Best practices, reproducible workflows, and tutorials with commands and configuration examples.
文章从 Claude Code、Codex 和 Gemini CLI 的官方文档中整理出四种提示词模式：先计划再编辑、给智能体一个可运行的检查、让智能体反过来访谈你、把反复重打的提示词存成文件，并给出各家对应的命令、参数和文件格式。
Awaiting translation
Why it matters: 横向对照 Claude Code、Codex、Gemini CLI 三家文档，给出计划模式、可运行检查、访谈式提问和保存提示词四种模式的命令与文件格式。
A six-person mobile team used Cursor’s hooks, safe lists, and a Telegram bot to turn project conventions from prompts into runtime enforcement.
Why it matters: The author wires Cursor’s hooks, safe lists, and a Telegram bot into a reusable team collaboration setup, so readers can judge which constraints belong in runtime enforcement rather than in prompts.
Cursor engineer Lauren Tan shares how she gets AI agents to submit and merge PRs on their own: the key is validation—letting the agent run code, capture CPU traces, and open an iOS simulator to check its own work.
Why it matters: Cursor engineers break trust in AI agents down into reusable validation skills, feature maps, and evals, so readers can build their own automated validation workflows.
Spotify 开源插件 shunt，通过 Claude Code 的 PreToolUse hooks 拦截超过 350 行的整文件读取，把 Read 以及 cat。
Awaiting translation
Why it matters: Spotify 用 PreToolUse Hook 把大文件读取和样板代码生成转给廉价模型，给出可迁移的成本拆分思路。
作者提出用六段式 spec 模板（Goal、Non-goals、Interfaces、Files、Verification、Budget）向编码智能体描述任务，并配了一个在交给智能体前检查 spec 的 linter。
Awaiting translation
Why it matters: 给出可直接套用的六段式 spec 模板、tally 实例和配套 linter，读者能据此改造自己交给编码智能体的任务描述。
作者给出一份按危害排序的十项 agent diff 检查清单，依次看被删除的测试、被跳过或弱化的断言、宽泛异常捕获、新增依赖、任务范围外文件、CI 配置改动、疑似密钥、遗留标记和净删除超过 40 行的文件。
Awaiting translation
Why it matters: 给出按危害排序的十项 agent diff 检查清单，并附可复用的扫描脚本与行号定位。
作者主张给每个 agent 任务配一个 git worktree 和一条分支，而不是每个会话一个，因为任务需要能单独评审和回滚。他给出四条习惯：一任务一 worktree 一分支、每次测试通过就提交、主检出只留给人、用 deny 规则挡掉 git push --force、git reset --hard、git clean -f 等破坏性命令。
Awaiting translation
Why it matters: 作者用真实仓库跑通脚本，给出每个 agent 任务一个 worktree 的四条版本控制习惯和可直接抄用的权限规则。
The author built the space exploration game Void Explorer in Codex with Astra, featuring 2,048 star systems and over 10,000 procedurally generated planets, and shared the full workflow from prompts to architecture, testing, and performance measurement.
Why it matters: Using Astra in Codex, the author built an entire game and showed a transferable collaborative workflow that spans prompts, testing, and performance measurement.
Cline 把 VS Code 扩展从约 76,000 行单体核心迁移到 Cline SDK，并自建灰度发布机制：一个安装包内打包 loader、legacy 和 next 两套扩展，由 PostHog 功能开关按百分比决定激活哪套，崩溃时自动回退到 legacy，开关可随时降到 0% 作为 kill switch。
Awaiting translation
Why it matters: Cline 官方复盘如何把 1100 万用户的 VS Code 扩展迁到新 harness，含灰度机制与前后指标对比。
GitHub Copilot 团队复盘了四项降低 AI 编码成本的改动，核心原则是按完整任务而非单次工具调用衡量效率。
Awaiting translation
Why it matters: GitHub Copilot 团队复盘四项降本改动，并给出可迁移的评估方法：按完整任务而非单次工具调用衡量成本。
Drawing on a hands-on session where he dispatched 13 subagents to build a storyboard, the author walks through the subagents feature that both Claude Code and Codex have: subagents work in their own separate windows and hand only their conclusions back to the main conversation.
