ReddRadar
Agent skill
no-task-output
Never Use TaskOutput
Install this agent skill to your Project
npx add-skill https://github.com/parcadei/Continuous-Claude-v3/tree/main/.claude/skills/no-task-output
SKILL.md
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
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
parcadei/Continuous-Claude-v3
tdd-migration-pipeline
Orchestrator-only workflow for migrating/rewriting codebases with full TDD and agent delegation
parcadei/Continuous-Claude-v3
agentica-prompts
Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity
parcadei/Continuous-Claude-v3
planning-agent
Planning agent that creates implementation plans and handoffs from conversation context
parcadei/Continuous-Claude-v3
recall
Query the memory system for relevant learnings from past sessions
parcadei/Continuous-Claude-v3
implement_task
Implementation agent that executes a single task and creates handoff on completion
parcadei/Continuous-Claude-v3
braintrust-tracing
Braintrust tracing for Claude Code - hook architecture, sub-agent correlation, debugging
Didn't find tool you were looking for?