The prompt-engineer agent now explicitly shows the complete prompt text
instead of just describing it. Changes include:
- Added mandatory instruction to always display prompts
- Created required output format with prompt section
- Updated deliverables to prioritize showing the actual prompt
- Added example demonstrating proper output format
- Included completion checklist to ensure prompts are displayed
This ensures users get the actual prompts they can use immediately.
Implements claude-code v1.0.64's model customization feature by adding
model specifications to all 46 subagents based on task complexity:
- Claude Haiku 3.5 (8 agents): Simple tasks like data analysis, documentation
- Claude Sonnet 4 (26 agents): Development, engineering, and standard tasks
- Claude Opus 4 (11 agents): Complex tasks requiring maximum capability
This task-based model tiering ensures cost-effective AI usage while
maintaining quality for complex tasks.
Updates:
- Added model field to YAML frontmatter for all agent files
- Updated README with comprehensive model assignments
- Added model configuration documentation
- Added business-analyst for KPIs, metrics, and growth projections
- Added content-marketer for SEO content and marketing campaigns
- Added sales-automator for cold outreach and proposal automation
- Added customer-support for FAQ, tickets, and support documentation
- Added risk-manager for portfolio risk and hedging strategies
- Added search-specialist for advanced web research and synthesis
Updated README:
- Increased count from 37 to 43 subagents
- Created new Business & Marketing section
- Added usage examples and workflows
- Updated guidance sections
- Added link to Claude Code Commands collection (52 slash commands)
- Highlighted integration between subagents and pre-built workflows
- Added Advanced Workflows section with slash command examples
- Shows how commands leverage subagents for complex orchestrations
- Added mlops-engineer to Data & AI section
- Updated count from 36 to 37 subagents
- Added to usage examples and workflow patterns
- Added to Analysis & Optimization guidance section
- Specializes in ML infrastructure, experiment tracking, model registries, and pipeline automation
- Added database-admin to Infrastructure & Operations section
- Updated count from 35 to 36 subagents
- Added to usage examples and workflow patterns
- Added to Operations & Maintenance guidance section
- Specializes in backups, replication, user management, and disaster recovery
Specializes in log analysis and pattern recognition:
- Log parsing and error extraction with regex patterns
- Stack trace analysis across programming languages
- Error correlation across distributed systems
- Anomaly detection in log streams
- Root cause analysis with actionable findings
- Added error-detective to Quality & Security section
- Updated count from 33 to 34 subagents
- Added to production incident workflow example
- Added to Quality Assurance section
- Add rust-pro, c-pro, javascript-pro, sql-pro to Language Specialists
- Add terraform-specialist to Infrastructure & Operations
- Update total agent count from 28 to 33
- Fix typo: terraform-specilist.md → terraform-specialist.md
- Update 'When to Use Which Agent' section with new agents
