spawn

A command that starts another coding agent in its own Git worktree, which is a separate working copy and branch of a repository. The new agent runs as an independent Claude Code session.

In plain words
What is it for?
Use it to delegate a named task, start an interactive agent session, and receive the separate worktree path and branch name.
Why use it?
It lets another agent work on a task without mixing its files or unfinished changes into the current working copy.

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/cdeust/ai-architect-mcp-codebase/spawn
Clone the repo
git clone --depth 1 https://github.com/cdeust/ai-architect-mcp-codebase

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 146 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 $0.00000 $0.00146
Opus 5 $0.00000 $0.00073
Sonnet 5 $0.00000 $0.00029
Haiku 4.5 $0.00000 $0.00015

Measured yesterday against content hash 48058a5a3a07, 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 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/agent/spawn.md · 19 lines

What it actually says

Spawn Agent in Worktree

Spawn an agent as a standalone Claude Code session in an isolated git worktree.

Instructions

  1. Parse arguments: the first word is the agent name, the rest is the task description. Example: /agent-spawn engineer Fix the auth bug in login.py

  2. Validate the agent exists by checking agents/<name>.md or agents/genius/<name>.md.

  3. Run: scripts/spawn-agent.sh <agent-name> "<task>"

  4. Report the worktree path and branch name to the user.

  5. If no task is provided, spawn in interactive REPL mode (no -p flag).

$ARGUMENTS

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 · 19 lines · 0 tokens per session scan A 48058a5a3a07

Subscribe to this mod's changes

spawn is a command published in the GitHub repository cdeust/ai-architect-mcp-codebase (4 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 146 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.