5dive-cli-extras

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

5dive-cli-extras

Companion to the

5dive-cli

skill: everything on the

5dive

CLI that isn't reached for every session. Read

5dive-cli

first for the mental model, the

--json

output contract, and the core spawn/send/task recipes — they apply here too and aren't repeated.

作为

5dive-cli

技能的配套工具：涵盖

5dive

CLI中所有非日常高频使用的功能。请先阅读

5dive-cli

文档，了解其核心概念、

--json

输出规范以及生成/发送/任务管理的基础用法——这些规则同样适用于本工具，此处不再重复说明。

Advanced agent create: personas, BYO providers, auth deferral

进阶Agent创建：角色定制、自定义提供商、延迟授权

Hire a ready-made persona from the agent market

从Agent市场雇佣现成角色

Beyond a blank teammate, hire a ready-made persona off the agent market (character-pack registry, DIVE-993/1020):

bash

5dive market                          # browse every pack, rarity-first
5dive market <keyword> [--role=<r>] [--rarity=<tier>] [--seasoned]  # --seasoned = ships trained memory
5dive market show <slug>              # preview: tier, model, skills, card, DID

5dive hire <role> --from-market --dry-run --json          # resolve + show disclosure, create NOTHING
5dive hire <role> --from-market [--as=<name>] --yes --json  # provision the top match

--from-market

provisions a REAL teammate (DIVE-1013):

--dry-run

creates nothing; a TTY requires an interactive

y/N

; non-interactive needs an explicit

--yes

or it aborts after the disclosure.

5dive hire <name> [--role="CTO"] [--title=...]

(no

--from-market

) is plain sugar for

agent create

plus an

org set

when

--role

--title

are given.

agent import

is the path to clone an exact persona from a market slug or a local

.tar.gz

. Always

inspect

an untrusted pack first (read-only, no root):

bash

5dive agent inspect <slug|pack.tar.gz> --json        # what shell/hooks/skills it would run
sudo 5dive agent import <slug|pack.tar.gz> --as=<name> [--allow-hooks] --json

A pack's hooks are arbitrary shell that auto-runs on the new agent's tool events, so

import

is deny-by-default on hooks — stripped unless you pass

--allow-hooks

— and refuses any member with a

..

/absolute path or a symlink (zip-slip + link-escape guards).

agent clone <src> <dst>

copies an existing agent's type/config into a new one.

--with-skills=<spec>[,<spec>...]

(bare id or

<owner/repo>:<id>

) /

--no-skills

control what a spawned child inherits (defaults to the

5dive-cli

skill when the caller is another agent);

--inherit-memory=<scope>

seeds recall from

wiki

, a sibling

<agent-name>

, or

all

team

;

--no-team-bot

opts a new no-bot agent out of the shared team bot.

除了创建空白Agent，你还可以从Agent市场雇佣现成的角色（角色包注册表，对应DIVE-993/1020）：

bash

5dive market                          # 浏览所有角色包，按稀有度排序
5dive market <keyword> [--role=<r>] [--rarity=<tier>] [--seasoned]  # --seasoned = 包含训练记忆
5dive market show <slug>              # 预览角色包：等级、模型、技能、卡片、DID

5dive hire <role> --from-market --dry-run --json          # 解析并展示披露信息，不实际创建
5dive hire <role> --from-market [--as=<name>] --yes --json  # 创建匹配度最高的角色

--from-market

会创建真实的Agent成员（对应DIVE-1013）：

--dry-run

不会创建任何内容；交互式终端会要求确认

y/N

；非交互式场景需显式指定

--yes

，否则会在展示披露信息后终止。不带

--from-market

的

5dive hire <name> [--role="CTO"] [--title=...]

是简化操作，等价于

agent create

加上指定

--role

--title

时的

org set

命令。

agent import

可通过市场slug或本地

.tar.gz

包克隆完全一致的角色。对于不可信的包，请先执行

inspect

进行只读检查（无权限风险）：

bash

5dive agent inspect <slug|pack.tar.gz> --json        # 查看该包会运行的shell/钩子/技能
sudo 5dive agent import <slug|pack.tar.gz> --as=<name> [--allow-hooks] --json

角色包中的钩子是可自动运行的任意shell脚本，因此

import

默认拒绝钩子——除非添加

--allow-hooks

参数，否则钩子会被移除；同时会拒绝包含

..

/绝对路径或符号链接的成员（防止zip-slip和链接逃逸攻击）。

agent clone <src> <dst>

会将现有Agent的类型/配置复制到新Agent中。

--with-skills=<spec>[,<spec>...]

（仅ID或

<owner/repo>:<id>

格式）/

--no-skills

控制新Agent继承的技能（默认继承调用方Agent的

5dive-cli

技能）；

--inherit-memory=<scope>

从Wiki、同级

<agent-name>

或

all

team

中导入记忆；

--no-team-bot

让新Agent不加入共享团队机器人。

Create-then-auth:

--defer-auth

创建后授权：

--defer-auth

Registers the agent before its credentials are wired up:

bash

sudo 5dive agent create draft-bot --type=claude --defer-auth --json

先注册Agent，之后再配置凭证：

bash

sudo 5dive agent create draft-bot --type=claude --defer-auth --json

BYO API key:

--provider

(hermes / openclaw / claude)

自定义API密钥：

--provider

（hermes / openclaw / claude）

hermes

and

openclaw

are bring-your-own-model harnesses:

bash

sudo 5dive agent create cheap-bot --type=openclaw \
  --provider=openrouter --api-key=- --json   # key on stdin

Providers:

openrouter google minimax moonshot huggingface anthropic deepseek qwen nous openai zai

. Since 0.8.0,

--provider

also works on

--type=claude

for the Anthropic-compatible subset (

openrouter deepseek moonshot zai

); it requires

--auth-profile=<name>

and wires

ANTHROPIC_BASE_URL

ANTHROPIC_AUTH_TOKEN

plus per-tier model defaults. Override with

--model=<slug>

at create or

agent config set model=<slug>

later. Keep the background HAIKU slot on a prompt-caching-capable model.

hermes

和

openclaw

是自定义模型的适配框架：

bash

sudo 5dive agent create cheap-bot --type=openclaw \
  --provider=openrouter --api-key=- --json   # 从标准输入读取密钥

支持的提供商：

openrouter google minimax moonshot huggingface anthropic deepseek qwen nous openai zai

。从0.8.0版本开始，

--provider

也可用于

--type=claude

，兼容Anthropic的子集（

openrouter deepseek moonshot zai

）；需要配合

--auth-profile=<name>

参数，自动配置

ANTHROPIC_BASE_URL

ANTHROPIC_AUTH_TOKEN

以及对应等级的模型默认值。可在创建时通过

--model=<slug>

或后续通过

agent config set model=<slug>

覆盖默认模型。建议将后台HAKU插槽设置为支持提示缓存的模型。

Tune a running claude agent: model + effort

调整运行中的Claude Agent：模型与算力

bash

sudo 5dive agent config worker-1 set model=claude-opus-4-8
sudo 5dive agent config worker-1 set effort=high

bash

sudo 5dive agent config worker-1 set model=claude-opus-4-8
sudo 5dive agent config worker-1 set effort=high

effort: low|medium|high|xhigh|max — claude only; xhigh/max are Opus-tier.

effort取值：low|medium|high|xhigh|max — 仅Claude支持；xhigh/max为Opus等级专属

undefined

undefined

Recover from

auth_required

从

auth_required

错误中恢复

bash

undefined

bash

undefined

If create fails with error.class=auth_required, the type isn't authenticated.

