使用方法
- 复制安装命令,在自己的智能体环境安装前先检查源码包。
- 从原始文档核对所需工具、凭据和支持的宿主。
- 说明输入材料与期望交付物,并对照来源检查输出。
npx skills add https://github.com/onsager-ai/agent-workbench --skill workbench-setup开始前需了解
- 安装不包含模型订阅、API 额度或访问文件的权限。
- 仓库星数和安装量反映活跃情况,不等于独立质量或安全测试。
按源仓库内容呈现,保留标题、案例、代码、表格、链接以及原文引用的演示图片。
Use the bundled Python 3.11+ installer on Linux or macOS. Native npx skills distributes this skill; it does not execute the installer or apply global prompts.
Orchestration's interactive Manager, native Worker ladder and configured context policy live in the orchestrate-harnesses skill. Window values come from the effective model configuration, not skill or role instructions. Updating that skill changes its distributed defaults, not the current Manager's interactive model/settings or the user's partial model overrides. Remove obsolete roles.manager/roles.preflight/roles.acceptance and controller-only log/prompt overrides as described in that skill before the next dispatch. Setup does not migrate those private settings or rewrite historical tasks. Private rules outside the managed block may still require a Gateway/fixed Manager or Python controller; inspect and reconcile those explicitly when migrating.
After global distribution, explicitly apply the setup:
python3 ~/.agents/skills/workbench-setup/scripts/workbench.py install
~/.local/bin/agent-workbench statusThe installer creates ~/.agents/AGENTS.md, links Codex's ~/.codex/AGENTS.md, and ensures ~/.claude/CLAUDE.md has one native import resolving to the shared instructions. An existing equivalent Claude import is reused. Personal text belongs outside <!-- BEGIN agent-workbench --> and <!-- END agent-workbench --> in the shared file. Existing Codex regular-file bytes migrate there on first installation; existing Claude text stays in its file.
agent-workbench install reapplies distributed assets. agent-workbench update first updates only installed skills owned by onsager-ai/agent-workbench through the native skills lock, then runs freshly distributed setup code. Node.js 22.20+ and npx are needed for distribution and updates. Do not edit the native skills lock yourself.
agent-workbench uninstall removes the public block and owned import/launcher, and makes Codex's file regular again with the current private text. Backups remain private under ~/.local/state/agent-workbench/backups; uninstall never restores stale snapshots over later edits. This is the normal rollback operation. Review retained backups manually for historical recovery.
If a command reports an override, foreign entry, missing resource, or edited managed block, preserve the files and resolve that specific conflict before retrying. There is no force-overwrite mode. State and lock live under ~/.local/state/agent-workbench/. Installation does not edit other skills, project files, shell configuration, credentials, models, or permissions.
For isolated fixtures, put the skill at the canonical location under a disposable home, then pass --home PATH before the command. Alternate-home updates require an explicit --skills-cmd executable command; they never default to the real user's npx update. Native permission choices remain with the user.

