# Craft Better Software

Write quality software with AI and Extreme Programming.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Build Your Own Software Factory in 5 Steps

DevFeed: [Build Your Own Software Factory in 5 Steps](<https://devfeed.tech/articles/build-your-own-software-factory-in-5-steps-138259.md>)

Original publisher: [Read original article](<https://craftbettersoftware.com/p/build-your-own-software-factory-in>)

Author: Daniel Moka

Published: 2026-11-17T06:01:53Z

Content type: tutorial

Language: en

Sources: [Craft Better Software](<https://devfeed.tech/sources/craft-better-software.md>)

Topics: [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [issue tracking](<https://devfeed.tech/topics/issue-tracking.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [code security](<https://devfeed.tech/topics/code-security.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>), [qualitygates](<https://devfeed.tech/topics/qualitygates.md>)

Tags: [actions](<https://devfeed.tech/tags/actions.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [authorization](<https://devfeed.tech/tags/authorization.md>), [autopilot](<https://devfeed.tech/tags/autopilot.md>), [bug](<https://devfeed.tech/tags/bug.md>), [bypass](<https://devfeed.tech/tags/bypass.md>), [ci](<https://devfeed.tech/tags/ci.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [cloud-agent](<https://devfeed.tech/tags/cloud-agent.md>), [code-quality](<https://devfeed.tech/tags/code-quality.md>), [code-review](<https://devfeed.tech/tags/code-review.md>), [code-security](<https://devfeed.tech/tags/code-security.md>), [codex](<https://devfeed.tech/tags/codex.md>), [coding-agent](<https://devfeed.tech/tags/coding-agent.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [control](<https://devfeed.tech/tags/control.md>), [software-factory](<https://devfeed.tech/tags/software-factory.md>)

### AI overview

The guide describes a five-step GitHub workflow that turns reports into reviewed pull requests while leaving merge approval to a person. Jev routes support emails and issues; a question about instructions outside the reported problem adds `needs-human` to keep suspicious issues away from coding agents. CodeRabbit Plan posts implementation plans, and a coding agent claims `planned` issues and opens pull requests. CodeRabbit reviews each push; the agent responds to findings, while configured checks can flag weakened tests and run security scanners. A script signals readiness only after CI is green and review is complete. CodeRabbit Triage ranks queued pull requests, and Explain groups changes by purpose. For repository security, Secure offers required pre-merge review checks, scheduled or on-demand deep scans, an attack surface map, and AI-drafted fixes. The author reports one scan finding an authorization bypass and a fix that added role checks and regression tests. The workflow automates triage through review, but a person still reads and merges the pull request.

### Source excerpt

The 5-step guide to implementing an end-to-end software factory on your repositories.

## Loop Engineering: 9 Ways to Automate Your AI Agents

DevFeed: [Loop Engineering: 9 Ways to Automate Your AI Agents](<https://devfeed.tech/articles/loop-engineering-9-ways-to-automate-your-ai-agents-126817.md>)

Original publisher: [Read original article](<https://craftbettersoftware.com/p/loop-engineering-9-ways-to-automate>)

Author: Daniel Moka

Published: 2026-11-10T06:09:49Z

Content type: tutorial

Language: en

Sources: [Craft Better Software](<https://devfeed.tech/sources/craft-better-software.md>)

Topics: [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>), [Fuzzing/Fuzz testing](<https://devfeed.tech/topics/fuzzing.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [3](<https://devfeed.tech/tags/3.md>), [actions](<https://devfeed.tech/tags/actions.md>), [after](<https://devfeed.tech/tags/after.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-coding](<https://devfeed.tech/tags/agentic-coding.md>), [agentic-engineering](<https://devfeed.tech/tags/agentic-engineering.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-assistant](<https://devfeed.tech/tags/ai-assistant.md>), [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [alert](<https://devfeed.tech/tags/alert.md>), [all](<https://devfeed.tech/tags/all.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [automate](<https://devfeed.tech/tags/automate.md>), [engineering](<https://devfeed.tech/tags/engineering.md>)

### AI overview

The article presents nine ways to automate recurring coding and maintenance work with agent loops: bug reports, production error spikes, issue triage, CI repair, dependency upgrades, CVE fixes, CI speed improvements, fuzz crashes, and inbox organization. Each loop uses a trigger to start an agent, a check to guide retries or stop, and human review of the resulting pull request or item. Examples use Claude Code scheduled tasks and GitHub triggers or Actions; inbox triage instead uses an always-on agent such as OpenClaw or Hermes with Discord and Markdown files. Several code-fixing loops stop after three failed attempts and send logs, tests, or crash inputs for review. The article also warns that emailed bug reports can carry prompt injection, recommending minimally scoped secrets, no merge rights, and review of every pull request.

### Source excerpt

Stop babysitting your AI agents. Put them on autopilot.

## Software is NOT Dead

DevFeed: [Software is NOT Dead](<https://devfeed.tech/articles/software-is-not-dead-110707.md>)

Original publisher: [Read original article](<https://craftbettersoftware.com/p/software-is-not-dead>)

Author: Daniel Moka

Published: 2026-11-01T08:03:19Z

Content type: opinion

Language: en

Sources: [Craft Better Software](<https://devfeed.tech/sources/craft-better-software.md>)

Topics: [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Code quality](<https://devfeed.tech/topics/code-quality.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Software](<https://devfeed.tech/topics/software.md>), [context-architecture](<https://devfeed.tech/topics/context-architecture.md>)

Tags: [abstractions](<https://devfeed.tech/tags/abstractions.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [build](<https://devfeed.tech/tags/build.md>), [building-software](<https://devfeed.tech/tags/building-software.md>), [code](<https://devfeed.tech/tags/code.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [context](<https://devfeed.tech/tags/context.md>), [control](<https://devfeed.tech/tags/control.md>), [design](<https://devfeed.tech/tags/design.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [fundamentals](<https://devfeed.tech/tags/fundamentals.md>), [future](<https://devfeed.tech/tags/future.md>), [quality](<https://devfeed.tech/tags/quality.md>), [ship](<https://devfeed.tech/tags/ship.md>), [software](<https://devfeed.tech/tags/software.md>), [write](<https://devfeed.tech/tags/write.md>)

### AI overview

The author argues that software engineering fundamentals remain essential as AI takes over more coding work: an agent's codebase provides context, and poorly structured code can confuse agents as it can people. Strong types, clean abstractions, and high-quality tests are presented as constraints that reduce agents' room for poor decisions. The proposed shift is from manually writing, reading, testing, and documenting code toward engineering agents to perform those tasks and verifying their work.