如果创建Agent时出现error.class=auth_required错误，说明该类型未完成授权。

A) Static API key in $KEY (preferred for automation)

A) 从环境变量$KEY读取静态API密钥（自动化场景首选）

echo "$KEY" | sudo 5dive agent auth set claude --api-key=- --json

B) Device-code flow (when only a human can complete login)

B) 设备码流程（仅人工可完成登录）

sudo 5dive agent auth start claude --json

-> session id; give the URL from

auth poll

to the user; they paste the

-> 返回会话ID；将

auth poll

返回的URL提供给用户，用户粘贴回调码后执行

auth submit

完成登录。

callback code back via

auth submit

—


Never call `5dive agent auth login <type>` from your own process — it hands
the TTY off to the upstream CLI's interactive flow and hangs your agent.
Use `auth start`/`auth set` instead.


请勿在自己的进程中调用`5dive agent auth login <type>`——该命令会将终端控制权交给上游CLI的交互式流程，导致你的Agent挂起。请使用`auth start`/`auth set`替代。

Multi-account: the

account

noun

多账号管理：

account

指令

A 5dive account is a named auth profile — one bag of credentials that any number of agents can share via

--auth-profile=<name>

. Use it when the host has more than one human/billing identity and different agents should use different ones.

bash

sudo 5dive account list --json           # which accounts exist, types, agents bound
sudo 5dive account usage --json          # per-account 5h/7d rate-limit headroom
sudo 5dive account show acme-prod --json # detail incl. which env keys are populated

sudo 5dive account add acme-prod         # provision empty, then sign in (TTY-only)
sudo 5dive account login acme-prod --type=claude

sudo 5dive agent set-account worker-1 acme-prod --json   # rebind + restart
sudo 5dive agent set-account worker-1 default --json     # clear the override

sudo 5dive account rename acme-prod acme-staging --json  # remove refuses while bound
sudo 5dive account remove acme-staging --json
sudo 5dive account set-active-provider acme-prod hermes openrouter --json  # hermes-only

The reserved name

default

is rejected by

account add

rename

— at the agent level,

auth-profile=default

means "no override, use the shared

/etc/5dive/connectors/<type>.env

". Check

account usage

before blaming quota for a failure or moving agents between accounts.

5dive的account是命名的授权配置文件——一组凭证，可通过

--auth-profile=<name>

让多个Agent共享。适用于主机拥有多个用户/计费身份，且不同Agent需使用不同身份的场景。

bash

sudo 5dive account list --json           # 查看所有账号、类型及绑定的Agent
sudo 5dive account usage --json          # 查看每个账号的5小时/7天调用余量
sudo 5dive account show acme-prod --json # 查看账号详情，包括已配置的环境变量

sudo 5dive account add acme-prod         # 创建空账号，之后登录（仅交互式终端支持）
sudo 5dive account login acme-prod --type=claude

sudo 5dive agent set-account worker-1 acme-prod --json   # 重新绑定账号并重启Agent
sudo 5dive agent set-account worker-1 default --json     # 清除账号覆盖，使用默认配置

sudo 5dive account rename acme-prod acme-staging --json  # 账号绑定Agent时无法删除
sudo 5dive account remove acme-staging --json
sudo 5dive account set-active-provider acme-prod hermes openrouter --json  # 仅hermes生效

default

是保留名称，无法通过

account add

rename

创建——在Agent层面，

auth-profile=default

表示"不使用覆盖配置，使用共享的

/etc/5dive/connectors/<type>.env

文件"。在因配额问题排查故障或迁移Agent账号前，请先检查

account usage

。

Telegram/Discord pairing and shared team bot

Telegram/Discord配对与共享团队机器人

bash

undefined

bash

undefined

Classic — return a pairing code, user DMs the bot, paste the bot reply.

经典方式 — 返回配对码，用户向机器人发送私信，粘贴机器人回复的内容完成配对。

sudo 5dive agent pair worker-1 --json sudo 5dive agent pair worker-1 --code=AB12CD --json

Auto-detect — long-poll for the next inbound message, seed access.json.

自动检测 — 长轮询下一条入站消息，生成access.json。

sudo 5dive agent telegram-discover --token="$BOT_TOKEN" --poll-secs=60 --json sudo 5dive agent pair worker-1 --user-id=<userId> --chat-id=<chatId> --json

Bot identity for a tappable deep link.

获取机器人身份，用于生成可点击的深度链接。

sudo 5dive agent telegram-getme --token="$BOT_TOKEN" --json


`telegram-discover`/`telegram-getme` are read-only and need no bound agent.
A few more helpers:

```bash
sudo 5dive agent telegram-info worker-1 [--refresh] --json         # cached getMe, backfills @handle
sudo 5dive agent telegram-pending-ignore worker-1 <code> --json    # drop a pending pairing
sudo 5dive agent telegram-resolve-handle worker-1 @someuser --json # getChat for @handle

Attach a bot after create, and prefer stdin over argv for tokens (never lands in

/proc/<pid>/cmdline

or logs):

bash

echo "$BOT_TOKEN" | sudo 5dive agent config worker-1 set telegram.token=-
sudo 5dive agent config worker-1 set channels=telegram
sudo 5dive agent config worker-1 set telegram.home-channel=<chat-id>  # hermes only

Only one

=-

key can be read per invocation, and

=-

with nothing piped blocks on stdin until your timeout. For non-channel secrets there's a root-only drop primitive:

bash

echo -n "$TOKEN" | sudo 5dive secret write OPENAI_API_KEY --connector=openai

Who may talk to the bot is governed by

access.json

(no restart needed — the plugin re-reads per message):

bash

sudo 5dive agent telegram-access get worker-1 --json
echo '{"dmPolicy":"allowlist","allowFrom":[1234567890],"groups":{}}' \
  | sudo 5dive agent telegram-access set worker-1
sudo 5dive agent config worker-1 set telegram.allowed-users=1234567890,5551234  # shortcut

A group chat the bot should reply in must be present in

groups{}

— without it, replies into that group are dropped.

sudo 5dive agent telegram-getme --token="$BOT_TOKEN" --json


`telegram-discover`/`telegram-getme`是只读命令，无需绑定Agent。还有以下辅助命令：

```bash
sudo 5dive agent telegram-info worker-1 [--refresh] --json         # 缓存的getMe信息，自动补全@handle
sudo 5dive agent telegram-pending-ignore worker-1 <code> --json    # 忽略待处理的配对请求
sudo 5dive agent telegram-resolve-handle worker-1 @someuser --json # 通过@handle获取聊天信息

