Agent Patterns
Overview
Agent Patterns defines the coordination protocol for multi-agent sprint execution within the Sprint plugin. It governs how the project architect spawns implementation and testing agents, how agents communicate results via structured reports, and how parallel agents avoid conflicts.
Prerequisites
- Sprint plugin installed and configured (
/plugin install sprint)
- Sprint directory initialized at
.claude/sprint/[N]/
specs.md written with clear scope and testing configuration
- Familiarity with the sprint phase lifecycle (see the
sprint-workflow skill)
Instructions
- Structure every agent spawn using the SPAWN REQUEST format. Include the agent name, the specification file it should read, and any scope constraints:
SPAWN REQUEST
Agent: python-dev
Specs: .claude/sprint/1/backend-specs.md
Contract: .claude/sprint/1/api-contract.md
Scope: Authentication endpoints only
- Ensure each spawned agent receives only the files relevant to its scope. Pass the
api-contract.md as a shared interface so backend and frontend agents stay synchronized.
- Collect structured reports from every agent upon completion. Each report must include: work completed, files modified, tests added, and conformity status against the specification.
- When running agents in parallel, partition work by domain boundary (e.g., backend vs. frontend vs. CI/CD). Never assign overlapping file paths to concurrent agents.
- Feed agent reports back to the project architect for review. The architect decides whether to iterate (re-spawn with narrowed specs) or advance to the next phase.
- For testing agents, pass the UI test report format shown in
${CLAUDE_SKILL_DIR}/references/ui-test-report.md so results follow a consistent schema including test counts, coverage, failures, and console errors.
Output
- SPAWN REQUEST blocks consumed by the sprint orchestrator to launch agents
- Structured agent reports containing: summary, files changed, test results, and conformity status
- UI test reports with pass/fail counts, coverage details, failure descriptions, and console error logs
- Updated
status.md reflecting completed and remaining work after each iteration
Error Handling
| Error |
Cause |
Solution |
| Agent receives wrong specification file |
Incorrect path in SPAWN REQUEST |
Verify the sprint directory number and file name before spawning |
| Overlapping file modifications from parallel agents |
Scope boundaries not clearly defined |
Partition work by domain; assign distinct directories to each agent |
| Agent report missing required fields |
Agent instructions lack report format |
Include the structured report template in the agent prompt |
| Infinite iteration loop |
Specs never fully satisfied |
Check status.md for blocking issues; the orchestrator pauses after 5 iterations |
| Agent not found |
Misspelled agent name in SPAWN REQUEST |
Verify agent markdown files exist in agents/ directory |
Examples
Spawning parallel implementation agents:
SPAWN REQUEST
Agent: python-dev
Specs: .claude/sprint/1/backend-specs.md
Contract: .claude/sprint/1/api-contract.md
SPAWN REQUEST
Agent: nextjs-dev
Specs: .claude/sprint/1/frontend-specs.md
Contract: .claude/sprint/1/api-contract.md
Both agents share the same api-contract.md to ensure API compatibility.
Structured agent report format:
AGENT REPORT
Agent: python-dev
Status: COMPLETE
Files Modified: src/auth/routes.py, src/auth/models.py, tests/test_auth.py
Tests: 12 passed, 0 failed
Conformity: All backend-specs requirements implemented
Notes: JWT token expiry set to 24h per spec
Testing agent coordination:
SPAWN REQUEST
Agent: qa-test-agent
Specs: .claude/sprint/1/specs.md
Run After: python-dev, nextjs-dev
SPAWN REQUEST
Agent: ui-test-agent
Specs: .claude/sprint/1/specs.md
Run After: qa-test-agent
Resources
${CLAUDE_SKILL_DIR}/references/ui-test-report.md -- Structured UI test report format with coverage and failure tracking
- Sprint workflow skill for phase lifecycle context
- API contract skill for shared interface design
- Sprint plugin README for agent architecture overview
1---
2name: agent-patterns
3description: |
4 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.
5allowed-tools: Read
6version: 1.0.0
7author: Damien Laine <damien.laine@gmail.com>
8license: MIT
9compatible-with: claude-code, codex, openclaw
10metadata:
11 source: https://skillmd.com/skills/micsapp/agent-patterns
12---
13
14# Agent Patterns
15
16## Overview
17
18Agent Patterns defines the coordination protocol for multi-agent sprint execution within the Sprint plugin. It governs how the project architect spawns implementation and testing agents, how agents communicate results via structured reports, and how parallel agents avoid conflicts.
