Problem or Need
The agent-creator agent currently has 3 examples in its description, but all demonstrate reactive triggering patterns where the user explicitly asks to create an agent. Per Claude Code subagent best practices and official documentation, agents should also demonstrate proactive triggering to show Claude when to automatically invoke them.
Current examples (all reactive):
- "Create an agent that reviews code for quality issues"
- "I need an agent that generates unit tests for my code"
- "Add an agent to my plugin that validates configurations"
Proposed Solution
Add a 4th example demonstrating proactive triggering, such as:
<example>
Context: User describes needing autonomous functionality while discussing plugin development
user: "My plugin needs something to automatically review code after I write it"
assistant: "I'll use the agent-creator agent to generate a code review agent for your plugin."
<commentary>
User describes agent-like functionality need without explicitly requesting agent creation, proactively trigger agent-creator.
</commentary>
</example>
This shows Claude recognizing implicit agent needs rather than waiting for explicit "create an agent" requests.
Which component would this affect?
Agent
Specific Component
plugins/plugin-dev/agents/agent-creator.md
Alternatives Considered
- Could add multiple proactive examples, but one well-crafted example should suffice
- Could modify existing examples to be proactive, but keeping reactive examples is valuable for explicit requests
Additional Context
Found during comprehensive subagent review against:
- Official Claude Code docs (sub-agents.md)
- agent-development skill best practices
The official docs specifically mention: "To encourage more proactive subagent use, include phrases like 'use PROACTIVELY' or 'MUST BE USED' in your description field."
Measurements:
- Current examples: 3
- Recommended: 2-4 (meeting minimum but all same pattern)
- File: 182 lines, 1,007 words, 7,479 chars
How important is this feature to you?
High - Would significantly improve my workflow
Problem or Need
The
agent-creatoragent currently has 3 examples in its description, but all demonstrate reactive triggering patterns where the user explicitly asks to create an agent. Per Claude Code subagent best practices and official documentation, agents should also demonstrate proactive triggering to show Claude when to automatically invoke them.Current examples (all reactive):
Proposed Solution
Add a 4th example demonstrating proactive triggering, such as:
This shows Claude recognizing implicit agent needs rather than waiting for explicit "create an agent" requests.
Which component would this affect?
Agent
Specific Component
plugins/plugin-dev/agents/agent-creator.mdAlternatives Considered
Additional Context
Found during comprehensive subagent review against:
The official docs specifically mention: "To encourage more proactive subagent use, include phrases like 'use PROACTIVELY' or 'MUST BE USED' in your description field."
Measurements:
How important is this feature to you?
High - Would significantly improve my workflow