请在创建Agent之后再绑定机器人，并且优先通过标准输入传递令牌（避免令牌出现在

/proc/<pid>/cmdline

或日志中）：

bash

echo "$BOT_TOKEN" | sudo 5dive agent config worker-1 set telegram.token=-
sudo 5dive agent config worker-1 set channels=telegram
sudo 5dive agent config worker-1 set telegram.home-channel=<chat-id>  # 仅hermes支持

每次调用只能读取一个

=-

格式的密钥，如果

=-

后没有输入，会阻塞等待输入直到超时。对于非频道密钥，可使用仅root用户可用的写入命令：

bash

echo -n "$TOKEN" | sudo 5dive secret write OPENAI_API_KEY --connector=openai

谁可以与机器人对话由

access.json

控制（无需重启——插件会在每次接收消息时重新读取）：

bash

sudo 5dive agent telegram-access get worker-1 --json
echo '{"dmPolicy":"allowlist","allowFrom":[1234567890],"groups":{}}' \
  | sudo 5dive agent telegram-access set worker-1
sudo 5dive agent config worker-1 set telegram.allowed-users=1234567890,5551234  # 快捷方式

机器人需要回复的群聊必须在

groups{}

中配置——否则机器人会忽略该群聊的回复请求。

Shared team bot: one bot, every agent

共享团队机器人：一个机器人，所有Agent共用

Instead of one token per agent, every agent can post into one Telegram forum group (its own topic per agent) on a single token, with a root listener as the sole

getUpdates

consumer (per-agent bridges go send-only):

bash

sudo 5dive agent team-bot status|provision|shared|intercom|discover|refresh-listener
sudo 5dive agent team-group discover|provision|shared|status [--group=<chat_id>]
sudo 5dive agent topic get|set <name> [--thread-id=N --chat-id=N]  # per-agent forum topic

无需为每个Agent配置单独令牌，所有Agent可通过单个令牌在同一个Telegram论坛群组中发送消息（每个Agent对应一个独立主题），由root监听器作为唯一的

getUpdates

消费者（每个Agent的桥接器仅负责发送消息）：

bash

sudo 5dive agent team-bot status|provision|shared|intercom|discover|refresh-listener
sudo 5dive agent team-group discover|provision|shared|status [--group=<chat_id>]
sudo 5dive agent topic get|set <name> [--thread-id=N --chat-id=N]  # 每个Agent对应的论坛主题

Delegating a request that came in over a channel — full walkthrough

转发通过渠道收到的请求——完整流程

When the user's request arrives via the channel plugin, it's wrapped:

<channel source="plugin:telegram:telegram" chat_id="1234567890" message_id="4671" user="..." ts="...">
redirect to marketing
</channel>

Map

chat_id

→

--reply-to-chat=<chat_id>

and

message_id

→

--reply-to-msg=<message_id>

(optional; threads the reply):

bash

sudo 5dive agent send marketing \
  --reply-to-chat=1234567890 --reply-to-msg=4671 \
  "User @alice asked your take on the Q3 launch copy. Reply in the chat
   via your own bot — do not reply back to me."

Receiver-side the envelope carries

reply-to-chat=<id> reply-to-msg=<id>

; on seeing it, post directly in that chat via your own Telegram/Discord tool instead of replying back to the sender. If the target agent's bot is not in the chat, relay the reply yourself and tell the user the bot needs adding.

当用户请求通过渠道插件到达时，会被包装为以下格式：

<channel source="plugin:telegram:telegram" chat_id="1234567890" message_id="4671" user="..." ts="...">
redirect to marketing
</channel>

将

chat_id

映射为

--reply-to-chat=<chat_id>

，

message_id

映射为

--reply-to-msg=<message_id>

（可选；用于线程化回复）：

bash

sudo 5dive agent send marketing \
  --reply-to-chat=1234567890 --reply-to-msg=4671 \
  "用户@alice询问你对Q3发布文案的看法。请直接在聊天中回复，不要回复我。"

接收方会收到包含

reply-to-chat=<id> reply-to-msg=<id>

的消息；收到后，请通过自己的Telegram/Discord工具直接在该聊天中回复，而不是回复给发送方。如果目标Agent的机器人不在该聊天中，请代为转发回复，并告知用户需要添加机器人。

Declarative fleets: compose + team templates

声明式Agent集群：组合与团队模板

For more than a couple of agents, declare the fleet in

5dive.yaml

bash

sudo 5dive up         # bring up everything declared (idempotent)
sudo 5dive ps         # declared agents' state
sudo 5dive down       # tear down declared agents
sudo 5dive export     # dump the LIVE fleet to a v2 5dive.yaml

sudo 5dive team ls
sudo 5dive team import startup --json   # bundled multi-agent company template

Spec keys per agent:

type, channels, telegram_token, discord_token, workdir, skills, no_skills, defer_auth, isolation, auth_profile, provider, api_key

. Strings expand

${ENV_VAR}

from the process env and fail loudly when missing.

当Agent数量超过几个时，可在

5dive.yaml

中声明集群配置：

bash

sudo 5dive up         # 启动所有已声明的Agent（幂等操作）
sudo 5dive ps         # 查看已声明Agent的状态
sudo 5dive down       # 停止所有已声明的Agent
sudo 5dive export     # 将当前运行的集群导出为v2版本的5dive.yaml

sudo 5dive team ls
sudo 5dive team import startup --json   # 导入预定义的多Agent公司模板

每个Agent的配置项包括：

type, channels, telegram_token, discord_token, workdir, skills, no_skills, defer_auth, isolation, auth_profile, provider, api_key

。字符串中的

${ENV_VAR}

会从进程环境变量中展开，若变量不存在会报错。

Host a CrewAI crew:

5dive crew

托管CrewAI团队：

5dive crew

The box can run a CrewAI crew as a first-class workload: its own venv, BYO LLM key stored owner-600, durable memory on disk (

CREWAI_STORAGE_DIR

), and a co-signed receipt per run.

bash

sudo 5dive crew install <git-url> --as=<name> [--entry=<module:Crew>] [--branch=<b>]
sudo 5dive crew secret set <name> KEY=VALUE [KEY=VALUE ...]
sudo 5dive crew run <name>          # also: show <name> | list | uninstall <name>

主机可将CrewAI团队作为一等工作负载运行：拥有独立的虚拟环境，自定义LLM密钥存储权限为owner-600，磁盘持久化记忆（

CREWAI_STORAGE_DIR

），每次运行都会生成带签名的回执。

bash

sudo 5dive crew install <git-url> --as=<name> [--entry=<module:Crew>] [--branch=<b>]
sudo 5dive crew secret set <name> KEY=VALUE [KEY=VALUE ...]
sudo 5dive crew run <name>          # 其他命令：show <name> | list | uninstall <name>

Projects: group a multi-task effort under its own ident namespace

项目管理：将多任务工作分组到独立的命名空间

Open a project instead of filing a sprawl of loose

DIVE-N

tasks — a named task workspace with its own ident prefix and an optional lead:

bash

5dive project add frog --name="Frog migration" --goal="port the parser" \
  --lead-agent=worker-1 --json          # prefix defaults to the upper-cased key
5dive project ls --json                 # key, prefix, task count, lead, status
5dive project show frog --json

5dive task add "port the lexer" --project=frog --assignee=worker-1 --json
5dive task ls --project=frog --json

Everything else —

start

done

need

block

loop

heartbeat

— works identically on a project's tasks.

