agent-patterns

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.

Agent Patterns

Coordinate multi-agent workflows using structured communication protocols. Covers spawn requests, status reports, and inter-agent messaging within the sprint system.

Spawn Request Format

When launching a parallel agent, use this structure:

## SPAWN REQUEST
- **Agent ID**: <unique-id>
- **Role**: <role-name>
- **Task**: <one-line description>
- **Context**: <relevant files or state>
- **Expected Output**: <deliverable format>
- **Timeout**: <max duration>

Agent Report Format

Each agent reports back using:

## AGENT REPORT
- **Agent ID**: <id>
- **Status**: completed | failed | blocked
- **Summary**: <one-line result>
- **Output**: <deliverable or file path>
- **Issues**: <blockers or warnings, if any>
- **Duration**: <time taken>

Coordination Workflow

Define tasks — break work into independent units suitable for parallel execution
Spawn agents — send SPAWN REQUEST for each task with clear context
Monitor status — track agent reports as they complete
Handle failures — retry failed agents or reassign blocked tasks
Merge results — combine agent outputs into final deliverable, resolving conflicts

Communication Rules

Agents communicate through structured reports, not free-form text
Each message includes agent ID for traceability
Blocked agents must report immediately rather than waiting silently
The coordinator agent reviews all reports before merging

Error Handling

See references/errors.md for common failure modes and recovery steps.

Examples

See references/examples.md for complete spawn-and-report workflows.