19
20## Prerequisites
21
22- Sprint plugin installed and configured (`/plugin install sprint`)
23- Sprint directory initialized at `.claude/sprint/[N]/`
24- `specs.md` written with clear scope and testing configuration
25- Familiarity with the sprint phase lifecycle (see the `sprint-workflow` skill)
26
27## Instructions
28
291. Structure every agent spawn using the SPAWN REQUEST format. Include the agent name, the specification file it should read, and any scope constraints:
30 ```
31 SPAWN REQUEST
32 Agent: python-dev
33 Specs: .claude/sprint/1/backend-specs.md
34 Contract: .claude/sprint/1/api-contract.md
35 Scope: Authentication endpoints only
36 ```
372. Ensure each spawned agent receives only the files relevant to its scope. Pass the `api-contract.md` as a shared interface so backend and frontend agents stay synchronized.
383. Collect structured reports from every agent upon completion. Each report must include: work completed, files modified, tests added, and conformity status against the specification.
394. When running agents in parallel, partition work by domain boundary (e.g., backend vs. frontend vs. CI/CD). Never assign overlapping file paths to concurrent agents.
405. Feed agent reports back to the project architect for review. The architect decides whether to iterate (re-spawn with narrowed specs) or advance to the next phase.
416. For testing agents, pass the UI test report format shown in `${CLAUDE_SKILL_DIR}/references/ui-test-report.md` so results follow a consistent schema including test counts, coverage, failures, and console errors.
42
43## Output
44
45- SPAWN REQUEST blocks consumed by the sprint orchestrator to launch agents
46- Structured agent reports containing: summary, files changed, test results, and conformity status
47- UI test reports with pass/fail counts, coverage details, failure descriptions, and console error logs
48- Updated `status.md` reflecting completed and remaining work after each iteration
49
50## Error Handling
51
52| Error | Cause | Solution |
53|-------|-------|----------|
54| Agent receives wrong specification file | Incorrect path in SPAWN REQUEST | Verify the sprint directory number and file name before spawning |
55| Overlapping file modifications from parallel agents | Scope boundaries not clearly defined | Partition work by domain; assign distinct directories to each agent |
56| Agent report missing required fields | Agent instructions lack report format | Include the structured report template in the agent prompt |
57| Infinite iteration loop | Specs never fully satisfied | Check `status.md` for blocking issues; the orchestrator pauses after 5 iterations |
58| Agent not found | Misspelled agent name in SPAWN REQUEST | Verify agent markdown files exist in `agents/` directory |
59
60## Examples
61
62**Spawning parallel implementation agents:**
63```
64SPAWN REQUEST
65Agent: python-dev
66Specs: .claude/sprint/1/backend-specs.md
67Contract: .claude/sprint/1/api-contract.md
68
69SPAWN REQUEST
70Agent: nextjs-dev
71Specs: .claude/sprint/1/frontend-specs.md
72Contract: .claude/sprint/1/api-contract.md
73```
74Both agents share the same `api-contract.md` to ensure API compatibility.
75
76**Structured agent report format:**
77```
78AGENT REPORT
79Agent: python-dev
80Status: COMPLETE
81Files Modified: src/auth/routes.py, src/auth/models.py, tests/test_auth.py
82Tests: 12 passed, 0 failed
83Conformity: All backend-specs requirements implemented
84Notes: JWT token expiry set to 24h per spec
85```
86
87**Testing agent coordination:**
88```
89SPAWN REQUEST
90Agent: qa-test-agent
91Specs: .claude/sprint/1/specs.md
92Run After: python-dev, nextjs-dev
93
94SPAWN REQUEST
95Agent: ui-test-agent
96Specs: .claude/sprint/1/specs.md
97Run After: qa-test-agent
98```
99
100## Resources
101
102- `${CLAUDE_SKILL_DIR}/references/ui-test-report.md` -- Structured UI test report format with coverage and failure tracking
103- Sprint workflow skill for phase lifecycle context
104- API contract skill for shared interface design
105- Sprint plugin README for agent architecture overview