创建项目来管理一系列任务，而不是零散的

DIVE-N

任务——项目是一个命名的任务工作区，拥有独立的标识前缀，可指定负责人：

bash

5dive project add frog --name="Frog迁移项目" --goal="迁移解析器" \
  --lead-agent=worker-1 --json          # 前缀默认为大写的项目key
5dive project ls --json                 # 查看项目key、前缀、任务数量、负责人、状态
5dive project show frog --json

5dive task add "迁移词法分析器" --project=frog --assignee=worker-1 --json
5dive task ls --project=frog --json

其他所有操作——

start

done

need

block

loop

heartbeat

——对项目中的任务同样适用。

Task queue extras: park, escalate, bulk-clear, org writes

任务队列扩展：暂停、升级、批量清除、组织架构编辑

Quiet waits:
task park
. Sleep a task without putting it in the human inbox:

bash

5dive task park DIVE-12 --reason="revisit after launch" --wake=+3d --json
5dive task unpark DIVE-12 --json   # wake it early

Both

--reason

and

--wake

are REQUIRED (no block-graveyard). If you're actually waiting on a person, use

task need

instead;

park

also refuses over a task with a live

task need

gate.

--type=access
gates are for "I'm blocked on a permission I don't have" — pair with

--probe=<cmd>

(a self-check that must currently FAIL, so the gate isn't filed for something you already have):

bash

5dive task need DIVE-9 --type=access --probe="aws s3 ls s3://prod-bucket" \
  --ask="Need read access to prod-bucket" --recommend="grant s3:GetObject" --json

Precedent prefill. A gate filed with a blank

--recommend

looks for the closest answered precedent (same need type + ask shape, equal-or-higher tier, within 90 days) and prefills the recommendation, citing it on the alert — never overrides an explicit

--recommend

Flag for attention:

task escalate <id>

bumps priority a tier (capped at urgent) and pings the owner + paired human, without filing a gate.

Bulk-clear as the paired human:

task clear-recs --channel-proof=<chat_id> [--only=<id>]

clears every eligible low-risk gate (tier<2, has a

--recommend

) in one shot from a verified DM.

Who fronts the inbox:

task coordinator [--json]

prints the resolved org coordinator — the sole agent a surface should pin a needs-you banner to.

Org chart writes (reads live in

5dive-cli

core):

bash

5dive org set worker-1 --manager=lead --title="Auth audit" --json
5dive org show worker-1 --json     # manager + direct reports
5dive org ls --json                # flat list of everyone placed
5dive org rm worker-1 --json       # remove (reports re-parent to null)

Writes are root-only — the chart is trusted input to gate routing.

静默等待：
task park
。让任务进入休眠状态，不进入人工收件箱：

bash

5dive task park DIVE-12 --reason="发布后再处理" --wake=+3d --json
5dive task unpark DIVE-12 --json   # 提前唤醒任务

--reason

和

--wake

为必填参数（无永久阻塞的"墓地"）。如果需要等待人工处理，请使用

task need

；若任务存在活跃的

task need

环节，

park

命令会执行失败。

--type=access
环节用于"我因缺少权限而被阻塞"的场景——配合

--probe=<cmd>

参数（当前必须执行失败的自检命令，避免为已拥有的权限创建环节）：

bash

5dive task need DIVE-9 --type=access --probe="aws s3 ls s3://prod-bucket" \
  --ask="需要prod-bucket的读取权限" --recommend="授予s3:GetObject权限" --json

先例自动填充。如果创建环节时未指定

--recommend

，系统会查找最近的已处理先例（相同需求类型+请求格式、等级相同或更高、90天内），自动填充推荐内容，并在提醒中引用该先例——不会覆盖显式指定的

--recommend

。

标记为重点关注：
task escalate <id>
。将任务优先级提升一级（最高为紧急），并通知任务所有者和配对的人工用户，无需创建环节。

批量清除（仅配对人工用户可用）：
task clear-recs --channel-proof=<chat_id> [--only=<id>]
。从已验证的私信中一次性清除所有符合条件的低风险环节（等级<2、带有

--recommend

）。

谁负责收件箱：
task coordinator [--json]
。输出当前组织的协调人——即收件箱应绑定的唯一Agent。

组织架构编辑（读取操作在

5dive-cli

核心功能中）：

bash

5dive org set worker-1 --manager=lead --title="权限审计" --json
5dive org show worker-1 --json     # 查看上级主管+直接下属
5dive org ls --json                # 查看所有已配置的组织成员
5dive org rm worker-1 --json       # 删除成员（下属会重新归为无主管）

编辑操作仅root用户可用——组织架构是环节路由的可信输入。

Recurring work + waking workers: heartbeat

周期性任务与唤醒Agent：heartbeat

A recurring template materializes into a normal todo on schedule; the heartbeat wakes an enrolled agent only when it actually has queued work.

bash

5dive task add "rotate the weekly metrics digest" \
  --recurring="0 9 * * 1" --assignee=worker-1 --json
5dive task ls --recurring --json     # list templates

sudo 5dive heartbeat on worker-1 --every=30m   # default every=30m; fresh sends /clear per task
sudo 5dive heartbeat ls              # enrolled agents + next wake + queued count
sudo 5dive heartbeat off worker-1

Enrolment uses the agent's short name, the same name

task --assignee

expects. No catch-up for missed ticks — keep schedules coarse.

周期性模板会按计划生成普通任务；heartbeat仅在Agent有排队任务时才唤醒已注册的Agent。

bash

5dive task add "生成每周指标摘要" \
  --recurring="0 9 * * 1" --assignee=worker-1 --json
5dive task ls --recurring --json     # 查看所有周期性模板

sudo 5dive heartbeat on worker-1 --every=30m   # 默认每30分钟唤醒一次；每次唤醒会清除任务状态
sudo 5dive heartbeat ls              # 查看已注册Agent、下次唤醒时间、排队任务数量
sudo 5dive heartbeat off worker-1

注册时使用Agent的短名称，与

task --assignee

要求的名称一致。错过的周期不会补执行——建议设置较粗的时间粒度。

Loops: relay work across agents (+ human gates)

循环：跨Agent任务中继（+人工审核环节）

A loop chains agents into an auto-relay: each step hands off the moment its

task done

lands, and a human gate pauses the chain for a tap. You can build, edit, and inspect it conversationally.

bash

5dive task loop start --title="Content pipeline" --steps='[
  {"agent":"olivia","label":"Pick the topic and brief the writer","handoff":"briefs"},
  {"agent":"theo","label":"Draft the post","handoff":"sends to review"},
  {"gate":"approval","label":"You approve before it publishes"},
  {"agent":"theo","label":"Publish and close"}
]' --json

5dive task loop ls --json        # board of loop runs: per-run step progress + status

The relay creates one subtask per step, chained N+1-blocked-by-N under a run parent. To edit a running loop, act on its subtasks (

task ls

task assign

task block/unblock

task rm

, or slip in a

task need

gate); to stop it,

task rm

the run parent (cascades).

