mirror of
https://github.com/wshobson/agents.git
synced 2026-03-18 09:37:15 +00:00
d2f3886ae1
Repository Restructure: - Move all 83 agent .md files to agents/ subdirectory - Add 15 workflow orchestrators from commands repo to workflows/ - Add 42 development tools from commands repo to tools/ - Update README for unified repository structure The commands repository functionality is now fully integrated, providing complete workflow orchestration and development tooling alongside agents. Directory Structure: - agents/ - 83 specialized AI agents - workflows/ - 15 multi-agent orchestration commands - tools/ - 42 focused development utilities No breaking changes to agent functionality - all agents remain accessible with same names and behavior. Adds workflow and tool commands for enhanced multi-agent coordination capabilities.
1.9 KiB
1.9 KiB
model
| model |
|---|
| claude-sonnet-4-0 |
Save current project context for future agent coordination:
[Extended thinking: This tool uses the context-manager agent to capture and preserve project state, decisions, and patterns. This enables better continuity across sessions and improved agent coordination.]
Context Capture Process
Use Task tool with subagent_type="context-manager" to save comprehensive project context.
Prompt: "Save comprehensive project context for: $ARGUMENTS. Capture:
-
Project Overview
- Project goals and objectives
- Key architectural decisions
- Technology stack and dependencies
- Team conventions and patterns
-
Current State
- Recently implemented features
- Work in progress
- Known issues and technical debt
- Performance baselines
-
Design Decisions
- Architectural choices and rationale
- API design patterns
- Database schema decisions
- Security implementations
-
Code Patterns
- Coding conventions used
- Common patterns and abstractions
- Testing strategies
- Error handling approaches
-
Agent Coordination History
- Which agents worked on what
- Successful agent combinations
- Agent-specific context and findings
- Cross-agent dependencies
-
Future Roadmap
- Planned features
- Identified improvements
- Technical debt to address
- Performance optimization opportunities
Save this context in a structured format that can be easily restored and used by future agent invocations."
Context Storage
The context will be saved to .claude/context/ with:
- Timestamp-based versioning
- Structured JSON/Markdown format
- Easy restoration capabilities
- Context diffing between versions
Usage Scenarios
This saved context enables:
- Resuming work after breaks
- Onboarding new team members
- Maintaining consistency across agent invocations
- Preserving architectural decisions
- Tracking project evolution
Context to save: $ARGUMENTS