Agent-Skills.md

Agent Skills: Never Use TaskOutput

Never Use TaskOutput

UncategorizedID: parcadei/continuous-claude-v3/no-task-output

Repository

parcadei/continuous-claude-v3
parcadeiLicense: MIT
3,631281

Install this agent skill to your local

pnpm dlx add-skill https://github.com/parcadei/Continuous-Claude-v3/tree/HEAD/.claude/skills/no-task-output

Skill Files

Browse the full folder contents for no-task-output.

Download Skill

Loading file tree…

.claude/skills/no-task-output/SKILL.md

Skill Metadata

Name
no-task-output
Description
Never Use TaskOutput

Never Use TaskOutput

TaskOutput floods the main context window with agent transcripts (70k+ tokens).

Rule

NEVER use TaskOutput tool. Use Task tool with synchronous mode instead.

Why

  • TaskOutput reads full agent transcript into context
  • This causes mid-conversation compaction
  • Defeats the purpose of agent context isolation

Pattern

# 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

Source

  • Session where TaskOutput caused context overflow