### Source excerpt

Software is more alive than ever. Our job is not to write code. Our job is to lead agents to ship quality software.

## 7 Tips to Write Great Skills for Your AI Agents

DevFeed: [7 Tips to Write Great Skills for Your AI Agents](<https://devfeed.tech/articles/7-tips-to-write-great-skills-for-your-ai-agents-109928.md>)

Original publisher: [Read original article](<https://craftbettersoftware.com/p/7-tips-to-write-great-skills-for>)

Author: Daniel Moka

Published: 2026-10-31T06:01:38Z

Content type: article

Language: en

Sources: [Craft Better Software](<https://devfeed.tech/sources/craft-better-software.md>)

Topics: [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>), [Developer skills](<https://devfeed.tech/topics/developer-skills.md>), [Learning](<https://devfeed.tech/topics/learning.md>)

Tags: [agent-skills](<https://devfeed.tech/tags/agent-skills.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-engineering](<https://devfeed.tech/tags/agentic-engineering.md>), [agents](<https://devfeed.tech/tags/agents.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [skills](<https://devfeed.tech/tags/skills.md>), [tips](<https://devfeed.tech/tags/tips.md>)

### AI overview

The article argues that reliable agent skills need concise, task-specific instructions supported by files and scripts. It recommends keeping SKILL.md under 500 lines, linking supporting files directly, and using clear names and tables of contents for long references so details load only when needed. Put repeatable mechanics such as builds and checks in scripts, while leaving context-dependent decisions to the model. Write skill descriptions with the words users use to trigger them; record real recurring failures in a short GOTCHAS.md; provide a finished output example; and remove generic instructions that do not change behavior. Finally, maintain shared skills in one Git repository: use linked global skills for common tasks and keep project-specific skills in the project. The text says the same skill folder can work with Claude Code, Codex, and Cursor.

### Source excerpt

The 7 mistakes I find in almost every skill, and how to fix them

## How I Ship Quality Code with AI Agents

DevFeed: [How I Ship Quality Code with AI Agents](<https://devfeed.tech/articles/how-i-ship-quality-code-with-ai-agents-100718.md>)

Original publisher: [Read original article](<https://craftbettersoftware.com/p/how-i-ship-quality-code-with-ai-agents>)

Author: Daniel Moka

Published: 2026-10-26T06:02:23Z

Content type: tutorial

Language: en

Sources: [Craft Better Software](<https://devfeed.tech/sources/craft-better-software.md>)

Topics: [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [mutation-testing](<https://devfeed.tech/topics/mutation-testing.md>), [Code review](<https://devfeed.tech/topics/code-review.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [Learning](<https://devfeed.tech/topics/learning.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-engineering](<https://devfeed.tech/tags/agentic-engineering.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [app](<https://devfeed.tech/tags/app.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [assertions](<https://devfeed.tech/tags/assertions.md>), [brain](<https://devfeed.tech/tags/brain.md>), [bug](<https://devfeed.tech/tags/bug.md>), [bug-reports](<https://devfeed.tech/tags/bug-reports.md>), [bugs](<https://devfeed.tech/tags/bugs.md>), [build](<https://devfeed.tech/tags/build.md>), [code](<https://devfeed.tech/tags/code.md>), [course](<https://devfeed.tech/tags/course.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [learning](<https://devfeed.tech/tags/learning.md>), [quality](<https://devfeed.tech/tags/quality.md>)

### AI overview

The course presents reliable AI-agent coding as an engineering problem across eight layers and workflows: fundamentals, harnesses, verification, review, memory, MCP, loops, and AI employees. It describes a harness as session-loaded instructions, skills, sub-agents, and hooks; verification combines mutation and property testing, end-to-end tests, and CI gates; review moves checks before and after coding with plan review, a reviewer agent, and a PR tour. A shared git-based "second brain" stores project facts and decisions. The MCP module builds a server intended to let Claude Code, Codex, and Cursor access an app's tools. The loop and AI-employee modules describe scheduled or event-triggered agents that check task completion, including an example that turns bug emails into tested fixes and pull requests. The source is promotional course copy and outlines the teaching and examples; it does not provide independent evidence of outcomes.

### Source excerpt

I built the course I wish I had when I started learning agentic engineering

## 7 Security Incidents in 48 hours. Here's What You Need to Know.

DevFeed: [7 Security Incidents in 48 hours. Here's What You Need to Know.](<https://devfeed.tech/articles/7-security-incidents-in-48-hours-here-s-what-you-need-to-know-97846.md>)

Original publisher: [Read original article](<https://craftbettersoftware.com/p/7-security-incidents-in-48-hours>)

Author: Daniel Moka

Published: 2026-10-23T13:04:05Z

Content type: news

Language: en

Sources: [Craft Better Software](<https://devfeed.tech/sources/craft-better-software.md>)

