菜单
just-prompt MCP server for model-agnostic prompt routing. Use when you need to send the same prompt to multiple LLM providers, compare outputs, or route prompts based on provider/model selection. Installed via uv sync.
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。
基于 SOC 职业分类
Claude Code hooks patterns. Use when writing hook scripts (PreToolUse, PostToolUse, Stop, SessionStart, etc.) or configuring .claude/settings.json to wire hooks. Reference lib/claude-code-hooks-mastery/ for working examples.
Interpretable Context Methodology — folder structure as agent architecture. Use when creating new stages, reading stage CONTEXT.md files, or understanding how this workspace routes work across numbered stage folders. Reference lib/ICM/ and lib/ICM-animation-example/ for working implementations.
Multi-agent observability patterns. Use when adding logging, tracing, or monitoring across agent interactions. Reference lib/claude-code-hooks-multi-agent-observability/ for working examples including agent session tracking, damage control, and multi-agent event streams.
Pi Coding Agent extension playground. Use when writing, running, or debugging Pi extensions for peer-to-peer communication (coms-net, coms, pi-pi) or multi-agent workflows (agent-team, agent-chain). Bun only — never pnpm/npm.
| name | just-prompt |
| description | just-prompt MCP server for model-agnostic prompt routing. Use when you need to send the same prompt to multiple LLM providers, compare outputs, or route prompts based on provider/model selection. Installed via uv sync. |
Python MCP server for multi-provider LLM prompt routing by Sam Disler.
lib/just-prompt/ — cloned and uv sync complete (19 packages installed).
cd lib/just-prompt
uv run just-prompt --help
Or as an MCP server (add to .mcp.json):
{
"mcpServers": {
"just-prompt": {
"command": "uv",
"args": ["run", "--directory", "lib/just-prompt", "just-prompt"],
"env": {
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
"OPENAI_API_KEY": "${OPENAI_API_KEY}"
}
}
}
}
ANTHROPIC_API_KEY — for Claude modelsOPENAI_API_KEY — for OpenAI modelsGEMINI_API_KEY — for Gemini models (optional)Use just-prompt when the triad review stage (04_triad_review) needs to compare outputs from different models before making a govern-or-block decision.