菜单
Build a progressive-disclosure ContextPack from an AGER bundle. Default 1/4 window token budget, fail-closed. Bodies off unless that node is the pack root.
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/SpillwaveSolutions/okf-agent-graph --skill ager-pack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。
End-to-end reverse engineer of agent codebases (Claude/ChatGPT APIs, LangChain/LangGraph, CrewAI, LlamaIndex, Claude Agent SDK, Deep Agents, MCP, AgentCore, microVMs) into a draft AGER OKF knowledge graph. Primary reverse entry skill for okf-agent-graph (AGKC).
Scan a codebase for agent frameworks (LangGraph, CrewAI, LlamaIndex, Claude/OpenAI APIs, MCP, Deep Agents, hyperscalers, microVMs) and for Claude/Grok/Codex/universal plugin agents and skills. Extracts prompts, tools, schemas, orchestration, loops, harness signals, and plugin frontmatter. Use when reverse-engineering an existing agent project into AGER concepts.
A helper skill that formats commit messages.
基于 SOC 职业分类
正在显示 SKILL.md
| name | ager-pack |
| description | Build a progressive-disclosure ContextPack from an AGER bundle. Default 1/4 window token budget, fail-closed. Bodies off unless that node is the pack root. |
Local packer. Do not fall back to okf-graph-eng for auto-inject.
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/ager_pack.py" agents/lead-researcher.md --repo . --hops 2
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/ager_pack.py" agents/lead-researcher.md --repo . --tiny
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/ager_pack.py" agents/lead-researcher.md --repo . --mermaid
SECOND_BRAIN_WINDOW_TOKENS (128000 → 32000)--max-tokens / SECOND_BRAIN_PACK_MAX_TOKENS--write. Node clip is not a token budget.