循环可将Agent链成自动中继：每个步骤在

task done

完成后立即移交任务，人工审核环节会暂停链条等待人工确认。你可以通过对话方式构建、编辑和查看循环。

bash

5dive task loop start --title="内容流水线" --steps='[
  {"agent":"olivia","label":"选择主题并给作者提供brief","handoff":"briefs"},
  {"agent":"theo","label":"撰写文章草稿","handoff":"提交审核"},
  {"gate":"approval","label":"你需要在发布前审核"},
  {"agent":"theo","label":"发布并关闭任务"}
]' --json

5dive task loop ls --json        # 查看所有循环运行状态：每个循环的步骤进度+状态

中继会为每个步骤创建一个子任务，在父任务下按N+1依赖于N的方式链式关联。要编辑运行中的循环，可操作其子任务（

task ls

、

task assign

、

task block/unblock

、

task rm

，或插入

task need

环节）；要停止循环，删除父任务即可（会级联删除所有子任务）。

Maker→verifier loops: the writer never grades itself

创作者→审核者循环：作者不自评

Verification is on by default for non-trivial tasks (a grader distinct from the maker);

--no-verify

opts out. To pin a specific grader:

bash

5dive task add "migrate the auth module to the new SDK" \
  --assignee=dario --verifier=marcus --max-iters=3 \
  --accept="builds clean, tests pass, no public API change" --json

5dive task reject DIVE-7 --feedback="tests pass but the public signature changed" --json

对于非 trivial 的任务，默认启用审核机制（审核者与创作者不同）；

--no-verify

参数可关闭审核。要指定特定审核者：

bash

5dive task add "将权限模块迁移到新SDK" \
  --assignee=dario --verifier=marcus --max-iters=3 \
  --accept="编译通过、测试通过、无公共API变更" --json

5dive task reject DIVE-7 --feedback="测试通过但公共签名变更" --json

-> bounces back to the maker; escalates to a human at --max-iters.

-> 将任务退回给创作者；达到--max-iters次数时升级给人工处理。

5dive task loops --json # board of maker→verifier loops (--stuck / --escalate-stuck) 5dive task loops --runs --json # loop_runs control window: topology/stage/iteration/ceiling


`5dive task verifier <id> <agent> [--accept=<criteria>] [--max-iters=<n>]`
attaches the rail to an already-filed task. Once delivered, `task done` is
refused from anyone but the verifier — send corrections there instead. If
the work ships as a PR, `5dive task deliver <id> --pr=<url> [--result=<text>]`
hands off to the verifier without closing; `task done` then refuses to close
until that PR is merged and green (`--force-merge-gate` overrides false
positives).

5dive task loops --json # 查看创作者→审核者循环列表（--stuck / --escalate-stuck可筛选） 5dive task loops --runs --json # 循环运行控制窗口：拓扑/阶段/迭代次数/上限


`5dive task verifier <id> <agent> [--accept=<criteria>] [--max-iters=<n>]`可给已创建的任务添加审核环节。任务交付后，只有审核者可以执行`task done`——请将修正内容发送给审核者。如果工作成果是PR，`5dive task deliver <id> --pr=<url> [--result=<text>]`会将任务移交给审核者但不关闭；`task done`会拒绝关闭，直到PR合并且状态为绿色（`--force-merge-gate`可覆盖误判）。

LOOP-7: agent-native orchestration verbs

LOOP-7：Agent原生编排指令

Lower-level than the relay above — JSON in/out, each verb spawns/grades agents directly and honors

--ceiling

(self-halts + escalates at the limit). Humans watch/kill via

task loops --kill <loopId>

; they never author a loop.

bash

5dive loop spawn --role=maker|verifier|worker --agent=<type|name> \
  --prompt="…" [--schema=<json>] [--ceiling=<tok>] [--wait[=<sec>]]
5dive loop verify --target=<id> --verifier=<agent> [--accept="…"]
5dive loop grade  --target=<id> --verifier=<agent> [--accept="…"] [--threshold=0-100] [--wait]
5dive loop panel  --n=<k> --lens="correctness,security" --claim="…" --quorum=<m>   # jury
5dive loop map    --over=<json-array> --do=<spawn-spec> [--max-concurrency=<n>]    # fan-out
5dive loop until-dry --round=<spawn-spec> --stop-after=<K> --dedup-key="…"         # drain a queue
5dive loop collect --handles=<id,id,…>       # gather results from spawned handles
5dive loop status  --handle=<loopId>         # read-only single-loop drilldown
5dive loop install <slug> --onto=<agent> [--cron="…"] [--ceiling=<tok>] [--dry-run]

比上述中继更底层——JSON输入输出，每个指令直接生成/评分Agent，并遵守

--ceiling

限制（达到限制时自动停止并升级给人工）。人工可通过

task loops --kill <loopId>

查看/终止循环；人工无法创建循环。

bash

5dive loop spawn --role=maker|verifier|worker --agent=<type|name> \
  --prompt="…" [--schema=<json>] [--ceiling=<tok>] [--wait[=<sec>]]
5dive loop verify --target=<id> --verifier=<agent> [--accept="…"]
5dive loop grade  --target=<id> --verifier=<agent> [--accept="…"] [--threshold=0-100] [--wait]
5dive loop panel  --n=<k> --lens="correctness,security" --claim="…" --quorum=<m>   # 评审团
5dive loop map    --over=<json-array> --do=<spawn-spec> [--max-concurrency=<n>]    # 扇出
5dive loop until-dry --round=<spawn-spec> --stop-after=<K> --dedup-key="…"         # 清空队列
5dive loop collect --handles=<id,id,…>       # 收集已生成Agent的结果
5dive loop status  --handle=<loopId>         # 只读：查看单个循环的详细状态
5dive loop install <slug> --onto=<agent> [--cron="…"] [--ceiling=<tok>] [--dry-run]

Goals: decompose an outcome into a task graph

目标管理：将结果分解为任务图

5dive goal add

turns a one-line outcome into a validated, guardrailed task DAG (checked for acyclicity, size/depth caps, tier-floor, assignability before anything is created). Over the count checkpoint or carrying any Tier-2 task, ONE decision gate holds the plan.

bash

5dive goal add "ship a public status page" --dry-run --json   # plan + render, create NOTHING
5dive goal add "ship a public status page" --json \
  [--project=<key>] [--planner=<agent>] [--max-tasks=12] [--depth-cap=5] \
  [--checkpoint=6] [--ceiling=40000] [--yes]
5dive goal add --from-gate=<id> --json    # materialize a plan a HUMAN answered 'approve'

goal add

is async by default: it returns immediately with a job id after spawning the planner (unless the planner is already idle, in which case it may return the finished result inline). Poll with:

bash

5dive goal status <job>   # queued | running | done (plan/gated/materialized) | failed

Pass

--wait

for the legacy bounded-block behavior in scripts, or

--plan=<json>

to skip the planner entirely. Always

--dry-run

first to eyeball the plan.