Topics: [ai security](<https://devfeed.tech/topics/ai-security.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>), [Security](<https://devfeed.tech/topics/security.md>), [least privilege](<https://devfeed.tech/topics/least-privilege.md>), [malware protection](<https://devfeed.tech/topics/malware-protection.md>), [AI software supply chain security](<https://devfeed.tech/topics/ai-software-supply-chain-security.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [2025](<https://devfeed.tech/tags/2025.md>), [3](<https://devfeed.tech/tags/3.md>), [actions](<https://devfeed.tech/tags/actions.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [all](<https://devfeed.tech/tags/all.md>), [also](<https://devfeed.tech/tags/also.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [api](<https://devfeed.tech/tags/api.md>), [here](<https://devfeed.tech/tags/here.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [need](<https://devfeed.tech/tags/need.md>), [patch](<https://devfeed.tech/tags/patch.md>), [security](<https://devfeed.tech/tags/security.md>)

### AI overview

The excerpt reports seven security incidents and gives immediate remediation steps: patch affected PHP, self-managed GitLab and Node.js versions; treat a machine that ran LiteLLM 1.107.0 as compromised, rotate reachable keys and pin 1.106.2; rotate Railway environment variables; clean a machine affected by tensorlake 0.5.144 before revoking its GitHub token; and update systems and trust stores for the eMudhra issue. It warns that agents combining private data, untrusted text and network or API access can be manipulated into leaking secrets, and says prompt rules alone are insufficient. Suggested safeguards include limiting tools and web access, sandboxing commands with secrets outside mounted folders, checking commands with a hook, restricting network destinations and running always-on agents on a dedicated machine. The source says several vulnerabilities were found with AI, including the Node.js Brotli bug by OpenAI Codex Security, and warns attackers also have capable AI models.

### Source excerpt

What to patch, what to rotate, and how to protect your AI agents

## How to Become an AI Agent Engineer

DevFeed: [How to Become an AI Agent Engineer](<https://devfeed.tech/articles/how-to-become-an-ai-agent-engineer-89801.md>)

Original publisher: [Read original article](<https://craftbettersoftware.com/p/how-to-become-an-ai-agent-engineer>)

Author: Daniel Moka

Published: 2026-10-19T04:59:53Z

Content type: news

Language: en

Sources: [Craft Better Software](<https://devfeed.tech/sources/craft-better-software.md>)

Topics: [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Learning](<https://devfeed.tech/topics/learning.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>)

Tags: [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [course](<https://devfeed.tech/tags/course.md>)

### AI overview

The author announces AI Agent Engineer, a course on building, steering, verifying and running AI coding agents. Its eight modules cover fundamentals, harnesses, verification, review, memory, MCP, recurring loops and continuously running agents. The course includes 56 lessons and 27 practical tasks using a TypeScript, Next.js and Postgres application, alongside a handbook and configuration resources.

### Source excerpt

Launching my new Agentic Engineering course in 1 week

## Jev: A Decision-Only AI Model for Fast Software Routing and Classification

DevFeed: [Jev: A Decision-Only AI Model for Fast Software Routing and Classification](<https://devfeed.tech/articles/jev-engineering-101-57874.md>)

Original publisher: [Read original article](<https://craftbettersoftware.com/p/jev-engineering-101>)

Author: Daniel Moka

Published: 2026-09-22T05:03:22Z

Content type: tutorial

Language: en

Sources: [Craft Better Software](<https://devfeed.tech/sources/craft-better-software.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [decision-making](<https://devfeed.tech/topics/decision-making.md>), [Code](<https://devfeed.tech/topics/code.md>), [Latency](<https://devfeed.tech/topics/latency.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [building-with-ai](<https://devfeed.tech/tags/building-with-ai.md>), [code](<https://devfeed.tech/tags/code.md>), [decision-making](<https://devfeed.tech/tags/decision-making.md>), [developers](<https://devfeed.tech/tags/developers.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [latency](<https://devfeed.tech/tags/latency.md>)

### AI overview

This tutorial introduces Jev as a decision-only AI model that accepts application state and typed questions, then returns choices, scores, or probabilities with confidence. It explains how Jev can handle fast, low-cost routing and classification inside agentic software systems, while code and other models perform the resulting actions.

### Source excerpt

Build the brain that predicts your agents' next step

## Agentic Engineering 101

DevFeed: [Agentic Engineering 101](<https://devfeed.tech/articles/agentic-engineering-101-26199.md>)

Original publisher: [Read original article](<https://craftbettersoftware.com/p/agentic-engineering-101>)

Author: Daniel Moka

Published: 2026-08-12T05:01:48Z

Content type: article

Language: en

Sources: [Craft Better Software](<https://devfeed.tech/sources/craft-better-software.md>)

Topics: [Prompt Engineering](<https://devfeed.tech/topics/prompt-engineering.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [Enhancing AI model performance](<https://devfeed.tech/topics/enhancing-ai-model-performance.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-engineering](<https://devfeed.tech/tags/agentic-engineering.md>), [ai](<https://devfeed.tech/tags/ai.md>), [context](<https://devfeed.tech/tags/context.md>), [context-engineering](<https://devfeed.tech/tags/context-engineering.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [graph](<https://devfeed.tech/tags/graph.md>), [graph-engineering](<https://devfeed.tech/tags/graph-engineering.md>), [harness](<https://devfeed.tech/tags/harness.md>), [harness-engineering](<https://devfeed.tech/tags/harness-engineering.md>), [loop-engineering](<https://devfeed.tech/tags/loop-engineering.md>), [memory](<https://devfeed.tech/tags/memory.md>), [prompt](<https://devfeed.tech/tags/prompt.md>)

### AI overview

The excerpt frames agentic engineering as widening beyond the prompt: prompt, context, harness, loop and graph engineering are presented as layers around a model, with memory engineering described as an emerging next step. Prompt engineering shapes one call through a clear task, examples and an output schema. Context engineering curates the finite model window--prompt, retrieved documents, memory, prior turns and tool outputs--by selecting relevant material and removing what adds little. The excerpt says repeated failures despite rewording a prompt signal that the bottleneck may lie outside that call. It introduces the remaining layers but ends partway through its context-engineering guidance, so their methods and tradeoffs are not established here.

