agent-spawning

A guide to starting specialized Claude Code agents with the Task tool. It describes agent roles such as researcher, coder, and tester, plus optional coordination through Claude Flow.

In plain words
What is it for?
Use it to assign research, implementation, and testing tasks to separate agents, and optionally coordinate them with Claude Flow.
Why use it?
It gives multi-agent work a clear execution pattern and encourages starting independent agents together. This makes responsibilities easier to divide and track.

Agent 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 agents/ruvnet/sublinear-time-solver/agent-spawning
Clone the repo
git clone --depth 1 https://github.com/ruvnet/sublinear-time-solver

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 175 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 $0.00175
Opus 5 $0.00000 $0.00088
Sonnet 5 $0.00000 $0.00035
Haiku 4.5 $0.00000 $0.00017

Measured yesterday against content hash 74bfe922137a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-spawning 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.

Origin

Copies of this mod

5 near-identical copies found in the catalogue:

.claude/commands/agents/agent-spawning.md · 29 lines

What it actually says

agent-spawning

Guide to spawning agents with Claude Code's Task tool.

Using Claude Code's Task Tool

CRITICAL: Always use Claude Code's Task tool for actual agent execution:

// Spawn ALL agents in ONE message
Task("Researcher", "Analyze requirements...", "researcher")
Task("Coder", "Implement features...", "coder")
Task("Tester", "Create tests...", "tester")

MCP Coordination Setup (Optional)

MCP tools are ONLY for coordination:

mcp__claude-flow__swarm_init { topology: "mesh" }
mcp__claude-flow__agent_spawn { type: "researcher" }

Best Practices

  1. Always spawn agents concurrently
  2. Use Task tool for execution
  3. MCP only for coordination
  4. Batch all operations
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 · 29 lines · 0 tokens per session scan A 74bfe922137a

Subscribe to this mod's changes

agent-spawning is an agent published in the GitHub repository ruvnet/sublinear-time-solver (89 stars, last pushed 29d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 175 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 2026-08-30.