5dive goal add

可将一行描述的结果转换为经过验证、受管控的任务DAG（在创建前会检查是否有环、大小/深度限制、最低等级、可分配性）。当任务数量超过检查点或包含Tier-2任务时，会创建一个决策环节来管控计划。

bash

5dive goal add "上线公共状态页面" --dry-run --json   # 生成并展示计划，不实际创建
5dive goal add "上线公共状态页面" --json \
  [--project=<key>] [--planner=<agent>] [--max-tasks=12] [--depth-cap=5] \
  [--checkpoint=6] [--ceiling=40000] [--yes]
5dive goal add --from-gate=<id> --json    # 基于人工批准的环节生成计划

goal add

默认是异步的：生成规划Agent后立即返回任务ID（除非规划Agent已空闲，此时可能直接返回完成的结果）。可通过以下命令轮询状态：

bash

5dive goal status <job>   # 状态：queued | running | done (plan/gated/materialized) | failed

在脚本中可使用

--wait

参数实现传统的阻塞行为，或使用

--plan=<json>

参数跳过规划环节。建议先执行

--dry-run

查看计划。

Objectives: a standing goal bound to a live metric

目标监控：绑定实时指标的长期目标

5dive objective

is different from

goal

: a standing target tied to a read-only metric command re-measured each

tick

, for tracking a number you want to move rather than decomposing work.

bash

5dive objective add "warm pool >= 1" --metric-cmd="5dive ps --warm --json | jq length" \
  --target=1 --direction=up [--unit=count] [--public]
5dive objective ls | show <name> | tick [<name>] | pause <name> | rm <name>
5dive objective resume <name> [--force]   # --force bypasses a preflight refusal

Self-steer it:

objective replan <name>

drives one cycle — a planner proposes a diff (new/reprioritized/cancelled tasks) toward the target, validated like a

goal add

plan:

bash

5dive objective replan warm-pool --dry-run --json     # see the proposed diff, create nothing
5dive objective replan warm-pool --json \
  [--max-new-per-cycle=3] [--no-progress-limit=3] [--yes] [--from-gate=<id>]

--yes

waives only the count-over-checkpoint gate — a Tier-2 task in the diff still hard-gates. Always

--dry-run

a replan first.

5dive objective

与

goal

不同：它是绑定只读指标命令的长期目标，每个

tick

会重新测量指标，用于跟踪你想要改变的数值，而非分解工作。

bash

5dive objective add "热池数量 >= 1" --metric-cmd="5dive ps --warm --json | jq length" \
  --target=1 --direction=up [--unit=count] [--public]
5dive objective ls | show <name> | tick [<name>] | pause <name> | rm <name>
5dive objective resume <name> [--force]   # --force参数可绕过预检查拒绝

自驱调整：
objective replan <name>
。执行一轮调整——规划Agent会提出一个朝向目标的变更方案（新增/重新排序/取消任务），并像

goal add

计划一样进行验证：

bash

5dive objective replan warm-pool --dry-run --json     # 查看变更方案，不实际创建
5dive objective replan warm-pool --json \
  [--max-new-per-cycle=3] [--no-progress-limit=3] [--yes] [--from-gate=<id>]

--yes

仅跳过数量超过检查点的环节——变更方案中的Tier-2任务仍会触发强制环节。建议先执行

--dry-run

查看变更方案。

Governance votes:

5dive council

治理投票：

5dive council

For decisions that should be a recorded vote rather than one agent's call — membership motions, constitutional amendments, or routing an open gate to a deliberation:

bash

5dive council convene "<question>" [--seats=a,b,c] [--mode=quick|deliberate|adversarial]
                                   [--bench=<name>] [--class=<decisionClass>] [--timeout=120]
5dive council gate-clear <task|DIVE-N> [--mode=deliberate] [--seats=a,b,c] [--dry-run]
5dive council schedule add <name> --question="<template>" --cron="<m h dom mon dow>"
5dive council schedule ls | show <name> | rm <name> | run <name> [--dry]

5dive council roster --json    # current seats, threshold + quorum, veto holder
5dive council log --limit=20 --json    # sealed verdict history
5dive council verify [<receipt-digest>]   # re-seal + hash-chain check, fails closed on tamper

convene

dispatches to the real seated agents (each votes via its own harness, blind first round) and seals an auditable, tamper-evident verdict.

gate-clear

routes an open tier-1 gate to the council — a tier-2 or human-only-type gate is never self-cleared, always bumped to a human. Writes (

init

promote

demote

expel

bench add/rm

schedule add/rm

) are sudo-gated; reads (

roster

log

verify

record

) are not. Reach for council deliberately, not as a substitute for a normal

task need

gate.

对于需要记录投票而非单个Agent决策的场景——成员变动、章程修改、将开放环节路由到审议：

bash

5dive council convene "<问题>" [--seats=a,b,c] [--mode=quick|deliberate|adversarial]
                                   [--bench=<name>] [--class=<decisionClass>] [--timeout=120]
5dive council gate-clear <task|DIVE-N> [--mode=deliberate] [--seats=a,b,c] [--dry-run]
5dive council schedule add <name> --question="<模板>" --cron="<m h dom mon dow>"
5dive council schedule ls | show <name> | rm <name> | run <name> [--dry]

5dive council roster --json    # 当前成员、阈值+法定人数、否决权持有者
5dive council log --limit=20 --json    # 密封的投票历史
5dive council verify [<receipt-digest>]   # 重新密封+哈希链检查，篡改时会失败

convene

会将投票发送给实际成员（每个成员通过自己的工具投票，第一轮为盲投），并生成可审计、防篡改的投票结果。

gate-clear

会将开放的tier-1环节路由到理事会——tier-2或仅人工处理的环节永远不会自动清除，会直接升级给人工。写入操作（

init

、

promote

demote

expel

、

bench add/rm

、

schedule add/rm

）需要sudo权限；读取操作（

roster

、

log

、

verify

、

record

）不需要。请谨慎使用理事会，不要将其作为

task need

环节的替代品。

Delegated push:

5dive push

委托推送：

5dive push

An agent created with

--can-push

(needs

--isolation=standard

, the default) can push ONE named feature branch for PR review once its task's gate is cleared and bound to that branch:

bash

5dive push DIVE-42 [--branch=<b>] [--dry-run]
sudo 5dive push setup   # once per box: scaffold the GitHub App config

The agent's own process never touches a GitHub token; a root-only helper mints one scoped to just that repo, pushes, and discards it.

