https://developertoolkit.ai/en/whats-new/ New agentic engineering guides for Claude Code, Codex CLI, and Cursor IDE by MichalBuda (Wondel.ai). en Sat, 10 Oct 2026 12:00:00 GMT https://developertoolkit.ai/en/ladder/vibe-coding-vs-agentic-engineering/ https://developertoolkit.ai/en/ladder/vibe-coding-vs-agentic-engineering/ Sat, 10 Oct 2026 12:00:00 GMT cross-tool The vocabulary of AI-assisted development in one table: who named each term and when, who writes the code, who checks it, and how each differs from vibe coding. Every quote is dated and linked. Use when: a vendor deck, a policy and a job post use four different names for working with AI, and you need to know which of them say who checks the code. https://developertoolkit.ai/en/ladder/level-5-run-the-factory/ https://developertoolkit.ai/en/ladder/level-5-run-the-factory/ Fri, 28 Aug 2026 12:00:00 GMT cross-tool The top rung of the free Ladder section: what the six stations of a software factory — intent, harness, loop, graph, verification, release — actually look like in Claude Code, Codex and Cursor. Use when: agents are opening more pull requests than anyone can read, and you have to decide which parts of the pipeline are safe to stop watching. https://developertoolkit.ai/en/ladder/state-of-agentic-engineering-2026/ https://developertoolkit.ai/en/ladder/state-of-agentic-engineering-2026/ Fri, 28 Aug 2026 12:00:00 GMT cross-tool Third-party evidence, dated: how much production code agents write in 2026, the autonomy ladder from assisted coding to the dark factory, and what stays human. Every number carries a publisher and a date. Use when: someone asks what share of your code agents should write, and you need numbers with sources instead of a vibe. https://developertoolkit.ai/en/ecosystem/frameworks/compound-engineering/ https://developertoolkit.ai/en/ecosystem/frameworks/compound-engineering/ Mon, 24 Aug 2026 12:00:00 GMT cross-tool Every's method for making each unit of work leave the system smarter — and an audit nobody else ran: both directories the guide points at are gone. Plus the measurement that argues its premise backwards. Use when: you keep re-solving problems your team already solved, and nothing you write down ever gets read again. https://developertoolkit.ai/en/ecosystem/skills/unslop/ https://developertoolkit.ai/en/ecosystem/skills/unslop/ Wed, 19 Aug 2026 12:00:00 GMT cross-tool The anti-slop genre in one pass: what unslop bans, why its scanners run in CI without an agent, its own benchmark recording a no-ship — plus miodkuj, for the Polish tells no English word list reaches. Use when: a reviewer keeps writing "this reads like ChatGPT" and nobody can point at the sentence that did it. https://developertoolkit.ai/en/method/principles/software-factories/ https://developertoolkit.ai/en/method/principles/software-factories/ Wed, 12 Aug 2026 12:00:00 GMT cross-tool Dex Horthy says factories fail, PostHog says they work, and both are right about different things. The ceiling is measured; the wound below it is fixable. Use when: your agents open more pull requests than the team can review, and you have to decide what it is safe to stop reading. https://developertoolkit.ai/en/ecosystem/skills/drskill/ https://developertoolkit.ai/en/ecosystem/skills/drskill/ Wed, 12 Aug 2026 12:00:00 GMT cross-tool A read-only CLI that resolves what each coding agent has actually loaded — skills, MCP servers — then checks the result against 34 issue categories, from shadowed names to secrets sitting in configs. Use when: your agent reaches for the wrong tool and you cannot tell what it actually has loaded — or before you let an unfamiliar MCP server near a repo. https://developertoolkit.ai/en/workflows/context/pruning-context-files/ https://developertoolkit.ai/en/workflows/context/pruning-context-files/ Tue, 04 Aug 2026 12:00:00 GMT cross-tool The advice inverted in July: stop adding a rule after every mistake, start deleting. What each tool really loads and when, the truncation Codex performs without a word, and the prompts that do the cutting. Use when: your context file has been growing for months and the agent still ignores the rule you added back in April. https://developertoolkit.ai/en/ecosystem/agent-tools/agent-shells/ https://developertoolkit.ai/en/ecosystem/agent-tools/agent-shells/ Thu, 30 Jul 2026 12:00:00 GMT cross-tool Everywhere you can run Claude Code, Codex and Cursor Agent — Zed and JetBrains over ACP, Conductor, Sculptor, Warp — with a decision table and one rule: does it run your agent, or its own? Use when: you are choosing where to run agents and do not want to build a workflow on a tool that is gone in six months. https://developertoolkit.ai/en/ecosystem/agent-tools/herdr-agent-multiplexer/ https://developertoolkit.ai/en/ecosystem/agent-tools/herdr-agent-multiplexer/ Thu, 30 Jul 2026 12:00:00 GMT cross-tool Real PTY panes and a persistent server like tmux, but every pane classified idle, working or blocked. Under the TUI sits a socket API: one agent can spawn, prompt and supervise the rest. Use when: you are running six agents and one has been sitting on a permission prompt since you went for coffee. https://developertoolkit.ai/en/ecosystem/agent-tools/tmux-for-agent-fleets/ https://developertoolkit.ai/en/ecosystem/agent-tools/tmux-for-agent-fleets/ Thu, 30 Jul 2026 12:00:00 GMT cross-tool Your agents create and clean up their own worktrees now, so the old tutorials sit a layer too low. What is left: sessions, send-keys between agents, wait-for barriers, and hooks that report exact state. Use when: you need runs to survive a closed laptop or a dropped SSH connection, and you want agents to hand work to each other. https://developertoolkit.ai/en/ecosystem/mcp/mobbin-mcp/ https://developertoolkit.ai/en/ecosystem/mcp/mobbin-mcp/ Sat, 25 Jul 2026 12:00:00 GMT cross-tool Ask an agent for a paywall and you get the statistical average of every paywall in its training data. This connects it instead to screens and flows captured from shipped iOS and web products. Use when: your AI-generated interface looks like everyone else’s AI-generated interface. https://developertoolkit.ai/en/ecosystem/skills/taste-skill/ https://developertoolkit.ai/en/ecosystem/skills/taste-skill/ Tue, 21 Jul 2026 12:00:00 GMT cross-tool How Leonxlnx/taste-skill constrains AI frontend generation up front: brief inference, three dials, a design-system map and a hard ban list — plus per-agent install and how it composes with the design pipeline. Use when: every screen your agent generates arrives as the same centred card with a gradient button, and you would rather constrain the generation than correct the output. https://developertoolkit.ai/en/ecosystem/frameworks/superpowers/ https://developertoolkit.ai/en/ecosystem/frameworks/superpowers/ Sat, 11 Jul 2026 12:00:00 GMT cross-tool How a plugin turns brainstorming, worktrees, executable plans, TDD, subagent review and fresh verification into one enforced workflow — with every installation target, the evidence behind it, and honest limits. Verified against upstream v6.1.1. Use when: your agent runs are improvised from scratch each time and you want one workflow it cannot quietly skip a step in, from the first sketch to the pull request. https://developertoolkit.ai/en/claude-code/build/features-you-havent-tried/ https://developertoolkit.ai/en/claude-code/build/features-you-havent-tried/ Fri, 03 Jul 2026 12:00:00 GMT claude-code The underused Claude Code features from Gui Ferreira's NDC AI 2026 talk: one-time setup, your daily loop, extensibility, and work beyond code. Every command verified against the docs, not against the talk. Use when: you have used Claude Code for months and suspect you are still driving it the way it worked a year ago.