agent-spawn-example

A document showing how a workflow can ask Claude Code to start a specialized coding agent with the Task tool.

In plain words
What is it for?
Use it as a reference when designing workflows that spawn agents for tasks such as writing feature specifications.
Why use it?
It gives workflow authors a concrete pattern for delegating focused work to another agent with its own instructions and context.

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/keychain-io/trustable-ai/agent-spawn-example
Clone the repo
git clone --depth 1 https://github.com/keychain-io/trustable-ai

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 865 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 $0.00865
Opus 5 $0.00000 $0.00432
Sonnet 5 $0.00000 $0.00173
Haiku 4.5 $0.00000 $0.00086

Measured yesterday against content hash ab0ea5ef067d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-spawn-example 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-example.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Example: Agent Spawning Pattern

This document demonstrates how workflows should instruct Claude Code to spawn specialized agents using the Task tool.


Step X: Create Specification (Spawn Senior Engineer)

YOU MUST USE THE TASK TOOL FOR THIS STEP.

Do not perform this work yourself. Instead, spawn a specialized agent:

Task Tool Parameters

Tool: Task
Parameters:
  subagent_type: "general-purpose"
  model: "opus"
  description: "Create feature specification"
  prompt: [SEE BELOW]

Prompt to Send to Agent

Copy the contents of .claude/agents/senior-engineer.md and append this task:


YOUR TASK

Create a detailed specification for Feature {feature_id}.

Input Materials:

  • Epic: {epic_title}
  • Feature: {feature_title}
  • Acceptance Criteria: {acceptance_criteria}

Required Output:

  1. API Contract with:
    • Function signatures with types
    • Input constraints
    • Output guarantees
    • Error conditions
  2. Test scenarios covering:
    • Happy path
    • Edge cases
    • Error handling
  3. Implementation notes

IMPORTANT: You have a fresh context dedicated to this task. Focus entirely on creating a precise, unambiguous specification.


After the agent completes: Save the output to docs/specifications/.


Step Y: Spec-Driven Testing (Spawn QA Tester - NO CODE ACCESS)

YOU MUST USE THE TASK TOOL FOR THIS STEP.

CRITICAL - Information Asymmetry: This agent must NOT see the implementation.

Task Tool Parameters

Tool: Task
Parameters:
  subagent_type: "general-purpose"
  model: "sonnet"
  description: "Generate spec-driven tests"
  prompt: [SEE BELOW - SPEC ONLY, NO CODE]

Prompt to Send to Agent

Copy the contents of .claude/agents/tester.md and append:


YOUR TASK

Generate comprehensive tests from this specification ONLY.

Specification: {specification_content}

API Contract: {api_contract}

YOU DO NOT HAVE ACCESS TO:

  • The implementation code
  • The developer's tests
  • Any hint about how the code was written

Read the full file on GitHub · 170 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. yesterday First seen · 170 lines · 0 tokens per session scan A ab0ea5ef067d

Subscribe to this mod's changes

agent-spawn-example is a command published in the GitHub repository keychain-io/trustable-ai (2 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 865 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.