使用

--can-push

参数创建的Agent（需要

--isolation=standard

，默认配置），在任务环节清除并绑定到指定分支后，可推送一个命名的功能分支用于PR评审：

bash

5dive push DIVE-42 [--branch=<b>] [--dry-run]
sudo 5dive push setup   # 每台主机执行一次：初始化GitHub App配置

Agent自身进程永远不会接触GitHub令牌；仅root用户可用的辅助工具会生成仅针对该仓库的令牌，推送后立即丢弃。

Company wizard:

5dive company

公司入门向导：

5dive company

bash

5dive company --yes --name=<n> --objective="<outcome>" --metric-cmd="<cmd>" \
  --target=<n> --direction=up|down

Sugar over

project add

objective add

(+ optional

goal add

) — stands up a whole self-steering project namespace in one call. Bare (TTY) walks an interactive wizard.

bash

5dive company --yes --name=<n> --objective="<结果>" --metric-cmd="<命令>" \
  --target=<n> --direction=up|down

是

project add

objective add

（可选

goal add

）的简化操作——一次调用即可创建完整的自驱项目命名空间。不带参数时（交互式终端）会启动交互式向导。

Compile durable knowledge:

memory add

+ hygiene

编译持久化知识：

memory add

+ 维护

The

memory search

read-path (core) has a write twin — the CLI behind "compile before you close." Body on stdin:

bash

echo "$BODY" | 5dive memory add --name=hetzner-cpx-drought \
  --description="cpx line delisted post price-hike; cx dry-run false-positive" \
  --type=reference --store=wiki --tags=hetzner,capacity \
  [--valid-to=2026-12-31] [--supersedes=<slug>] [--confidence=high] [--provenance="<src>"]

5dive memory doctor --json   # hygiene: index drift, dangling [[links]], stale refs, near-dupes

Writes into your own store (or the shared team wiki with

--store=wiki

, the path teammates can search), stamps provenance, and appends the store's index line. A token/key tripwire refuses secret-shaped bodies (

--force

does NOT bypass it). More read-path flags:

--limit=N --max-tokens=T --roots=a,b --store=all|mine|wiki --agent=<name>

(another agent's store, root-only).

memory search

读取功能（核心功能）对应的写入功能——即"关闭前编译"的CLI命令。从标准输入读取内容：

bash

echo "$BODY" | 5dive memory add --name=hetzner-cpx-drought \
  --description="cpx系列因涨价下架；客户预演出现误报" \
  --type=reference --store=wiki --tags=hetzner,capacity \
  [--valid-to=2026-12-31] [--supersedes=<slug>] [--confidence=high] [--provenance="<来源>"]

5dive memory doctor --json   # 维护：索引漂移、无效[[链接]]、过期引用、近似重复内容

写入到你自己的存储（或使用

--store=wiki

写入共享团队Wiki，可供团队成员搜索），标记来源，并添加到存储的索引中。系统会拒绝包含密钥/令牌格式的内容（

--force

参数无法绕过）。更多读取参数：

--limit=N --max-tokens=T --roots=a,b --store=all|mine|wiki --agent=<name>

（查看其他Agent的存储，仅root用户可用）。

Read the fleet: digest, usage, supervisor

查看集群状态：摘要、使用情况、监控

Read-only surfaces, no agent reasoning, no tokens burned. usage
/
cost
/
activity
require an admin (sudo) agent even for reads:

bash

5dive digest --json          # standup: shipped/in-progress/gates/token burn (--7d widens)
sudo 5dive digest --send     # deliver to the paired Telegram chat
sudo 5dive digest on --at=7  # opt in to daily auto-delivery (default OFF); off | status

sudo 5dive usage --json           # board: top agents + top tasks, 24h (--7d)
sudo 5dive usage worker-1 --json  # one agent: per-model + per-task breakdown
sudo 5dive cost --json            # per-agent 24h burn vs soft/ceiling + state
sudo 5dive activity worker-1 --json    # files touched, commands run, cost (--task=DIVE-N, --7d)
sudo 5dive usage loops --json     # spend rolled up per loop / topology
sudo 5dive usage budget set worker-1 --daily=2000000 [--ceiling=<tok>] [--hard-stop]
sudo 5dive usage budget ls        # all budgets; `budget clear worker-1` removes one

sudo 5dive supervisor              # per-agent state, classification, cause, last activity
sudo 5dive supervisor --watch      # live repaint (default 5s)

Check

usage

account usage

before blaming quota for a failure; check

supervisor

before restarting an agent on a hunch.

只读界面，无需Agent推理，不会消耗Token。usage
/
cost
/
activity
命令需要管理员（sudo）权限的Agent，即使是读取操作：

bash

5dive digest --json          # 每日站会：已完成/进行中/环节/Token消耗（--7d可查看7天数据）
sudo 5dive digest --send     # 发送到配对的Telegram聊天
sudo 5dive digest on --at=7  # 开启每日自动发送（默认关闭）；off | status可关闭/查看状态

sudo 5dive usage --json           # 看板：Top Agent + Top任务，24小时数据（--7d可查看7天）
sudo 5dive usage worker-1 --json  # 单个Agent：按模型+任务的消耗明细
sudo 5dive cost --json            # 单个Agent24小时消耗 vs 软限制/上限 + 状态
sudo 5dive activity worker-1 --json    # 操作的文件、执行的命令、消耗（--task=DIVE-N可查看指定任务，--7d可查看7天）
sudo 5dive usage loops --json     # 按循环/拓扑汇总的消耗
sudo 5dive usage budget set worker-1 --daily=2000000 [--ceiling=<tok>] [--hard-stop]
sudo 5dive usage budget ls        # 查看所有预算；`budget clear worker-1`可删除单个预算

sudo 5dive supervisor              # 单个Agent状态、分类、原因、最后活动时间
sudo 5dive supervisor --watch      # 实时刷新（默认5秒）

在因配额问题排查故障前，请先检查

usage

account usage

；在凭直觉重启Agent前，请先检查

supervisor

。

Control other boxes:

5dive fleet

控制其他主机：

5dive fleet

A fleet registry maps box names to SSH targets (references only — never key material):

bash

sudo 5dive fleet add prod-2 --host=1.2.3.4 --key=/home/claude/.ssh/id_ed25519
5dive fleet ls
5dive fleet status --json          # per-box reachability + agent counts (parallel SSH)
5dive fleet agents --json          # every agent across the fleet, one view
5dive fleet send scout@prod-2 "status report please"
5dive fleet restart scout@prod-2

One unreachable box never fails the whole view.

add

rm

need root; the read surfaces don't.

集群注册表将主机名称映射到SSH目标（仅引用——不存储密钥）：

bash

sudo 5dive fleet add prod-2 --host=1.2.3.4 --key=/home/claude/.ssh/id_ed25519
5dive fleet ls
5dive fleet status --json          # 查看每台主机的可达性+Agent数量（并行SSH）
5dive fleet agents --json          # 查看集群中所有Agent的统一视图
5dive fleet send scout@prod-2 "请发送状态报告"
5dive fleet restart scout@prod-2

单台主机不可达不会影响整个视图。

add

rm

命令需要root权限；读取界面不需要。

Diagnose a sick host

诊断主机故障

bash

sudo 5dive doctor --json

Envelope is always

{ ok: true, data: { summary, checks } }

with exit 0. Branch on

data.summary.errors > 0

. Add

--fix

(alias

--repair

) to attempt reversible fixes;

--dry-run

previews them. Narrow with

--category=deps|types|auth|creds|registry|shelld|channels|host|memory

bash

5dive selfcheck --json                # proves gate delivery, audit log, bundle integrity,
                                       # scorecard FOR REAL in an isolated sandbox
sudo 5dive agent stats --all --json   # whole fleet: unit state, restarts, health
5dive update --check --json           # is the CLI behind/stale? read-only, no root
5dive trace <id|DIVE-N>               # causal timeline: goal/parent/objective/loop -> ship -> verdict
5dive models --json                   # live model id per alias (opus/sonnet/fable/haiku)
sudo 5dive watch                      # htop-style live view (interactive TTY only)

Treat any

selfcheck

"not-reached" probe as "unmeasured here", not "fine".

