bb-cli
Use this when controlling bb. The bb CLI inspects and manages threads, environments, projects, machines, providers, skills, plugins, settings, terminals, and other BB services.
- License 许可
- MIT
- 最近更新
- 2026-11-14
- Stars
- ★ 4.3k
- Forks
- 626
01 前言 Front Matter
- name
- bb-cli
- description
- Use this when controlling bb. The bb CLI inspects and manages threads, environments, projects, machines, providers, skills, plugins, settings, terminals, and other BB services.
02 资源文件 9
- 参考文档references/app-settings.md4.3 KB
- 参考文档references/command-index.md4.8 KB
- 参考文档references/configuration.md3.7 KB
- 参考文档references/failure-recovery.md2.4 KB
- 参考文档references/plugins.md13.2 KB
- 参考文档references/theme-commands.md3.4 KB
- 参考文档references/theming.md11.7 KB
- 参考文档references/thread-creation.md10.8 KB
- 参考文档references/thread-operation.md10.4 KB
03 SKILL.md 正文
BB CLI
Never inspect or message other threads unless the user explicitly requests that action.
Use bb for BB state and actions. Inspect the current context before you choose IDs, machines, workspaces, providers, or models.
Start with context
bb status --json
Use JSON when command output controls later work. Use human output for quick inspection.
Run bb --version for the CLI version. Use bb --help or bb help [command]
for help. Run bb guide for the system overview. Run bb guide <chapter> for one
area. Use bb <group> --help for current flags and defaults.
A standalone CLI targets http://127.0.0.1:38886. Use BB_SERVER_URL and BB_HOST_DAEMON_PORT only for an intentional non-default target.
Read only the relevant reference
- Read references/command-index.md to find the exact core command path. Use live help for current flags and defaults.
- Read references/configuration.md for settings, agent instructions, skills, remote clients, and environment setup scripts.
- Read references/thread-creation.md before you spawn or fork threads, create projects, select machines, or create environments.
- Read references/thread-operation.md for messages, queues, interactions, panes, terminals, inspection, and long-running commands.
- Read references/failure-recovery.md when a thread fails, stops, or needs plan or goal recovery.
- Read references/theme-commands.md for palette and favicon commands. Read references/theming.md before you create or edit theme CSS.
- Read references/plugins.md for plugin discovery, install, build, update, configuration, runtime, and contributed commands.
- Read references/app-settings.md for complete app setting keys and effects.
Command habits
- Resolve names and IDs with a list or show command before mutation.
- Pass an explicit project when a command can act across projects.
- Pass an environment or machine selector when the default host is uncertain.
- Query provider models on the machine that will run the thread.
- Prefer non-interactive commands and machine-readable output for automation.
- Pass
--yesfor a confirmed destructive command in a non-interactive shell. - Treat plugin commands as normal top-level commands after installation.
- Inspect real status, logs, API results, or diffs instead of assumptions.
- Keep file paths on the machine that owns the selected workspace.
- BB rejects symlinks as project/environment roots (
Root path ... must not be a symlink). Use real directories. Before a rename or rollback, check every affected environment and thread; changing only project sources is not enough.
Common checks
bb project list --json
bb machine list --json
bb provider list --environment "$BB_ENVIRONMENT_ID" --json
bb thread show "$BB_THREAD_ID" --json
bb environment status "$BB_ENVIRONMENT_ID" --json
bb plugin list --json
bb skill list --environment "$BB_ENVIRONMENT_ID" --json
Completion
Confirm the command result and any affected thread, environment, plugin, or remote service. Report the stable ID or URL that the user needs next.
04 同仓库更多 Skills
varied-search
Research a topic across the web, GitHub, and X/Twitter with DeepAPI and produce a concise Markdown report. Use for varied-search or requests to compare web coverage, relevant repositories, and social discussion.
total-review
Run five independent max-effort reviews (Fable 5.1, Opus 5.5, GPT-6 Astra, GPT-6.1 Sol, Muse Wonder), merge their findings, and fix only what the user approves. Use for /total-review, or when the user or another agent asks for a total review.
stop-overthinking
Manually-invoked skill that stops overthinking and forces a short, practical decision. Use only when the user explicitly invokes stop-overthinking.
state
Manually-invoked skill that recaps what the current thread is doing and how far along it is. Use when the user says "state", "where are we", or "what % are we done".
setup-help
Guide setup one step at a time and show what remains. Use only when the user explicitly asks for it by name.
self-archive
Archive the current Cloudroom thread and release its runtime. Use only when the user explicitly asks to self-archive, archive yourself, or archive this thread.