YaoleWu/agent-loop-workflow

LeslieWylie/agent-loop-workflow

面向 DeepSeek Harness、与具体项目无关的多智能体协作协议:阻止失控循环的循环守卫、六字段交接格式、按风险分级的评审路由,以及固定的验证→提交→推送→评审→关闭流程。用一个 skill 取代复制粘贴进每个 agent 指令里的相同规则。

工作流与自动化agentscollaborationdeepseek-harness

agent-loop-workflow · Multi-Agent Collaboration Workflow Skeleton

简体中文

What is this

A project-agnostic multi-agent collaboration workflow skeleton. Any agent squad composed of DRI + reviewer + lead + ops can load it to get consistent workflow rules, without duplicating them across every agent's instructions.

Core Capabilities

ModuleContent
Role TopologyDRI (doer), reviewer, lead (decision/routing), ops (automation) — four roles with clear responsibility boundaries
Loop Guard (6 invariants)Turn limit, progress stall detection, repeated error fuse, timeout warning, explicit exit gate, single authoritative writer
Standard Handoff Format6-field handoff template: owner, goal, input, permitted writes, acceptance criteria, failure evidence
Risk-based Routingfast / standard / high lanes, routing to different reviewers based on change scope
Delivery Sequenceverify → commit → push → Draft MR/PR → ready signal → in_review (fixed order)
Review→Close ProtocolAutomatic in_review dispatch, reviewer metadata, reject/retry, escalation
Anti-loop ProtectionIdempotent issue creation, state-change filtering, human-source-only new task trigger
Red LinesSecret isolation, token permission separation, destructive operation confirmation

Install

dsh plugin --profile web add "github:LeslieWylie/agent-loop-workflow"

After restart, load the skill in any session:

load agent-loop-workflow

Design Principles

  • Project-agnostic: Only defines collaboration flow rules. Project-specific knowledge goes in *-conventions / *-engineering / *-review-rules skills
  • Zero dependencies: No external services required, only the DSH skill loading mechanism
  • Forge-agnostic: the skill describes the collaboration flow only. Map its "issue" and "MR" onto whatever tracker and forge you already use — it names none.

License

MIT