- name
SKILL.md
技能文件保留在发布者的仓库中。
在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add vibeeval/vibecosystem --skill agent-context-isolation -a cursor -y在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add vibeeval/vibecosystem --skill agent-context-isolation -a claude-code -y在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add vibeeval/vibecosystem --skill agent-context-isolation -a codex -y在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add vibeeval/vibecosystem --skill agent-context-isolation -a grok -y在 Grok Bot 聊天中发送复制的消息。Bot 会从 GitHub 获取这个 SKILL.md,并添加到你所有 Bot 共享的技能中。
Install this skill: https://github.com/vibeeval/vibecosystem/tree/HEAD/skills/agent-context-isolation来自发布者
Prevent agent output from polluting the main context window.
# RIGHT - background agent writes to file, main reads file
Task(subagent_type="...", run_in_background=true, prompt="... Output to: /path/to/file.md")
# WRONG - foreground agent dumps full transcript into main context
Task(subagent_type="...", run_in_background=false)
Background agents with run_in_background=true isolate their context. Have them write results to files in .claude/cache/agents/<agent-type>/.
# WRONG - dumps entire transcript (70k+ tokens) into context
TaskOutput(task_id="<id>")
TaskOutput(task_id="<id>", block=true)
# RIGHT - check expected output files
Bash("ls -la .claude/cache/agents/<agent-type>/")
Bash("bun test") # verify with tests
TaskOutput returns the full agent transcript. Always use file-based coordination instead.
# System reminders come automatically:
# "Agent a42a16e progress: 6 new tools used, 88914 new tokens"
# To detect completion:
# - Watch for progress reminders to stop arriving
# - Poll for expected output files: find .claude/cache/agents -name "*.md" -mmin -5
# - Check task output file size growth: wc -c /tmp/claude/.../tasks/<id>.output
Stuck agent detection:
After agent work:
bun testResearch agent → .claude/cache/agents/oracle/output.md
↓
Plan agent → .claude/cache/agents/plan-agent/output.md (reads research)
↓
Validate agent → .claude/cache/agents/validate-agent/output.md (reads plan)
↓
Implement agent → src/module.ts (reads validated plan)
Each agent reads the previous agent's file output, not TaskOutput.
Agent context isolation preserves the main conversation's context budget. Reading agent outputs via TaskOutput floods context, causing:
Agent Context Isolation
---name: agent-context-isolationdescription: Agent Context Isolation---# skills/agent-context-isolation/SKILL.md常见问题
从发布者处下载 skills/agent-context-isolation/SKILL.md,或复制路径后打开仓库。PlugMCP 只收录该技能,不托管文件。
发布者将它存放在 https://github.com/vibeeval/vibecosystem。
Claude、Cursor、Codex 和 Grok Build 可以读取你从发布者仓库添加的 SKILL.md。在聊天中发送技能的 GitHub 文件夹链接,Grok Bot 就会安装它。