### Source excerpt

Prompt vs Context vs Harness vs Loop vs Graph Engineering

## How to Catch AI Mistakes In Your Code

DevFeed: [How to Catch AI Mistakes In Your Code](<https://devfeed.tech/articles/how-to-catch-ai-mistakes-in-your-code-26207.md>)

Original publisher: [Read original article](<https://craftbettersoftware.com/p/how-to-catch-ai-mistakes-in-your>)

Author: Daniel Moka

Published: 2026-05-27T05:01:22Z

Content type: article

Language: en

Sources: [Craft Better Software](<https://devfeed.tech/sources/craft-better-software.md>)

Topics: [Code review](<https://devfeed.tech/topics/code-review.md>), [ai slop pull requests](<https://devfeed.tech/topics/ai-slop-pull-requests.md>), [Software Testing](<https://devfeed.tech/topics/software-testing.md>), [Static code analysis](<https://devfeed.tech/topics/static-code-analysis.md>), [Continuous integration](<https://devfeed.tech/topics/continuous-integration.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-harness](<https://devfeed.tech/tags/agent-harness.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [async](<https://devfeed.tech/tags/async.md>), [audits](<https://devfeed.tech/tags/audits.md>), [automatically](<https://devfeed.tech/tags/automatically.md>), [bedrock](<https://devfeed.tech/tags/bedrock.md>), [bench](<https://devfeed.tech/tags/bench.md>), [ci](<https://devfeed.tech/tags/ci.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [code](<https://devfeed.tech/tags/code.md>), [deterministic-guardrails](<https://devfeed.tech/tags/deterministic-guardrails.md>), [guardrails](<https://devfeed.tech/tags/guardrails.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [mistakes](<https://devfeed.tech/tags/mistakes.md>), [prevent](<https://devfeed.tech/tags/prevent.md>)

### AI overview

The excerpt argues that deterministic checks can keep AI-generated code from shipping defects at a pace human reviews cannot match. Compilers, tests, linters, analyzers, and CI enforce rules outside an agent's control, leaving people to assess intent, tradeoffs, and product decisions. It describes static analysis and linting as a way to catch patterns such as dead code, unused dependencies, unsafe async flows, code smells, and excess complexity. The excerpt begins in sponsored Cline SDK material and then shifts to the article's argument; it does not show the complete list of six guardrails.

### Source excerpt

6 Deterministic Guardrails To Prevent AI Mistakes

## Why AI Changes Code Reviews and Why Engineers Should Review Intent

DevFeed: [Why AI Changes Code Reviews and Why Engineers Should Review Intent](<https://devfeed.tech/articles/human-code-reviews-are-dead-26209.md>)

Original publisher: [Read original article](<https://craftbettersoftware.com/p/human-code-reviews-are-dead>)

Author: Daniel Moka

Published: 2026-05-18T05:02:06Z

Content type: opinion

Language: en

Sources: [Craft Better Software](<https://devfeed.tech/sources/craft-better-software.md>)

Topics: [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [code-reviews](<https://devfeed.tech/tags/code-reviews.md>), [quality](<https://devfeed.tech/tags/quality.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>), [vibe-coding](<https://devfeed.tech/tags/vibe-coding.md>)

### AI overview

The article argues that AI-generated code is increasing the volume of pull requests, commits, and overall code output beyond what humans can review line by line. It recommends shifting engineering attention from reviewing implementation details to reviewing intent, solutions, and the reasoning behind what AI agents build.

### Source excerpt

How Top Engineers Review Code in the Age of AI

## Create Your First AI Agent In 5 Minutes

DevFeed: [Create Your First AI Agent In 5 Minutes](<https://devfeed.tech/articles/create-your-first-ai-agent-in-5-minutes-26204.md>)

Original publisher: [Read original article](<https://craftbettersoftware.com/p/create-your-first-ai-agent-in-5-minutes>)

Author: Daniel Moka

Published: 2026-04-28T05:01:46Z

Content type: tutorial

Language: en

Sources: [Craft Better Software](<https://devfeed.tech/sources/craft-better-software.md>)

Topics: [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [software-development](<https://devfeed.tech/topics/software-development.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [browser](<https://devfeed.tech/tags/browser.md>), [bug](<https://devfeed.tech/tags/bug.md>), [build-ai-agents](<https://devfeed.tech/tags/build-ai-agents.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [command](<https://devfeed.tech/tags/command.md>), [context-window](<https://devfeed.tech/tags/context-window.md>), [cost](<https://devfeed.tech/tags/cost.md>), [debugging](<https://devfeed.tech/tags/debugging.md>), [docs](<https://devfeed.tech/tags/docs.md>), [example](<https://devfeed.tech/tags/example.md>), [first](<https://devfeed.tech/tags/first.md>), [fundamentals](<https://devfeed.tech/tags/fundamentals.md>), [governance](<https://devfeed.tech/tags/governance.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [main-thread](<https://devfeed.tech/tags/main-thread.md>), [memory](<https://devfeed.tech/tags/memory.md>), [motivation](<https://devfeed.tech/tags/motivation.md>), [subagents](<https://devfeed.tech/tags/subagents.md>)

### AI overview

Claude Code subagents are specialized workers with separate context windows, system prompts, tool access and permissions. They handle focused tasks and return results to the main conversation, helping keep noisy work from flooding its context. To start creating one, type `/agents`, choose Library -> Create New Agent, select Personal for global access, then choose Manual and give it a name. The excerpt ends as the next step begins, so it does not establish the full creation process or the promised browser-based QA example.

