1---2name: no-task-output-23description: Never Use TaskOutput4---56# Never Use TaskOutput78TaskOutput floods the main context window with agent transcripts (70k+ tokens).910## Rule1112NEVER use `TaskOutput` tool. Use `Task` tool with synchronous mode instead.1314## Why1516- TaskOutput reads full agent transcript into context17- This causes mid-conversation compaction18- Defeats the purpose of agent context isolation1920## Pattern2122```23# WRONG - floods context24Task(run_in_background=true)25TaskOutput(task_id="...") // 70k tokens dumped2627# RIGHT - isolated context, returns summary28Task(run_in_background=false) // Agent runs, returns summary29```3031## Source32- Session where TaskOutput caused context overflow
Run npx skillmds@latest add majiayu000/no-task-output-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Never Use TaskOutput It is listed under AI & ML on SkillMD.
This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
majiayu000 (@majiayu000) published this skill. Their other Agent Skills are listed on their SkillMD profile.