher with an initial task
npx monomind agent spawn --type researcher --task "Research React 19 concurrent features"

# Spawn with specific provider and model
npx monomind agent spawn --type architect --provider anthropic --model claude-sonnet-5

# Spawn with auto tools and timeout
npx monomind agent spawn --type coder --auto-tools --timeout 300

Agent Types

Type Best For
coder Implementation, code generation
researcher Documentation, exploration, analysis
analyst Data-driven decisions, performance review
tester Test creation, quality assurance
coordinator Task management, progress tracking
architect System design, architecture decisions

Integration with Claude Code

mcp__monomind__agent_spawn({
  type: "coder",
  name: "API Builder",
  capabilities: ["typescript", "rest-api"]
})

Note: This tool provides coordination and metadata — Claude Code performs all actual implementation using its native tools.

See Also

  • agent list — list all active agents (monomind agent list)
  • agent status — check agent status (monomind agent status --id <id>)
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. yesterday First seen · 69 lines · 20 tokens per session scan A 76d60bb2d7d4

Subscribe to this mod's changes

coordination:agent-spawn is a command published in the GitHub repository monoes/monomind (23 stars, last pushed yesterday), licensed Apache-2.0. It adds 20 tokens to every session and 535 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-26.