### Source excerpt

A practical guide to building real Claude Code subagents with tools, context, and and well-defined outputs

## Master Claude Code Skills in 5 Minutes

DevFeed: [Master Claude Code Skills in 5 Minutes](<https://devfeed.tech/articles/master-claude-code-skills-in-5-minutes-26211.md>)

Original publisher: [Read original article](<https://craftbettersoftware.com/p/master-claude-code-skills-in-5-minutes>)

Author: Daniel Moka

Published: 2026-03-30T05:02:24Z

Content type: article

Language: en

Sources: [Craft Better Software](<https://devfeed.tech/sources/craft-better-software.md>)

Topics: [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>), [Learning](<https://devfeed.tech/topics/learning.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [article](<https://devfeed.tech/tags/article.md>), [autocomplete](<https://devfeed.tech/tags/autocomplete.md>), [automatically](<https://devfeed.tech/tags/automatically.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [background](<https://devfeed.tech/tags/background.md>), [bad-data](<https://devfeed.tech/tags/bad-data.md>), [bash](<https://devfeed.tech/tags/bash.md>), [basic](<https://devfeed.tech/tags/basic.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [claude-code-skills](<https://devfeed.tech/tags/claude-code-skills.md>), [context](<https://devfeed.tech/tags/context.md>), [control](<https://devfeed.tech/tags/control.md>), [markdown](<https://devfeed.tech/tags/markdown.md>), [markdown-files](<https://devfeed.tech/tags/markdown-files.md>), [skills](<https://devfeed.tech/tags/skills.md>)

### AI overview

The excerpt's main point is that a Claude Code skill is a directory, not just a SKILL.md file: the file is an entry point, while scripts, reference docs, templates, and configuration can supply details on demand through progressive disclosure. It says YAML frontmatter controls invocation and permissions. The excerpt distinguishes default skills, which both Claude and the user can invoke; manual-only skills, suited to actions with side effects; and hidden skills that Claude may invoke automatically for background guidance. It also emphasizes the description as a trigger for automatic discovery, but cuts off before explaining that mechanism further.

### Source excerpt

Skills aren't markdown files. Here's what they actually are.

## Stop Using Claude Code Like a Chatbot

DevFeed: [Stop Using Claude Code Like a Chatbot](<https://devfeed.tech/articles/stop-using-claude-code-like-a-chatbot-26212.md>)

Original publisher: [Read original article](<https://craftbettersoftware.com/p/stop-using-claude-code-like-a-chatbot>)

Author: Daniel Moka

Published: 2026-03-23T06:44:01Z

Content type: tutorial

Language: en

Sources: [Craft Better Software](<https://devfeed.tech/sources/craft-better-software.md>)

Topics: [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [Programming](<https://devfeed.tech/topics/programming.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [coding assistant](<https://devfeed.tech/topics/coding-assistant.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-subscriptions](<https://devfeed.tech/tags/ai-subscriptions.md>), [chatbot](<https://devfeed.tech/tags/chatbot.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [claude-md](<https://devfeed.tech/tags/claude-md.md>), [code](<https://devfeed.tech/tags/code.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-standards](<https://devfeed.tech/tags/coding-standards.md>), [command](<https://devfeed.tech/tags/command.md>), [commands](<https://devfeed.tech/tags/commands.md>), [context](<https://devfeed.tech/tags/context.md>), [debug](<https://devfeed.tech/tags/debug.md>), [developers](<https://devfeed.tech/tags/developers.md>), [markdown](<https://devfeed.tech/tags/markdown.md>), [markdown-files](<https://devfeed.tech/tags/markdown-files.md>), [monorepo](<https://devfeed.tech/tags/monorepo.md>), [productivity](<https://devfeed.tech/tags/productivity.md>)

### AI overview

The excerpt recommends organizing Claude Code's project guidance in nested CLAUDE.md files: session startup loads files up the directory tree, while files in subdirectories load when Claude works there. This can provide shared root and component conventions without loading unrelated guidance into context. It also describes Skills as markdown files triggered with a slash to save recurring workflows such as PR reviews, debugging, and test generation. The excerpt says older commands still work and Skills are now the recommended path, but it cuts off before explaining further details.

### Source excerpt

5 Claude Features That 10x Your Productivity

## Build Your AI Agent the Right Way

DevFeed: [Build Your AI Agent the Right Way](<https://devfeed.tech/articles/build-your-ai-agent-the-right-way-26200.md>)

Original publisher: [Read original article](<https://craftbettersoftware.com/p/build-your-ai-agent-the-right-way>)

Author: Daniel Moka

Published: 2026-03-02T06:20:17Z

Content type: tutorial

Language: en

Sources: [Craft Better Software](<https://devfeed.tech/sources/craft-better-software.md>)

Topics: [OpenClaw](<https://devfeed.tech/topics/openclaw.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-assistant](<https://devfeed.tech/tags/ai-assistant.md>), [ai-subscriptions](<https://devfeed.tech/tags/ai-subscriptions.md>), [app](<https://devfeed.tech/tags/app.md>), [bot](<https://devfeed.tech/tags/bot.md>), [chrome](<https://devfeed.tech/tags/chrome.md>), [chrome-extension](<https://devfeed.tech/tags/chrome-extension.md>), [code](<https://devfeed.tech/tags/code.md>), [computing](<https://devfeed.tech/tags/computing.md>), [configuration](<https://devfeed.tech/tags/configuration.md>), [data](<https://devfeed.tech/tags/data.md>), [database](<https://devfeed.tech/tags/database.md>), [databases](<https://devfeed.tech/tags/databases.md>), [debug](<https://devfeed.tech/tags/debug.md>), [docker](<https://devfeed.tech/tags/docker.md>), [gateway](<https://devfeed.tech/tags/gateway.md>), [getting-started](<https://devfeed.tech/tags/getting-started.md>), [hetzner](<https://devfeed.tech/tags/hetzner.md>), [openclaw](<https://devfeed.tech/tags/openclaw.md>)

### AI overview

The excerpt recommends running OpenClaw in Docker on an always-on Mac mini or VPS, then focusing on configuration rather than installation tweaks. It says to define the agent's identity first so it challenges assumptions and prioritizes correctness over politeness. Because the project moves quickly and includes many issues, pull requests, and AI-generated contributions, the author advises treating it like production code and setting firm security boundaries. The visible checklist starts with keeping the gateway private and requiring pairing; the excerpt cuts off before the remaining security steps.

