home / skills / jeremylongshore / claude-code-plugins-plus-skills / agent-patterns

agent-patterns skill

safe

/plugins/community/sprint/skills/agent-patterns

This skill assists coordinating agents and generating structured spawn request outputs and reports to streamline sprint collaboration.

npx playbooks add skill jeremylongshore/claude-code-plugins-plus-skills --skill agent-patterns

Review the files below or copy the command above to add this skill to your agents.

Files (4)

SKILL.md

1.1 KB

---
name: agent-patterns
description: |
  Execute this skill should be used when the user asks about "SPAWN REQUEST format", "agent reports", "agent coordination", "parallel agents", "report format", "agent communication", or needs to understand how agents coordinate within the sprint system. Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.
allowed-tools: Read
version: 1.0.0
author: Damien Laine <[email protected]>
license: MIT
---

# Agent Patterns

## Overview

This skill provides automated assistance for the described functionality.

## Prerequisites

- Appropriate file access permissions
- Required dependencies installed

## Instructions

1. Invoke this skill when the trigger conditions are met
2. Provide necessary context and parameters
3. Review the generated output
4. Apply modifications as needed

## Output

The skill produces structured output relevant to the task.

## Error Handling

See `{baseDir}/references/errors.md` for comprehensive error handling.

## Examples

See `{baseDir}/references/examples.md` for detailed examples.

## Resources

- Project documentation
- Related skills and commands

Overview

This skill helps you understand and apply agent coordination patterns used in the sprint system, including the SPAWN REQUEST format and standardized agent reports. It clarifies how agents communicate, hand off work, and run in parallel to achieve coordinated outcomes. Use it to produce well-formed requests, summaries, and coordination artifacts for multi-agent workflows.

How this skill works

The skill inspects incoming coordination triggers and maps them to the SPAWN REQUEST schema, populating required fields and validation checks. It generates agent reports and communication templates, advises on parallel execution constraints, and emits structured outputs that can be consumed by other agents or orchestration layers. It also highlights common error cases and suggests remediation steps.

When to use it

When drafting or validating SPAWN REQUEST messages for new agents
When designing agent reports or post-task summaries for sprint reviews
When coordinating multiple agents to run tasks in parallel or in sequence
When troubleshooting communication failures between agents
When you need a canonical format for agent handoffs and status updates

Best practices

Always include clear objectives, input artifacts, and success criteria in each SPAWN REQUEST
Keep agent reports concise: outcome, actions taken, next steps, and confidence level
Design idempotent tasks so parallel runs are safe to retry
Use explicit timeouts and resource limits to avoid runaway parallel agents
Include correlation IDs in every message to trace workflows across agents

Example use cases

Create a SPAWN REQUEST to run feature tests across three parallel test agents and collect consolidated results
Generate a standardized agent report after an automated code review to feed sprint retrospective notes
Coordinate a handoff: data-extraction agent produces artifacts, then spawner issues requests to analysis agents
Validate a proposed multi-agent workflow and flag missing fields or conflicting resource constraints
Produce a summary report that aggregates parallel-agent outputs and highlights discrepancies

FAQ

What is the SPAWN REQUEST format?

A SPAWN REQUEST is a structured message that specifies task objectives, required inputs, agent capabilities needed, success criteria, and operational constraints such as timeouts and resource limits.

How do I handle conflicting parallel outputs?

Include reconciliation rules in the request: prefer latest timestamp, majority vote, or a validator agent. Also surface conflicts in the aggregated report for human review.