trace-claude-code
Automatically trace Claude Code conversations to Braintrust for observability. Captures sessions, conversation turns, and tool calls as hierarchical traces.
No Polling for Background Agents
$ npx -y skills add parcadei/Continuous-Claude-v3 --skill no-polling-agents --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/no-polling-agentsContext preview
The summary Claude sees to decide when to auto-load this skill.
No Polling for Background Agents
name: no-polling-agents description: No Polling for Background Agents user-invocable: false
When launching parallel background agents, do NOT poll with sleep loops.
Background agents write to status files when complete. Wait for them naturally.
1. User explicitly asks "are they done?" 2. You need agent output to proceed with next task 3. Significant time has passed and user is waiting
// Launch agents
Task({ ..., run_in_background: true })
Task({ ..., run_in_background: true })
// Continue with other work or conversation
// Agents will write to status file when done
// Only check when needed
cat .claude/cache/status.txtUser feedback: "You can just wait until everyone pings you"
A persistent, learning, multi-agent development environment built on Claude Code Continuous Claude transforms Claude Code into a continuously learning system that maintains context across sessions, orchestrates specialized agents, and eliminates wasting
Repo: parcadei/Continuous-Claude-v3
Automatically trace Claude Code conversations to Braintrust for observability. Captures sessions, conversation turns, and tool calls as hierarchical traces.
Guide for integrating Agentica SDK with Claude Code CLI proxy
Reference guide for Agentica multi-agent infrastructure APIs