spawn

spawn is a command for Claude Code from ngocsangyem/MeowKit. It costs 0 tokens per session (587 once invoked), scanned A, original, MIT.

A command for launching specialist coding agents in separate workspaces. Each agent receives a defined task and a list of files it is allowed to change.

In plain words
What is it for?
Use it to assign backend, frontend, testing, or documentation tasks in parallel, then review and merge their results.
Why use it?
It lets several agents work at the same time while reducing conflicting edits and keeping ownership clear.

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/ngocsangyem/meowkit/spawn
Clone the repo
git clone --depth 1 https://github.com/ngocsangyem/MeowKit

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 spawn

README.md
[![agentmods](https://agentmods.dev/badge/commands/ngocsangyem/meowkit/spawn.svg)](https://agentmods.dev/commands/ngocsangyem/meowkit/spawn)
Your own site
<a href="https://agentmods.dev/commands/ngocsangyem/meowkit/spawn"><img src="https://agentmods.dev/badge/commands/ngocsangyem/meowkit/spawn.svg" alt="Measured on agentmods" height="20"></a>
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 587 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 $0.00587
Opus 5 $0.00000 $0.00293
Sonnet 5 $0.00000 $0.00117
Haiku 4.5 $0.00000 $0.00059

Measured today against content hash 41ec260b2d62, 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.

.claude/commands/mk/spawn.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/spawn — Parallel Agent Sessions

Usage

/spawn [agent-role] [task]

Behavior

Launch a specialist agent in an isolated workspace to handle a specific task in parallel. Based on the Conductor pattern.

Execution Steps

  1. Validate prerequisites.

    • An approved plan must exist (agents inherit the plan).
    • The task must be scoped to non-overlapping files (no two agents work on the same file).
    • Ownership boundaries from team-protocol are enforced.
  2. Launch specialist agent. Create an isolated session with:

    • The agent role (e.g., backend, frontend, tester, documenter)
    • The specific task to complete
    • The approved plan for context
    • File ownership boundaries (which files this agent may touch)
  3. Agent execution. The spawned agent:

    • Works within its assigned file boundaries
    • Follows the same rules (TDD, security, naming conventions)
    • Cannot modify files outside its ownership boundary
    • Produces output that will be reviewed before merging
  4. Review results. When the spawned agent completes:

    • Review its output against the plan
    • Check for conflicts with other agents' work
    • Merge results back into the main workspace

Common Patterns

# Backend + frontend in parallel
/spawn backend "Implement user avatar API endpoint"
/spawn frontend "Build avatar upload component"

# Tests + docs in parallel
/spawn tester "Write integration tests for avatar feature"
/spawn documenter "Update API docs for avatar endpoint"

Rules

  • Spawned agents inherit the approved plan — they do not create their own plans.
  • Each agent works on non-overlapping files. If two agents need the same file, one must wait.
  • Ownership boundaries from team-protocol are strictly enforced.
  • All spawned agent output is reviewed before merging back to the main workspace.
  • If an agent encounters an issue outside its boundary, it flags it and stops (does not fix it).
  • TDD mode inheritance: spawned agents read the same .claude/session-state/tdd-mode sentinel as the parent. If the parent invocation set TDD mode (via --tdd), child spawns observe the same mode automatically — no env var propagation required. Filesystem state persists across Bash tool calls and subagent contexts.

Read the full file on GitHub · 70 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 · 70 lines · 0 tokens per session scan A 41ec260b2d62

Subscribe to this mod's changes

spawn is a command published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 587 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 2026-09-03.