一键导入
observability
Use when checking server health, viewing context window usage, or managing async runs
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Use when checking server health, viewing context window usage, or managing async runs
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Thorough code review covering architecture, code quality, and performance. Use when asked to "review this plan", "review code", "audit architecture", "check code quality", or "review for performance". Walks through issues interactively with tradeoff analysis and opinionated recommendations.
Manage Letta AI agent fleets with kubectl-style CLI
Use when releasing features - covers issues, branches, tests, commits, PRs, versioning, and publishing
Use when deploying agents from YAML configuration files
Use when managing individual agents - creating, updating, deleting, listing, or describing
Use when performing bulk operations like cleanup, delete-all, or bulk messaging
| name | observability |
| description | Use when checking server health, viewing context window usage, or managing async runs |
src/commands/health.ts - Server health checksrc/commands/context.ts - Context window analysissrc/commands/runs.ts - Async job management# Health check
lettactl health [-q] [-v]
# Context usage
lettactl context <agent> [-o table|json|yaml]
# Async runs
lettactl runs <agent> [--limit <n>] [--status pending|running|completed|failed] [-o table|json]
ContextUsage {
total_tokens: number
max_tokens: number
usage_percent: number
breakdown: { system_prompt, memory_blocks, tool_definitions, conversation: number }
}
Run {
id: string
status: 'pending' | 'running' | 'completed' | 'failed' | 'cancelled'
created_at: string
completed_at?: string
}
# Check server
lettactl health
# View context usage
lettactl context my-agent
# Get usage as JSON
lettactl context my-agent -o json
# List recent runs
lettactl runs my-agent
# Show only failed runs
lettactl runs my-agent --status failed
# Show last 50 runs
lettactl runs my-agent --limit 50
0 - Success1 - General error2 - Connection failed3 - Auth failed4 - Agent not found