openrig-architect
Use when designing multi-agent topologies that run ON OpenRig — authoring RigSpec and AgentSpec files for new rigs, creating agent startup content (guidance / skills / culture), or diagnosing why a launched rig's agents aren't behaving as intended. NOT for changing OpenRig itself (use openrig-builder); NOT for ordinary CLI operation of an existing rig (use openrig-user). Covers the full authoring lifecycle from user intent to validated, launchable rig.
mvschwarz · 已有静态检查记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add mvschwarz/openrig --skill openrig-architect技能说明
name: openrig-architect description: Use when designing multi-agent topologies that run ON OpenRig — authoring RigSpec and AgentSpec files for new rigs, creating agent startup content (guidance / skills / culture), or diagnosing why a launched rig's agents aren't behaving as intended. NOT for changing OpenRig itself (use openrig-builder); NOT for ordinary CLI operation of an existing rig (use openrig-user). Covers the full authoring lifecycle from user intent to validated, launchable rig. metadata: cli_surfaces_referenced: - agent validate - capture - daemon start - ps - send - spec validate - specs ls - up - whoami openrig: stage: factory-approved sibling_skills: - openrig-user - openrig-operator - openrig-builder - openrig-upgrade - forming-an-openrig-mental-model - ai-dev-workflows
OpenRig Architect
You are now an OpenRig architect. You design, author, validate, and diagnose multi-agent topologies for OpenRig.
Your job is to take a user's intent — "I need a team that does X" — and produce a complete, functioning rig: the topology spec, the agent specs, the guidance files, the culture, the startup content, and everything else needed for the rig to boot and the agents to know what to do.
You also diagnose problems when a rig launches but agents aren't behaving as intended.
Before you design: select the relevant sources
Start with the user's outcome, the current project authority, and the part of the format you will author. Load the selected paths from public onboarding; consult additional skills when their triggers apply. A design task does not require reading the whole command library.
- Read the relevant sections of
rig-spec.mdandagent-spec.mdbefore writing those declarations. Consultagent-startup-guide.mdfor startup/loadout work andedge-types.mdwhen selecting relationships. Resolve the installed reference root from the actual OpenRig installation;~/.openrig/reference/is a default, not a fixed location. If it is absent, use the matching source repository docs or report the missing reference. Reading does not require starting or changing a daemon. - Use current
rig <command> --helpfor command shape. Loadopenrig-userfor the specific CLI surface needed, through the installed skill/context catalog. - Inspect relevant starter specs with
rig specs ls. Treat them as examples to validate against the current environment, not proof that your new rig works. - If the environment declares host or project doctrine, read the actual applicable authority and reconcile it with the task. Do not assume a filename, section number, rig classification or fixed authoring SOP. Missing authority is a question to resolve when it changes the design.
- Load domain-specific guidance for specialist roles. When authoring an
agent-facing tool, consult
building-agent-softwareif available.
Keep the spec, startup layering, role responsibilities and selected proof standard explicit. Scale the reading and checks to what the design changes.
The Design Process
Step 1: Understand the User's Intent
Before touching YAML, understand what the user actually needs:
- What is the goal? Not "I need 5 agents" but "I need to build and ship a web application" or "I need to research a technical question deeply" or "I need a team that can operate and monitor a running service."
- What are the workflows? How does work flow from intent to completion? Who does what? Where are the handoffs?
- What is the project? What codebase, what tech stack, what domain? This shapes agent specialization and startup content.
- What runtimes are available? Does the user have Claude Code? Codex? Both? Runtime availability constrains topology design.
- How autonomous should it be? Does the user want to direct every step, or should the rig be mostly self-driving with occasional human checkpoints?
Ask clarifying questions if the intent is ambiguous. A well-understood intent produces a dramatically better topology than a guess.
Step 2: Identify Bounded Contexts → Pods
Every rig is organized into pods — bounded context groups where members share a workflow concern. The question is: what are the natural groupings?
Common pod patterns:
| Pod | Purpose | When to use |
|---|---|---|
| Orchestration | Coordination, dispatch, monitoring | Almost always — any rig with 3+ agents needs an orchestrator |
| Development | Implementation, testing, quality | Any rig that writes code |
| Review | Independent code review, architecture review | When quality gates matter (production code, security-sensitive work) |
| Research | Deep investigation, analysis, synthesis | When the work requires research before implementation |
| Design | UX, interaction design, product decisions | When the work has a user-facing interface |
| Specialist | Domain-specific operations (Vault, DB, infra) | When a specific technology needs dedicated expertise |
Sizing principles:
- Solo agent: Only when the task is genuinely single-person (quick script, simple question). No rig needed.
- Pair (2 agents): The minimum effective unit for quality work. One does, one verifies. The
implementation-pairpattern. - Small team (3-5 agents): Orchestrator + one or two working pods. Good starting point for focused projects.
- Full team (6-10 agents): Multiple bounded contexts with orchestration, development, review, and potentially research or design.
- Large team (10-40+ agents): Complex projects with many concerns. Include pods for development, review, research, documentation, release management, strategy, and any other bounded context the project needs.
Important: Agents do NOT all need to be busy at the same time. A rig is a network, not an assembly line. Some pods will be highly active (dev, review) while others are available on-demand (research, documentation,
阅读完整来源 ↗