### Source excerpt

Setting Up Your AI Assistant of OpenClaw Correctly for Real Work

## The Vibe Coding Stack for 2026

DevFeed: [The Vibe Coding Stack for 2026](<https://devfeed.tech/articles/the-vibe-coding-stack-for-2026-26215.md>)

Original publisher: [Read original article](<https://craftbettersoftware.com/p/the-vibe-coding-stack-for-2026>)

Author: Daniel Moka

Published: 2025-12-13T06:01:36Z

Content type: tutorial

Language: en

Sources: [Craft Better Software](<https://devfeed.tech/sources/craft-better-software.md>)

Topics: [Vibe coding](<https://devfeed.tech/topics/vibe-coding.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [coding assistant](<https://devfeed.tech/topics/coding-assistant.md>), [Programming](<https://devfeed.tech/topics/programming.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [autocomplete](<https://devfeed.tech/tags/autocomplete.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [claude-md](<https://devfeed.tech/tags/claude-md.md>), [code](<https://devfeed.tech/tags/code.md>), [coding](<https://devfeed.tech/tags/coding.md>), [command](<https://devfeed.tech/tags/command.md>), [commands](<https://devfeed.tech/tags/commands.md>), [context](<https://devfeed.tech/tags/context.md>), [conversations](<https://devfeed.tech/tags/conversations.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [costs](<https://devfeed.tech/tags/costs.md>), [developers](<https://devfeed.tech/tags/developers.md>), [software](<https://devfeed.tech/tags/software.md>), [stack](<https://devfeed.tech/tags/stack.md>), [vibe-coding](<https://devfeed.tech/tags/vibe-coding.md>)

### AI overview

The excerpt recommends using Claude Code as a context-aware coding agent: connect it to the code through its VS Code extension, document project goals, stack, layout and conventions in a Claude.md file (including nested files for richer context), and ask it to explore, plan, then code. It suggests enabling Plan Mode for larger tasks, using /clear when conversations drift to refresh context and reduce token use, and creating reusable slash commands for workflows such as generating tests or summarizing log errors. The author says this approach leads to fewer mistakes and cleaner code, but the excerpt provides no comparative evidence for that claim and gives no substantive guidance on the other tools it names.

### Source excerpt

How Top Developers Supervise AI to Craft Better Software

## Code Review with AI: Best Practices

DevFeed: [Code Review with AI: Best Practices](<https://devfeed.tech/articles/code-review-with-ai-best-practices-26203.md>)

Original publisher: [Read original article](<https://craftbettersoftware.com/p/code-review-with-ai-best-practices>)

Author: Daniel Moka

Published: 2025-10-11T05:01:22Z

Content type: tutorial

Language: en

Sources: [Craft Better Software](<https://devfeed.tech/sources/craft-better-software.md>)

Topics: [ai code review](<https://devfeed.tech/topics/ai-code-review.md>), [Code review](<https://devfeed.tech/topics/code-review.md>), [Pull Request](<https://devfeed.tech/topics/pull-request.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Visual Studio Code](<https://devfeed.tech/topics/visual-studio-code.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [apis](<https://devfeed.tech/tags/apis.md>), [best-practices](<https://devfeed.tech/tags/best-practices.md>), [bugs](<https://devfeed.tech/tags/bugs.md>), [business](<https://devfeed.tech/tags/business.md>), [code-review](<https://devfeed.tech/tags/code-review.md>), [config](<https://devfeed.tech/tags/config.md>), [configure](<https://devfeed.tech/tags/configure.md>), [custom](<https://devfeed.tech/tags/custom.md>), [focus](<https://devfeed.tech/tags/focus.md>), [helps](<https://devfeed.tech/tags/helps.md>), [ide](<https://devfeed.tech/tags/ide.md>), [ignore](<https://devfeed.tech/tags/ignore.md>), [inside](<https://devfeed.tech/tags/inside.md>), [jira](<https://devfeed.tech/tags/jira.md>), [linear](<https://devfeed.tech/tags/linear.md>), [review](<https://devfeed.tech/tags/review.md>), [tips](<https://devfeed.tech/tags/tips.md>)

### AI overview

CodeRabbit's review quality can be improved by configuring it for the repository and keeping pull requests small. The excerpt says CodeRabbit clones the repo into a sandbox to build codebase context, and can use past PRs and linked Jira, Linear, GitHub, or GitLab issues to infer change intent. A `.coderabbit.yaml` can filter out WIP or draft branches and generated files, set review tone, enable chat and a knowledge base, and define path-specific review instructions. The source also recommends splitting large PRs because they can slow reviews and increase the chance of missed bugs or irrelevant comments. It begins to describe using CodeRabbit in an IDE such as VS Code before committing, but the excerpt cuts off before explaining that workflow.

### Source excerpt

Practical tips to use the best AI-powered code review assistant

## Five Proven Practices for Mastering Debugging

DevFeed: [Five Proven Practices for Mastering Debugging](<https://devfeed.tech/articles/debug-like-a-pro-26205.md>)

Original publisher: [Read original article](<https://craftbettersoftware.com/p/debug-like-a-pro>)

Author: Daniel Moka

Published: 2025-10-04T05:01:09Z

Content type: article

Language: en

Sources: [Craft Better Software](<https://devfeed.tech/sources/craft-better-software.md>)

Topics: [debugging](<https://devfeed.tech/topics/debugging.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [test](<https://devfeed.tech/topics/test.md>)

Tags: [debug](<https://devfeed.tech/tags/debug.md>), [debugging](<https://devfeed.tech/tags/debugging.md>), [prompt](<https://devfeed.tech/tags/prompt.md>), [test](<https://devfeed.tech/tags/test.md>)

### AI overview

An article presents five practices for improving debugging: writing reproducible bug reports, prompting AI with a structured diagnosis process, and writing failing tests for bugs. It frames debugging as a disciplined engineering practice focused on questioning assumptions and preventing future defects.

