AI Coding Agents

These pages cover the agents themselves: how they are configured, what they are good and bad at, and the workflow changes that follow when most code arrives from one.

37 articles, newest first.

Shiplight blog cover: a shelf of skill folders sorted into bundled, vendor and community groups, with a test-status panel showing green checks beside the loaded skills
AI TestingGuides

Best Claude Code Skills for Testing and QA

Shiplight blog cover, light gradient, indigo accents, showing a Claude Code terminal connected by lines to a small grid of labeled MCP server nodes
GuidesEngineering

Best MCP Servers for Claude Code: 9 Worth Installing

Shiplight blog cover, light gradient, indigo accents, diagram of the Claude Code agent core surrounded by five extension layers labeled skills, hooks, subagents, MCP servers, and plugins
GuidesEngineering

What Is Claude Code? The Terminal Agent and Its Extension Model

Shiplight blog cover: an event timeline of a Claude Code session with hook checkpoints firing at PreToolUse, PostToolUse and Stop, one gate shown blocking in red and one passing in green
GuidesEngineering

Claude Code Hooks: Deterministic Rules for an Agentic Workflow

Shiplight blog cover, light gradient, indigo accents, diagram of a plugin package bundling skill, agent, hook, and MCP server cards into a single installable box
GuidesEngineering

Claude Code Plugins: The Bundle Layer Explained

Shiplight blog cover, light gradient, indigo accents, diagram of a main Claude Code agent delegating tasks to three subagent context windows defined by markdown files
GuidesEngineering

Claude Code Subagents: How to Define Them and When to Delegate

Shiplight blog cover, light gradient, indigo accents, split diagram of a terminal window and an IDE window each running a coding agent, connected to a shared browser verification layer
GuidesEngineering

Claude Code vs Antigravity: Terminal Agent or Agent-First IDE

Shiplight blog cover: a SKILL.md file being assembled from frontmatter and instruction blocks into a folder, with an arrow showing the agent loading it on demand
GuidesEngineering

How to Create a Claude Code Skill, Step by Step

Shiplight blog cover, light gradient, indigo accents, with a diagram of a .cursor/rules folder feeding rule files into an agent's context window alongside a skills folder and MCP tools
GuidesEngineering

Cursor Rules: How They Work and When a Rule Beats a Skill

Shiplight blog cover, light gradient, indigo accents, a two-gate diagram showing an agent action passing a pre-action gate before execution and a post-action gate after
GuidesEngineering

Pre-Action Checks for AI Coding Agents: Tools and Patterns

Illustrated Shiplight blog cover: several agents working on separate partitions of one codebase, converging on a single verified result.
GuidesEngineering

Claude Code Agent Teams: Coordinating Several Agents at Once

Illustrated Shiplight blog cover: a glossy proposed plan document floating above a codebase with an approval gate before any edit reaches the files.
GuidesEngineering

Claude Code Plan Mode: What It Does and When to Use It

Illustrated Shiplight blog cover: a glossy folder of instruction cards being loaded on demand into an agent, beside distinct hook and subagent layers.
GuidesEngineering

Claude Code Skills: What They Are and When to Use One

Illustrated Shiplight blog cover: a glossy code editor window with visible inline diffs beside an autonomous terminal agent window, linked by a glowing verification loop.
GuidesEngineering

Claude Code vs Cursor: Which AI Coding Tool in 2026?

Illustrated Shiplight blog cover: a glossy terminal window dispatching a coding task to a cloud sandbox and receiving a finished diff back.
GuidesEngineering

Codex CLI: What It Is and How Teams Actually Use It

Illustrated Shiplight blog cover: a committed instruction file feeding conventions into a coding agent, with an enforcement gate beside it.
GuidesEngineering

Codex Skills: Teaching the Agent Your Conventions

Illustrated Shiplight blog cover: a token budget meter with the largest slice consumed by retries and oversized tool responses rather than the task.
GuidesEngineering

Codex Usage: Where the Tokens Actually Go

Illustrated Shiplight blog cover: two glossy terminal windows facing each other in balanced head-to-head comparison, each streaming generated code, a bright green verification checkmark floating between them.
GuidesEngineering

Codex vs Claude Code: Which Terminal Coding Agent in 2026?

Illustrated Shiplight blog cover: a glossy code editor window and a terminal agent window sharing one codebase between them.
GuidesEngineering

Cursor CLI: The Terminal Half of an Editor-First Tool

Illustrated Shiplight blog cover: an open modular terminal harness with several swappable glowing model cards slotting into it, beside a single sealed managed agent capsule.
GuidesEngineering

OpenCode vs Claude Code: Open Source Agent or Managed One?

