菜单
Token-efficient AI agent hooks -- env vars, test flag optimization, output truncation, NODE_OPTIONS. Use when optimizing Claude Code for fewer tokens or reducing context waste.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/redpanda-data/ui-harness --skill setup-agent-config命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
| name | setup-agent-config |
| description | Token-efficient AI agent hooks -- env vars, test flag optimization, output truncation, NODE_OPTIONS. Use when optimizing Claude Code for fewer tokens or reducing context waste. |
AI_AGENT=1, CLAUDECODE=1, NODE_OPTIONS=--max-old-space-size=8192--verbose, suggest --pool=forks, --bail=1, --teardownTimeout=5000. Also handle jest/bun test (back-compat)scripts/llm-env.sh, scripts/llm-test-flags.sh, scripts/llm-truncate.sh -> .claude/hooks/. chmod +x..claude/settings.json:
llm-env.shllm-test-flags.shllm-truncate.shAI_AGENT/CLAUDECODE set after session startvitest --verbose rewrite to vitestSee REFERENCE.md for vitest config optimizations.
Snyk dependency sweeps across frontend, Go, and Bazel paths with npm false-positive triage and release-age gates.
Generate Codex hooks.json and AGENTS.md from Claude Code hooks. Maps supported hooks directly, including Edit|Write apply_patch aliases, and keeps Stop batch checks only as fallback. Use when setting up Codex compatibility or dual-agent support.
Question changed code as liability and remove unjustified surface area. Use before commit, push, PR, merge, or when a change feels overbuilt or low-value.
基于 SOC 职业分类