### Source excerpt

5 proven practices to master your debugging skills.

## 100 Tips to Write Clean Code

DevFeed: [100 Tips to Write Clean Code](<https://devfeed.tech/articles/100-tips-to-write-clean-code-26197.md>)

Original publisher: [Read original article](<https://craftbettersoftware.com/p/100-tips-to-write-clean-code>)

Author: Daniel Moka

Published: 2025-09-17T05:03:43Z

Content type: tutorial

Language: en

Sources: [Craft Better Software](<https://devfeed.tech/sources/craft-better-software.md>)

Topics: [clean-code](<https://devfeed.tech/topics/clean-code.md>), [programming-tips](<https://devfeed.tech/topics/programming-tips.md>), [software-development](<https://devfeed.tech/topics/software-development.md>), [ai code review](<https://devfeed.tech/topics/ai-code-review.md>), [Static code analysis](<https://devfeed.tech/topics/static-code-analysis.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-code](<https://devfeed.tech/tags/ai-code.md>), [ai-code-review](<https://devfeed.tech/tags/ai-code-review.md>), [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [arguments](<https://devfeed.tech/tags/arguments.md>), [ast](<https://devfeed.tech/tags/ast.md>), [boolean](<https://devfeed.tech/tags/boolean.md>), [c-plus-plus](<https://devfeed.tech/tags/c-plus-plus.md>), [c-sharp](<https://devfeed.tech/tags/c-sharp.md>), [changes](<https://devfeed.tech/tags/changes.md>), [class](<https://devfeed.tech/tags/class.md>), [classes](<https://devfeed.tech/tags/classes.md>), [clean-code](<https://devfeed.tech/tags/clean-code.md>), [code](<https://devfeed.tech/tags/code.md>), [commits](<https://devfeed.tech/tags/commits.md>), [functions](<https://devfeed.tech/tags/functions.md>), [tips](<https://devfeed.tech/tags/tips.md>)

### AI overview

The excerpt presents clean code as readable, business-focused code that can be changed with confidence, then offers practical guidance on naming, functions, and classes. It recommends intention-revealing, searchable names; small, concise functions with few arguments and minimal side effects; and classes with one main responsibility. A sponsor section describes CodeRabbit CLI as a terminal-based review tool that can inspect staged or unstaged changes, files, commits, and branches within Git workflows. It claims to flag issues including code smells, security problems, and performance concerns, and lists free reviews subject to rate limits. The excerpt ends partway through the class tips, so it does not provide the full set of 100.

### Source excerpt

Clean Functions, Classes, Comments, Commits and everything you need to write Clean Code

## Claude Code AI best practices

DevFeed: [Claude Code AI best practices](<https://devfeed.tech/articles/claude-code-ai-best-practices-26201.md>)

Original publisher: [Read original article](<https://craftbettersoftware.com/p/claude-code-ai-best-practices>)

Author: Daniel Moka

Published: 2025-08-23T05:00:29Z

Content type: tutorial

Language: en

Sources: [Craft Better Software](<https://devfeed.tech/sources/craft-better-software.md>)

Topics: [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [software-development](<https://devfeed.tech/topics/software-development.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [VS Code Extension](<https://devfeed.tech/topics/vscode-extension.md>), [Visual Studio Code](<https://devfeed.tech/topics/visual-studio-code.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [coding](<https://devfeed.tech/tags/coding.md>), [development](<https://devfeed.tech/tags/development.md>), [ide](<https://devfeed.tech/tags/ide.md>), [patterns](<https://devfeed.tech/tags/patterns.md>), [prompt](<https://devfeed.tech/tags/prompt.md>), [tdd](<https://devfeed.tech/tags/tdd.md>), [vs-code](<https://devfeed.tech/tags/vs-code.md>)

### AI overview

This developer article shares practical Claude Code workflow advice, including using its VS Code extension, adding Claude.md onboarding documentation to a repository, and following an explore-then-plan-then-code process. The author presents these practices as ways to improve alignment, collaboration, maintainability, and edge-case discovery.

### Source excerpt

The future of coding isn't autocomplete of AI. It's collaboration with AI.

## CodeRabbit as an AI Code Reviewer for Code Quality and Testing

DevFeed: [CodeRabbit as an AI Code Reviewer for Code Quality and Testing](<https://devfeed.tech/articles/the-best-ai-tool-for-clean-code-26214.md>)

Original publisher: [Read original article](<https://craftbettersoftware.com/p/the-best-ai-tool-for-clean-code>)

Author: Daniel Moka

Published: 2025-05-17T05:00:44Z

Content type: opinion

Language: en

Sources: [Craft Better Software](<https://devfeed.tech/sources/craft-better-software.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Code review](<https://devfeed.tech/topics/code-review.md>), [Code quality](<https://devfeed.tech/topics/code-quality.md>), [clean-code](<https://devfeed.tech/topics/clean-code.md>), [Software Testing](<https://devfeed.tech/topics/software-testing.md>), [Code](<https://devfeed.tech/topics/code.md>), [Security](<https://devfeed.tech/topics/security.md>), [SQL](<https://devfeed.tech/topics/sql.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [best-practices](<https://devfeed.tech/tags/best-practices.md>), [code](<https://devfeed.tech/tags/code.md>), [code-quality](<https://devfeed.tech/tags/code-quality.md>), [code-review](<https://devfeed.tech/tags/code-review.md>), [security](<https://devfeed.tech/tags/security.md>), [sql](<https://devfeed.tech/tags/sql.md>), [testing](<https://devfeed.tech/tags/testing.md>)

### AI overview

The article presents CodeRabbit as an AI code reviewer that analyzes pull requests, summarizes changes, generates sequence diagrams, identifies security issues such as SQL injection risks, and suggests improvements to code quality and test coverage.

