Token导航 LogoToken导航TokenDH.com
研究检索操作浏览器clawhub未标认证来源可访问clear审计通过

multi-agent-protocol多 Agent 协议

Agent Skill

multi-agent-protocol 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

8,411

周安装

347

GitHub Stars

公开资料未说明

下载量

2,748
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:multi-agent-protocol(多 Agent 协议)
来源仓库:https://github.com/hakityc/multi-agent-protocol
安装命令:
openclaw skills install multi-agent-protocol
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install multi-agent-protocol

简介

OpenClaw 原生 v2 协议,规范优先的多代理交付流程。

  • 适用于需双重审查门、有界重试与 CI 集成的复杂代理协作。
  • 支持显式阶段控制与优先级调度,确保关键任务及时完成。
  • 安装命令为 openclaw skills install multi-agent-protocol,需统一各节点协议版本。
  • 使用前应配置审计日志与告警机制,便于事后追溯与合规审查。

SKILL.md

name
multi-agent-protocol
description
>

Multi-Agent Protocol v2

OpenClaw-native multi-agent protocol. Keep the good parts from v1:

  • spec-first
  • review gates
  • retry with circuit breaker

Replace the brittle parts from v1:

  • no fixed sessionKey memory contract
  • no shared/blackboard.json
  • no undeclared beads or git dependency
  • no prompt-only state machine
  • no LangGraph

Architecture

Use the stack below and do not silently swap layers:

  1. SKILL.md

Defines protocol, roles, dependency expectations, and non-negotiable rules.

  1. OpenProse

Owns orchestration flow and agent dispatch.

  1. Lobster

Owns approval, pause/resume, and side-effect recovery templates.

  1. task-store plugin

Owns authoritative task state via typed tools + SQLite event log.

  1. ACP

Connects external coding harnesses such as Codex.

Source Of Truth

The source of truth is the task-store plugin, not prompts and not reviewer output.

  • Canonical task phase lives in SQLite.
  • Every phase change is an event.
  • Reviewers append findings and verdicts.
  • Reviewers do not finalize phase transitions.
  • The orchestrator is the only actor that decides phase movement.

Required Dependencies

Declare these dependencies explicitly in the skill or the workflow setup:

  • OpenClaw runtime with OpenProse
  • Lobster runtime for approval/resume
  • task-store plugin enabled
  • local SQLite availability
  • ACP bridge when external harnesses are involved

Optional, but explicit when used:

  • git
  • browser/runtime plugins
  • language-specific build tools

Do not assume:

  • beads
  • bd
  • shared/blackboard.json
  • persistent role memory through fixed sessions
  • git worktree

Core Rules

1. Spec-first

No execution phase starts before a spec record exists in task-store.

Minimum spec payload:

  • goal
  • scope_in
  • scope_out
  • inputs
  • outputs
  • acceptance_criteria[]
  • risks[]

If acceptance criteria are weak or missing, the orchestrator keeps the task in spec_draft.

2. Phase transitions are explicit

Use a stored phase enum. Recommended baseline:

spec_draft
spec_review
execution_ready
executing
spec_gate
quality_gate
awaiting_approval
ready_to_resume
completed
failed
circuit_open

All transitions must be written through task_transition.

3. Reviewers are evidence producers

Reviewer output is evidence, not authority.

  • Spec reviewer answers: "Does the artifact satisfy the spec?"
  • Quality reviewer answers: "Is the implementation acceptable for maintainability and risk?"
  • Reviewers write findings via task_append_review.
  • The orchestrator reads review state and decides the next phase.

4. Retry and circuit breaker are stored state

Retries are not tracked in free text.

  • attempt counters live in SQLite
  • retry reasons are evented
  • circuit state is explicit

Recommended policy:

  • attempt 1-2: retry same phase with bounded backoff
  • attempt 3: optional stronger model/runtime
  • attempt >= 4: circuit_open

5. Side effects require Lobster gates

Any real-world effect should pass through Lobster:

  • writing to external systems
  • approvals
  • irreversible file mutations outside the declared sandbox
  • deployments
  • notifications
  • merges

Lobster pauses, requests approval, and resumes from persisted state.

6. ACP is the bridge for external harnesses

When using Codex or another external coding harness:

  • launch work through ACP, not prompt-only relays
  • pass task_id, attempt_id, workspace, and allowed capabilities
  • capture external session metadata as non-authoritative references

Practical note inferred from the local OpenClaw installation: parent streaming features such as streamTo are tied to runtime=acp, not generic subagent runtime. Design the workflow accordingly.

Role Model

Orchestrator

The orchestrator:

  • creates the task record
  • validates spec completeness
  • dispatches agents
  • reads stored findings
  • decides phase transitions
  • triggers Lobster when approval or recovery is needed
  • opens the circuit when retries are exhausted

The orchestrator does not become a passive message relay or free-form blackboard parser.