Illustrated Shiplight blog cover: one main agent context delegating two isolated side contexts that return only their conclusions.
GuidesEngineering

Subagents: When Splitting the Context Actually Helps

Illustrated Shiplight blog cover: two glossy AI code editor windows side by side, one showing inline diffs and one showing an autonomous multi-step flow.
GuidesEngineering

Windsurf vs Cursor: Which AI Editor Fits Your Workflow?

context sources - a document, a code window, tools, and a green test checkmark - streaming into a bright central AI chip.
EngineeringGuides

Context Engineering for Coding Agents

Illustrated Shiplight blog cover: a glossy code editor window connected by a glowing link to a browser window being verified with a bright green checkmark.
EngineeringAI Testing

How to Test Code Written by Cursor

Illustrated Shiplight blog cover: a glossy AI chip reading a specification document and producing a small app window, with a green checkmark verifying the output matches the spec, arranged in a compact loop.
EngineeringGuides

Spec-Driven Development with AI Coding Agents

Illustrated Shiplight blog cover: glossy green test-checkmark cards feeding as fuel into a glossy AI chip that then writes clean code, with a subtle feedback loop arrow.
AI Testing

Tests Are the Best Context You Can Give a Coding Agent

Diagram of a coding agent's verification loop: write code, see the result in a real browser, record the check as a reviewable test
AI TestingTesting Strategy

Can Coding Agents Test Their Own Code?

Illustrated Shiplight blog cover: a glossy AI coding-agent core plugging into a real browser window and emitting freshly generated test cards, the nearest stamped with a bright green checkmark.
GuidesTool Comparisons

Top Coding Agent Plugins for Automated Test Generation (2026)

Marketing cover with the headline 'Vibe Coding QA Process.' on the left and a circular 9-stage closed-loop diagram on the right: nine numbered indigo circles (01 highlighted) arranged in a ring with arrowheads indicating clockwise flow and a 'QA Loop' label in the center
AI TestingBest Practices

How to Set Up a Vibe Coding QA Process: A Practical 9-Stage Workflow for 2026

Two trajectories diverging (output velocity climbing steadily while production bug rate spikes) visualizing the 6-week vibe coding quality cliff
AI TestingEngineering

Vibe Coding Quality Issues: A Triage Playbook for Engineering Leaders

Two contrasting test paradigms (rigid pre-coded scripts on the left, fluid AI-driven intent flows on the right), illustrating how vibe testing replaces brittle selectors with natural-language intent
AI TestingTesting Strategy

What Is Vibe Testing? Definition + Why It Matters (2026)

Illustrated Shiplight blog cover: a glossy podium of floating QA tool cards with the top one elevated and glowing, a bright green checkmark crowning the winner, a coding-agent chip looking on.
AI TestingGuides

5 Best AI QA Tools for Coding Agents (2026): Real Results

Marketing cover for 'QA Code Written by Claude Code' with a Shiplight indigo pill badge and left-aligned hero, and on the right a feedback-loop diagram between a top indigo Coding Agent tile and a bottom white Tester tile (with checkmark shield) connected by curved indigo arrows and a green PASS badge
AI TestingGuides

How to QA Code Written by Claude Code

Marketing cover for 'QA AI-Written Code from Codex' with a Shiplight indigo pill badge and left-aligned hero, and on the right a horizontal pipeline of four stages (Prompt → Code → Test → Ship) connected by arrows with a 'Quality Gate' bracket over the final two stages and the Ship tile filled in solid indigo to mark the verified-merge gate
AI TestingGuides

OpenAI Codex Testing: How to QA AI-Written Code

Illustrated Shiplight blog cover: a glossy fast-moving vibe-coded app window with a bright green verification safety net stretched beneath it, speed meeting a safety net.
AI TestingEngineering

Vibe Coding Testing: How to Add QA Without Slowing Down

AI coding workflow: AI writes code, agent verifies in browser, test saved as YAML
Engineering

How to Add Automated Testing to Cursor, Copilot, and Codex

Illustrated Shiplight blog cover: a glossy verification layer bar sitting between a row of AI coding-agent chips above and a running app below, stamped with a green checkmark.
EngineeringEnterprise

The Testing Layer for the AI Age: Closing the Loop Between AI Coding Agents and Real End-to-End Quality

Other topics

Agent-Native TestingFlaky TestsSelf-Healing TestsMCP and Agent ToolingPlaywrightEnd-to-End TestingCI and Release GatesTesting AI FeaturesTool ComparisonsEnterprise and ComplianceQA FoundationsSpec-Driven DevelopmentNo-Code and Natural-Language TestingAI Testing StrategyAgentic QA

See testing that keeps up with your AI coding agents.