trace-claude-code
Automatically trace Claude Code conversations to Braintrust for observability. Captures sessions, conversation turns, and tool calls as hierarchical traces.
Hook Development Rules
$ npx -y skills add parcadei/Continuous-Claude-v3 --skill hooks --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/hooksContext preview
The summary Claude sees to decide when to auto-load this skill.
Hook Development Rules
name: hooks description: Hook Development Rules user-invocable: false
When working with files in `.claude/hooks/`:
Shell wrapper (.sh) → TypeScript (.ts) via `npx tsx`
#!/bin/bash set -e cd "$CLAUDE_PROJECT_DIR/.claude/hooks" cat | npx tsx <handler>.ts
interface HookInput {
// Event-specific fields
}
async function main() {
const input: HookInput = JSON.parse(await readStdin());
// Process input
const output = {
result: 'continue', // or 'block'
message: 'Optional system reminder'
};
console.log(JSON.stringify(output));
}Test hooks manually:
echo '{"type": "resume"}' | .claude/hooks/session-start-continuity.shAdd hooks to `.claude/settings.json`:
{
"hooks": {
"EventName": [{
"matcher": ["pattern"], // Optional
"hooks": [{
"type": "command",
"command": "$CLAUDE_PROJECT_DIR/.claude/hooks/hook.sh"
}]
}]
}
}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