### Source excerpt

How AI became my favorite code review partner

## How Smart Devs Get Hired in 2025

DevFeed: [How Smart Devs Get Hired in 2025](<https://devfeed.tech/articles/how-smart-devs-get-hired-in-2025-26206.md>)

Original publisher: [Read original article](<https://craftbettersoftware.com/p/how-smart-devs-get-hired-in-2025>)

Author: Daniel Moka

Published: 2025-04-26T05:00:27Z

Content type: tutorial

Language: en

Sources: [Craft Better Software](<https://devfeed.tech/sources/craft-better-software.md>)

Topics: [software-development](<https://devfeed.tech/topics/software-development.md>), [developer-productivity](<https://devfeed.tech/topics/developer-productivity.md>), [Programming](<https://devfeed.tech/topics/programming.md>)

Tags: [2025](<https://devfeed.tech/tags/2025.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-code](<https://devfeed.tech/tags/ai-code.md>), [ast](<https://devfeed.tech/tags/ast.md>), [code-reviews](<https://devfeed.tech/tags/code-reviews.md>), [coding-standards](<https://devfeed.tech/tags/coding-standards.md>), [context](<https://devfeed.tech/tags/context.md>), [cv](<https://devfeed.tech/tags/cv.md>), [dev](<https://devfeed.tech/tags/dev.md>), [feedback](<https://devfeed.tech/tags/feedback.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [job](<https://devfeed.tech/tags/job.md>), [linkedin](<https://devfeed.tech/tags/linkedin.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [performance](<https://devfeed.tech/tags/performance.md>), [pr](<https://devfeed.tech/tags/pr.md>), [tech](<https://devfeed.tech/tags/tech.md>)

### AI overview

The excerpt recommends making a CV quick to scan: keep it to two pages, tailor it to each role, emphasize recent relevant experience and measurable impact, and skip skill bars and generic hobbies. It also frames LinkedIn as an early part of the hiring process and advises using a professional photo, a specific headline and a concise About section. The source text ends mid-list, so further LinkedIn recommendations and the remaining strategies are not available here.

### Source excerpt

How to land your dream job in this brutal tech market

## Write Clean Classes Like a PRO

DevFeed: [Write Clean Classes Like a PRO](<https://devfeed.tech/articles/write-clean-classes-like-a-pro-26216.md>)

Original publisher: [Read original article](<https://craftbettersoftware.com/p/write-clean-classes-like-a-pro>)

Author: Daniel Moka

Published: 2025-04-19T05:00:55Z

Content type: article

Language: en

Sources: [Craft Better Software](<https://devfeed.tech/sources/craft-better-software.md>)

Topics: [clean-code](<https://devfeed.tech/topics/clean-code.md>), [Inheritance](<https://devfeed.tech/topics/inheritance.md>), [software-development](<https://devfeed.tech/topics/software-development.md>), [programming-tips](<https://devfeed.tech/topics/programming-tips.md>), [object](<https://devfeed.tech/topics/object.md>)

Tags: [api](<https://devfeed.tech/tags/api.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [classes](<https://devfeed.tech/tags/classes.md>), [clean-code](<https://devfeed.tech/tags/clean-code.md>), [composition](<https://devfeed.tech/tags/composition.md>), [composition-over-inheritance](<https://devfeed.tech/tags/composition-over-inheritance.md>), [data-transfer-objects](<https://devfeed.tech/tags/data-transfer-objects.md>), [fields](<https://devfeed.tech/tags/fields.md>), [flow](<https://devfeed.tech/tags/flow.md>), [inheritance](<https://devfeed.tech/tags/inheritance.md>), [responsibility](<https://devfeed.tech/tags/responsibility.md>)

### AI overview

The excerpt recommends making classes easier to understand and change by using noun-based names, hiding state behind intention-revealing behavior (with DTOs as an exception), and keeping a class's public API focused. It also suggests ordering methods by call flow so readers can follow the logic. The excerpt begins a recommendation to favor composition over inheritance but cuts off before explaining it, and it introduces six principles without showing them all.

### Source excerpt

7 essential tips to produce maintainable and intention-revealing classes

## How To Refactor Legacy Code

DevFeed: [How To Refactor Legacy Code](<https://devfeed.tech/articles/how-to-refactor-legacy-code-26208.md>)

Original publisher: [Read original article](<https://craftbettersoftware.com/p/how-to-refactor-legacy-code>)

Author: Daniel Moka

Published: 2025-04-12T05:01:26Z

Content type: tutorial

Language: en

Sources: [Craft Better Software](<https://devfeed.tech/sources/craft-better-software.md>)

Topics: [Refactoring](<https://devfeed.tech/topics/refactoring.md>), [Software Testing](<https://devfeed.tech/topics/software-testing.md>), [Dependency injection](<https://devfeed.tech/topics/dependency-injection.md>), [Mocking](<https://devfeed.tech/topics/mocking.md>), [test-coverage](<https://devfeed.tech/topics/test-coverage.md>)

Tags: [dependency-injection](<https://devfeed.tech/tags/dependency-injection.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [legacy-code](<https://devfeed.tech/tags/legacy-code.md>), [refactor](<https://devfeed.tech/tags/refactor.md>), [refactoring](<https://devfeed.tech/tags/refactoring.md>), [testing](<https://devfeed.tech/tags/testing.md>), [tests](<https://devfeed.tech/tags/tests.md>)

### AI overview

A six-step strategy for refactoring legacy code by breaking dependencies, using characterization and other testing techniques, achieving test coverage, and then changing the code.

### Source excerpt

The art of making your code testable, testing it effectively, and refactoring it like a pro

[Next page](<https://devfeed.tech/sources/craft-better-software.md?cursor=WyIyMDI1LTA0LTEyVDA1OjAxOjI2KzAwOjAwIiwgImZkNTNmMWQyLTM4MjEtNDFlNy1hZWU4LTA1ZTg2MTdlNTNmZCJd>)