Why it matters: Using a hands-on session where he dispatched 13 subagents to build a storyboard, the author shows how subagents keep their work outside the main conversation and send back only the conclusions.
Anthropic has published a guide dissecting e-commerce AI agents. Drawing on deployment experience with retailers, e-commerce platforms, and teams in travel, entertainment, and telecom, it proposes a single-agent architecture that puts Claude in a standard agent loop, uses skills to cover long-tail needs, and calls tools to work with existing systems. The guide says that in comparative testing, this architecture beats both sub-agent designs and the approach of cramming everything into the prompt.
Why it matters: Drawing on enterprise e-commerce agent deployment experience, Anthropic lays out a complete engineering approach covering a single-agent-plus-skills architecture, latency and cost optimization, and memory and security evaluation.
作者提出用 agent 会话记录衡量一次工程决策的下游影响，即 blast radius（影响范围），并用自家 tapes 项目的一次架构决策做验证：设计文档会话花费 57.05 美元，后续引发 4704.74 美元工作量，分布在 70 个人工会话、3 名工程师、8 个仓库和 27 天中，另有 404 个自动化评测会话花费 431.54 美元。
Awaiting translation
Why it matters: 作者用自家一次架构决策的 474 条会话记录，展示如何把决策的下游成本量化成可复用的指标。
Thoughtworks Europe 把 10 名工程师放进巴塞罗那办公室，用智能体工程在四天内构建了一套航空 IROps 系统。
Awaiting translation
Why it matters: 作者复盘 10 名工程师用智能体四天构建 IROps 系统时，仓库意外变成智能体协调用的黑板。
Author mattpocock has released a set of AI coding Agent Skills he uses day to day. They're aimed at real engineering rather than vibe coding, and the emphasis is on being small, easy to modify, composable, and compatible with any model.
Why it matters: The author breaks years of engineering experience into a set of composable Skills and explains the failure mode each one targets, so readers can judge whether they fit into their own development workflow.
Addy Osmani 建议每隔几周运行一次 Claude Code 的 /doctor，单独用 /memory 检查记忆，并让每条指令重新证明自己的价值，因为模型、harness 和代码库都在变，旧配置会留下。
Awaiting translation
Why it matters: 作者结合自身配置审计经验与近期研究，说明 Agent 配置文件为何会腐化，以及如何按节奏清理。
The Cline team built a code review agent with the Cline SDK, splitting review into two agent loops—review and judge—then using a driver script to batch-submit the surviving issues as a single COMMENT event to the GitHub PR.
Why it matters: A full breakdown of the plugin, Hooks, and two-stage loop behind a code review agent, transferable to other automated review scenarios.
Lovable shared a retrospective on how it connected its platform app to third-party services: first it supported MCP as a stopgap for pulling context into chats, then it built app connectors of its own, using a Connector Gateway to proxy requests between published apps and third-party APIs. The gateway holds credentials and refresh logic, so deployed apps never touch the keys.
Why it matters: Lovable’s retrospective on turning connectors into reusable infrastructure is worth a look for teams doing third-party integrations and credential management.
OpenAI engineers use Codex with the open-source notebook app Runme to automate repetitive work such as running model evaluations. The approach: write a goal cell in the Runme notebook, have Codex read the goal, produce a plan, and wait for human approval before executing, logging commands, outputs, and conclusions along the way—including the dead ends.
Why it matters: The author uses the Runme notebook plus WebMCP to hand the evaluation process over to Codex; readers can borrow the way it handles goals, approvals, and context capture.
From his phone, author Jesse Vincent set a goal inside Evener, his own agent framework, and let the agent autonomously build an ARM64 C compiler that compiles SQLite and passes basic smoke tests. It took about 21 hours, running on Evener with GLM 5.2.
Why it matters: The author used an autonomous agent loop to generate a C compiler from scratch that can compile SQLite, showing what recursive sub-agents and goal-setting actually deliver in practice.