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

related skills

semantically similar in the cross-vendor index

clawhub

41% match

Claude Sonnet 4 Lite Agent

Efficiently create content by rapidly advancing tasks, handling failures by stopping after two retries, and strictly following provided research and templates.

don't have the plugin yet? install it then click "run inline in claude" again.

implexa · skills ranked by SkillRank

top skills resources guides install github llms.txt x / twitter privacy

by @clawhub

skills.sh

40% match

agent-workflow-designer

Design production-grade multi-agent workflows with clear pattern choice (sequential, parallel, hierarchical), handoff contracts, failure handling, and…

by @alirezarezvani

skills.sh

33% match

continuous-agent-loop

Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls.

Claude Code compatibility mirror for the Codex-native 10000 Mentors Research Workflow. Use only when running from Claude Code and the user wants the same sou...

by @clawhub

clawhub

32% match

Chief Creative Officer

AI agent for chief creative officer tasks

by @clawhub