trace-claude-code
Automatically trace Claude Code conversations to Braintrust for observability. Captures sessions, conversation turns, and tool…
Never Use TaskOutput
Claude Code
$ npx -y skills add parcadei/Continuous-Claude-v3 --skill no-task-output --agent claude-code
Codex
$ npx skills add parcadei/Continuous-Claude-v3 --skill no-task-output -a codex -y
Cursor
$ npx skills add parcadei/Continuous-Claude-v3 --skill no-task-output -a cursor -y
Gemini CLI
$ npx skills add parcadei/Continuous-Claude-v3 --skill no-task-output -a gemini-cli -y
GitHub Copilot
$ npx skills add parcadei/Continuous-Claude-v3 --skill no-task-output -a github-copilot -y
OpenCode
$ npx skills add parcadei/Continuous-Claude-v3 --skill no-task-output -a opencode -y
Windsurf
$ npx skills add parcadei/Continuous-Claude-v3 --skill no-task-output -a windsurf -y
name: no-task-output description: Never Use TaskOutput user-invocable: false
TaskOutput floods the main context window with agent transcripts (70k+ tokens).
NEVER use `TaskOutput` tool. Use `Task` tool with synchronous mode instead.
# WRONG - floods context Task(run_in_background=true) TaskOutput(task_id="...") // 70k tokens dumped # RIGHT - isolated context, returns summary Task(run_in_background=false) // Agent runs, returns summary
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
Automatically trace Claude Code conversations to Braintrust for observability. Captures sessions, conversation turns, and tool…
Guide for integrating Agentica SDK with Claude Code CLI proxy
Reference guide for Agentica multi-agent infrastructure APIs
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Ask which skill or flow fits your situation. A router over the skills in this repo.