5dive self-update

upgrades the CLI + plugins and restarts every agent on the host — never run it casually from an agent session.

bash

sudo 5dive doctor --json

输出格式始终为

{ ok: true, data: { summary, checks } }

，退出码为0。可根据

data.summary.errors > 0

判断是否有错误。添加

--fix

（别名

--repair

）参数可尝试可逆修复；

--dry-run

参数可预览修复操作。可使用

--category=deps|types|auth|creds|registry|shelld|channels|host|memory

参数缩小诊断范围。

bash

5dive selfcheck --json                # 在隔离沙箱中验证环节交付、审计日志、包完整性、评分卡
                                       # 真实结果
sudo 5dive agent stats --all --json   # 整个集群：单元状态、重启次数、健康状况
5dive update --check --json           # 检查CLI是否过时？只读操作，无需root权限
5dive trace <id|DIVE-N>               # 因果时间线：目标/父任务/监控目标/循环 -> 交付 -> 结果
5dive models --json                   # 每个别名对应的实时模型ID（opus/sonnet/fable/haiku）
sudo 5dive watch                      # htop风格的实时视图（仅交互式终端支持）

将

selfcheck

中"not-reached"的探针视为"未在此处测量"，而非"正常"。

5dive self-update

会升级CLI+插件，并重启主机上的所有Agent——请勿在Agent会话中随意执行该命令。

Reference

参考

See

5dive-cli

references/commands.md

exit-codes.md

, and

paths.md

for full flag detail, and

sudo 5dive --help

sudo 5dive <noun> --help

as the ultimate authority if a flag here is rejected.

Synced to 5dive CLI 0.17.2 (2026-07-29).

请查看

5dive-cli

的

references/commands.md

、

exit-codes.md

和

paths.md

获取完整的参数说明，如果此处的参数被拒绝，请以

sudo 5dive --help

sudo 5dive <noun> --help

的输出为准。

同步至5dive CLI 0.17.2（2026-07-29）。

5dive-cli-extras

Original

Translation

5dive-cli-extras

5dive-cli-extras

Advanced agent create: personas, BYO providers, auth deferral

进阶Agent创建：角色定制、自定义提供商、延迟授权

Hire a ready-made persona from the agent market

从Agent市场雇佣现成角色

Create-then-auth: --defer-auth

创建后授权：--defer-auth

BYO API key: --provider (hermes / openclaw / claude)

自定义API密钥：--provider（hermes / openclaw / claude）

Tune a running claude agent: model + effort

调整运行中的Claude Agent：模型与算力

effort: low|medium|high|xhigh|max — claude only; xhigh/max are Opus-tier.

effort取值：low|medium|high|xhigh|max — 仅Claude支持；xhigh/max为Opus等级专属

Recover from auth_required

从auth_required错误中恢复

If create fails with error.class=auth_required, the type isn't authenticated.

如果创建Agent时出现error.class=auth_required错误，说明该类型未完成授权。

A) Static API key in $KEY (preferred for automation)

A) 从环境变量$KEY读取静态API密钥（自动化场景首选）

B) Device-code flow (when only a human can complete login)

B) 设备码流程（仅人工可完成登录）

-> session id; give the URL from auth poll to the user; they paste the

-> 返回会话ID；将auth poll返回的URL提供给用户，用户粘贴回调码后执行auth submit完成登录。

callback code back via auth submit.

Multi-account: the account noun

多账号管理：account指令

Telegram/Discord pairing and shared team bot

Telegram/Discord配对与共享团队机器人

Classic — return a pairing code, user DMs the bot, paste the bot reply.

经典方式 — 返回配对码，用户向机器人发送私信，粘贴机器人回复的内容完成配对。

Auto-detect — long-poll for the next inbound message, seed access.json.

自动检测 — 长轮询下一条入站消息，生成access.json。

Bot identity for a tappable deep link.

获取机器人身份，用于生成可点击的深度链接。

Shared team bot: one bot, every agent

共享团队机器人：一个机器人，所有Agent共用

Delegating a request that came in over a channel — full walkthrough

转发通过渠道收到的请求——完整流程

Declarative fleets: compose + team templates

声明式Agent集群：组合与团队模板

Host a CrewAI crew: 5dive crew

托管CrewAI团队：5dive crew

Projects: group a multi-task effort under its own ident namespace

项目管理：将多任务工作分组到独立的命名空间

Task queue extras: park, escalate, bulk-clear, org writes

任务队列扩展：暂停、升级、批量清除、组织架构编辑

Recurring work + waking workers: heartbeat

周期性任务与唤醒Agent：heartbeat

Loops: relay work across agents (+ human gates)

循环：跨Agent任务中继（+人工审核环节）

Maker→verifier loops: the writer never grades itself

创作者→审核者循环：作者不自评

-> bounces back to the maker; escalates to a human at --max-iters.

-> 将任务退回给创作者；达到--max-iters次数时升级给人工处理。

LOOP-7: agent-native orchestration verbs

LOOP-7：Agent原生编排指令

Goals: decompose an outcome into a task graph

目标管理：将结果分解为任务图

Objectives: a standing goal bound to a live metric

目标监控：绑定实时指标的长期目标

Governance votes: 5dive council

治理投票：5dive council

Delegated push: 5dive push

委托推送：5dive push

Company wizard: 5dive company

公司入门向导：5dive company

Compile durable knowledge: memory add + hygiene

编译持久化知识：memory add + 维护

Read the fleet: digest, usage, supervisor

查看集群状态：摘要、使用情况、监控

Control other boxes: 5dive fleet

控制其他主机：5dive fleet

Diagnose a sick host

诊断主机故障

Reference

参考

Create-then-auth:
`--defer-auth`

创建后授权：
`--defer-auth`

BYO API key:
`--provider`
(hermes / openclaw / claude)

自定义API密钥：
`--provider`
（hermes / openclaw / claude）

Recover from
`auth_required`

从
`auth_required`
错误中恢复

-> session id; give the URL from
`auth poll`
to the user; they paste the

-> 返回会话ID；将
`auth poll`
返回的URL提供给用户，用户粘贴回调码后执行
`auth submit`
完成登录。

callback code back via
`auth submit`
.

Multi-account: the
`account`
noun

多账号管理：
`account`
指令

Host a CrewAI crew:
`5dive crew`

托管CrewAI团队：
`5dive crew`

Governance votes:
`5dive council`

治理投票：
`5dive council`

Delegated push:
`5dive push`

委托推送：
`5dive push`

Company wizard:
`5dive company`

公司入门向导：
`5dive company`

Compile durable knowledge:
`memory add`
+ hygiene

编译持久化知识：
`memory add`
+ 维护

Control other boxes:
`5dive fleet`

控制其他主机：
`5dive fleet`