connect-rpc
AgentsMesh login uses the Connect unary endpoint:
$ npx -y skills add AgentsMesh/AgentsMesh --agent claude-codeHow it fires
How this agent gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
Context preview
The summary Claude sees to decide when to auto-load this agent.
AgentsMesh login uses the Connect unary endpoint:
Agent definition
connect-rpc.mdConnect-RPC Authentication Contract
AgentsMesh login uses the Connect unary endpoint:
POST /proto.auth.v1.AuthService/Login Content-Type: application/json Connect-Protocol-Version: 1
Use protobuf JSON field names and encoding rules. In particular, field names are lower camel case and 64-bit integers are represented as JSON strings.
The SSO discovery endpoint follows the same routing contract:
POST /proto.sso.v1.SSOService/Discover
The development and production reverse proxies must route `/proto.` to the Backend with higher priority than the frontend catch-all.
- A Backend credential failure should be a structured Connect error such as an
unauthenticated response.
- An HTML 404 containing Next.js assets means the request reached the frontend;
it does not prove the email or password is wrong.
- A JSON 404 from the Backend means the procedure or deployment version must be
checked.
Do not use the removed `/api/v1/auth/login` route in new tests or diagnostics.
The AI Agent Workforce Platform. Run a hundred AI coding agents across your own machines — schedule, isolate, and steer them all from one console.
Repo: AgentsMesh/AgentsMesh
Other agents on agentsmesh.
- cochange-churn
静态切面看不到的架构问题,往往在**版本历史**里暴露。这是来自代码审查 git-history lens 的高信号视角。仅当处于 git 仓库时启用。
Open agent - concept-modeling
架构的本质是**概念的识别与组织**。这是优先级最高的 lens。
Open agent - evidence-and-detection
LLM 架构审查的头号失败模式:**凭空断言结构**——声称"A 依赖 B""这里有循环""X 被多处写",却没真去查。本文件给出强制接地原则 + 各语言的实际探测命令。
Open agent - report-format
范围小用 SKILL.md 里的精简版即可。下面是全量审计的结构化报告。
Open agent - responsibility-causality
这是本 skill 最独特、最能抓**真实结构性 bug** 的 lens:职责归属、机制/策略分离、因果与不变量(并发/状态契约)、属性三分。
Open agent - solid-grasp-yagni
经典原则做交叉验证。**这一 lens 最容易产出假阳性(教科书式建议)——严格用置信度门控,不报"理论上更优雅但无实际危害"的项。**
Open agent

