# No Task Output

> Avoid TaskOutput tool which floods context with 70k+ token agent transcripts; use synchronous Task instead. Use when managing agent context budgets. Trigger phrases: "context window full", "TaskOutput bloat", "agent transcript too large".

- Skill: `dojogenesis/no-task-output` (Agent Skill)
- Install (CLI): `npx skillmds@latest add dojogenesis/no-task-output`
- Raw SKILL.md: https://api.skillmd.com/api/skills/dojogenesis/no-task-output/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: DojoGenesis (https://skillmd.com/u/dojogenesis)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/dojogenesis/no-task-output

---


# 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