mirror of
https://github.com/wshobson/agents.git
synced 2026-03-18 09:37:15 +00:00
3802bca865
Plugin Scope Improvements: - Remove language-specialists plugin (not task-focused) - Split specialized-domains into 5 focused plugins: * blockchain-web3 - Smart contract development only * quantitative-trading - Financial modeling and trading only * payment-processing - Payment gateway integration only * game-development - Unity and Minecraft only * accessibility-compliance - WCAG auditing only - Split business-operations into 3 focused plugins: * business-analytics - Metrics and reporting only * hr-legal-compliance - HR and legal docs only * customer-sales-automation - Support and sales workflows only - Fix infrastructure-devops scope: * Remove database concerns (db-migrate, database-admin) * Remove observability concerns (observability-engineer) * Move slo-implement to incident-response * Focus purely on container orchestration (K8s, Docker, Terraform) - Fix customer-sales-automation scope: * Remove content-marketer (unrelated to customer/sales workflows) Marketplace Statistics: - Total plugins: 27 (was 22) - Tool coverage: 100% (42/42 tools referenced) - Fat plugins removed: 3 (language-specialists, specialized-domains, business-operations) - All plugins now have clear, focused tasks Model Migration: - Migrate all 42 tools from claude-sonnet-4-0/opus-4-1 to model: sonnet - Migrate all 15 workflows from claude-opus-4-1 to model: sonnet - Use short model syntax consistent with agent files Documentation Updates: - Update README.md with refined plugin structure - Update plugin descriptions to be task-focused - Remove anthropomorphic and marketing language - Improve category organization (now 16 distinct categories) Ready for October 9, 2025 @ 9am PST launch
68 lines
2.3 KiB
Markdown
68 lines
2.3 KiB
Markdown
---
|
|
model: sonnet
|
|
---
|
|
|
|
Perform comprehensive multi-agent code review with specialized reviewers:
|
|
|
|
[Extended thinking: This tool command invokes multiple review-focused agents to provide different perspectives on code quality, security, and architecture. Each agent reviews independently, then findings are consolidated.]
|
|
|
|
## Review Process
|
|
|
|
### 1. Code Quality Review
|
|
Use Task tool with subagent_type="code-reviewer" to examine:
|
|
- Code style and readability
|
|
- Adherence to SOLID principles
|
|
- Design patterns and anti-patterns
|
|
- Code duplication and complexity
|
|
- Documentation completeness
|
|
- Test coverage and quality
|
|
|
|
Prompt: "Perform detailed code review of: $ARGUMENTS. Focus on maintainability, readability, and best practices. Provide specific line-by-line feedback where appropriate."
|
|
|
|
### 2. Security Review
|
|
Use Task tool with subagent_type="security-auditor" to check:
|
|
- Authentication and authorization flaws
|
|
- Input validation and sanitization
|
|
- SQL injection and XSS vulnerabilities
|
|
- Sensitive data exposure
|
|
- Security misconfigurations
|
|
- Dependency vulnerabilities
|
|
|
|
Prompt: "Conduct security review of: $ARGUMENTS. Identify vulnerabilities, security risks, and OWASP compliance issues. Provide severity ratings and remediation steps."
|
|
|
|
### 3. Architecture Review
|
|
Use Task tool with subagent_type="architect-reviewer" to evaluate:
|
|
- Service boundaries and coupling
|
|
- Scalability considerations
|
|
- Design pattern appropriateness
|
|
- Technology choices
|
|
- API design quality
|
|
- Data flow and dependencies
|
|
|
|
Prompt: "Review architecture and design of: $ARGUMENTS. Evaluate scalability, maintainability, and architectural patterns. Identify potential bottlenecks and design improvements."
|
|
|
|
## Consolidated Review Output
|
|
|
|
After all agents complete their reviews, consolidate findings into:
|
|
|
|
1. **Critical Issues** - Must fix before merge
|
|
- Security vulnerabilities
|
|
- Broken functionality
|
|
- Major architectural flaws
|
|
|
|
2. **Important Issues** - Should fix soon
|
|
- Performance problems
|
|
- Code quality issues
|
|
- Missing tests
|
|
|
|
3. **Minor Issues** - Nice to fix
|
|
- Style inconsistencies
|
|
- Documentation gaps
|
|
- Refactoring opportunities
|
|
|
|
4. **Positive Findings** - Good practices to highlight
|
|
- Well-designed components
|
|
- Good test coverage
|
|
- Security best practices
|
|
|
|
Target for review: $ARGUMENTS |