写作

介绍 RTK 如何在命令输出进入模型上下文前过滤测试、Git、搜索和构建噪声，把 Context Engineering 做到工具输出边界。

How the Google Cloud Developer Plugin packages Skills, MCP configuration, and rules, and what this means for distribution, versions, and permissions.

拆解 Google Cloud Developer Plugin 如何把 Skill、MCP 配置和规则按 Agent Plugins 规范打包，暴露跨 Coding Agent 的分发、版本与权限问题。

OpenCompany uses company.toml, agent teams, and human sign-off to put organizational structure and agent configuration into version-controlled files.

OpenCompany 用 company.toml、Agent Team 和 Human Sign-off 把组织结构与 Agent 配置写成可版本控制文件，并明确保留人工签字点。

The Anthropic incident review shows why automated monitors and LLM graders need coverage, independence, and tests for their own failure modes.

从 Anthropic Agentic Search 事故复盘看自动监控和 LLM grader 的漏检问题，说明 Agent Eval 也需要覆盖率、独立性和失效模式测试。

Munim Computer Use reads the accessibility tree and operates desktop controls by element ID, reducing reliance on fragile screenshot-coordinate automation.

介绍 Munim Computer Use 如何先读取可访问性树，再按元素 ID 操作桌面控件，减少依赖截图坐标的脆弱自动化。

How jcode handles multi-agent resources, state synchronization, and verification in its harness, beyond the capabilities of the model alone.

介绍 jcode 如何把多 Agent 的资源、状态同步和验证放到 Harness 层，说明并行 Coding Agent 的瓶颈不只是模型能力。

OpenAI 的组织级数据说明 Coding Agent 使用规模上升后，瓶颈会转向任务拆分、并发调度、Harness、Eval 和结果选择。