Executor

The executor may be:

  • a local OpenClaw worker
  • an ACP-backed external harness such as Codex
  • a read-only research agent

Executor responsibilities:

  • produce artifacts
  • record attempt heartbeat/checkpoints through typed tools
  • report structured outputs and evidence

Executor cannot finalize completed, failed, or gate transitions on its own.

Spec Reviewer

Reads the actual artifact and records one of:

  • approved
  • changes_requested
  • blocked

Plus findings with file references or artifact references.

Quality Reviewer

Reads the actual artifact after spec gate passes and records:

  • maintainability concerns
  • test gaps
  • safety or regression risk
  • approval/rework recommendation

Lobster Approver / Recovery Actor

Lobster manages:

  • approval prompts
  • pause/resume after interruption
  • resuming idempotent or compensating side-effect steps

Lobster does not own the business workflow phase. It only writes approval state and recovery evidence back to task-store.

Minimal Lifecycle

task_create
  -> spec_review
  -> execution_ready
  -> executing
  -> spec_gate
  -> quality_gate
  -> awaiting_approval (only if side effects exist)
  -> ready_to_resume
  -> completed

Failure branches:

executing -> retrying -> executing
executing -> circuit_open
spec_gate -> execution_ready
quality_gate -> execution_ready
awaiting_approval -> failed

Protocol By Phase

spec_draft

  • Create task in task-store.
  • Persist full spec content or spec reference.
  • Do not spawn builders yet.

spec_review

  • Reviewer checks the spec itself for ambiguity and testability.
  • Orchestrator either:

- fixes the spec and stays in spec_draft, or - transitions to execution_ready

execution_ready

  • Orchestrator chooses runtime:

- local worker for low-side-effect or local tasks - ACP for Codex/external harness

  • Orchestrator creates a new attempt record.

executing

  • Executor works only against declared inputs/outputs.
  • Checkpoints go through typed tools.
  • Side effects are declared ahead of time as planned actions.

spec_gate

  • Spec reviewer inspects produced artifact.
  • Reviewer writes findings only.
  • Orchestrator decides:

- pass to quality_gate - rework back to execution_ready - open circuit if repeated mismatch indicates spec or implementation collapse

quality_gate

  • Quality reviewer records findings only.
  • Orchestrator decides:

- completed - execution_ready - awaiting_approval

awaiting_approval

  • Lobster requests human approval with structured context.
  • Approved result becomes evidence in store.
  • Orchestrator transitions to ready_to_resume.

ready_to_resume

  • Lobster or orchestrator resumes the exact side-effect step using persisted idempotency data.

circuit_open

  • Stop automatic retries.
  • Surface:

- failure summary - attempts - last known good artifact - unblock options

What Goes In Storage

The task-store plugin should persist at least:

  • task header
  • current phase
  • spec payload or reference
  • review records
  • attempt records
  • artifact records
  • approval records
  • event log
  • optional external session references

The plugin storage is authoritative. Prompt text is not.

OpenProse Guidance

The .prose workflow should be minimal and boring:

  • read state
  • branch on typed state
  • dispatch one actor
  • store result
  • decide next phase

Do not encode business state only in the prose graph. The graph coordinates. The plugin stores.

Read workflows/openclaw-native-v2.prose when wiring the workflow.

Lobster Guidance

Use Lobster only where it adds hard guarantees:

  • approval request with resumable context
  • idempotent recovery after interruption
  • controlled side-effect replay

Read lobster/approval-recovery.template.yaml when a task contains side effects or human approval.

Plugin Guidance

Use the task-store plugin as the only write path for protocol state.

Read references/task-store-plugin.md when:

  • implementing the plugin
  • validating tool shapes
  • deciding schema changes

Permissions

Use least privilege. The matrix lives in references/agent-permissions.md.

Key rule:

  • executors can write artifacts and attempts
  • reviewers can write findings
  • only orchestrator can move the phase

Migration Rules From v1

Read references/migration.md before replacing an existing v1 setup.

Summary:

  • replace fixed session identity with run-scoped attempt_id and optional external_session_ref
  • replace blackboard with typed storage
  • replace beads/git buses with plugin tools
  • replace reviewer-led state changes with orchestrator-led transitions

Quick Start

  1. Enable task-store.
  2. Create a task with a full spec.
  3. Run the OpenProse workflow.
  4. Route external coding work through ACP.
  5. Use Lobster only for approval/recovery steps.
  6. Let orchestrator decide every phase transition from stored evidence.

Anti-Patterns

Do not do any of the following:

  • use fixed role sessionKey as the memory backbone
  • store canonical state in shared/blackboard.json
  • let reviewer verdict directly close the task
  • let executor mutate final phase
  • assume git or beads exists without declaring it
  • recover from interruption by guessing from prompt history
  • add LangGraph just to simulate a state machine already held in SQLite

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

76.84%
按下载量换算2,112

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills