Guides from July to October, and the job each one is for.
The 15 most recent guides, from 3 July to 10 October 2026. Each one says what you get from it and when to reach for it, so you can skip the ones that are not your problem this week.
Every guide is available in English and Polish.
The full record Read the full changelogThe digest, by email
A digest lists several new guides and, for each one, what it gives you and the job it is for.
A free account also opens 10 articles a month.
The last digest went out in August 2026. It went to every account with a verified email that had not unsubscribed, free accounts included, and every email has an unsubscribe link.
You already have an account.
The log, newest first.
Filter by topic, or show only the guides that are free to read. Always free: 3 of 15. The other 12 count toward your free monthly articles, and the Toolkit opens all of them.
- Guide
- Free to read
- Filtered out
No guide matches both filters. Switch one off to see more.
October2026
-
Vibe Coding vs Agentic Engineering: 21 Terms Compared
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.
Reach for it 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.
Free to read Ladder
August2026
-
Level 5: You Run the Software Factory
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.
Reach for it 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.
Free to read Ladder -
The State of Agentic Engineering, August 2026
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.
Reach for it when someone asks what share of your code agents should write, and you need numbers with sources instead of a vibe.
Free to read Ladder -
Compound Engineering: The Loop, the Plugin, the Evidence
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.
Reach for it when you keep re-solving problems your team already solved, and nothing you write down ever gets read again.
Frameworks -
Anti-Slop Writing Skills: Unslop, miodkuj, and What the Evals Say
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.
Reach for it when a reviewer keeps writing "this reads like ChatGPT" and nobody can point at the sentence that did it.
Skills -
Software Factories: How to Build One and Keep It From Rotting
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.
Reach for it when your agents open more pull requests than the team can review, and you have to decide what it is safe to stop reading.
Method -
Dr. Skill: Audit What Your Agent Actually Loads
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.
Reach for it 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.
Skills -
Pruning CLAUDE.md and AGENTS.md: The Ablation Protocol
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.
Reach for it when your context file has been growing for months and the agent still ignores the rule you added back in April.
Method
July2026
-
Alternative IDEs and Agent Shells
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?
Reach for it 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.
Agents -
herdr: The Agent Multiplexer With a Scriptable API
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.
Reach for it when you are running six agents and one has been sitting on a permission prompt since you went for coffee.
Agents -
tmux for Agent Fleets: Sessions, send-keys, wait-for
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.
Reach for it when you need runs to survive a closed laptop or a dropped SSH connection, and you want agents to hand work to each other.
Agents -
Mobbin MCP: Real Design Examples for AI Agents
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.
Reach for it when your AI-generated interface looks like everyone else’s AI-generated interface.
MCP -
Taste Skill: The Anti-Slop Frontend Skill Library
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.
Reach for it 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.
Skills -
Superpowers: A Disciplined Design-to-PR Agent Workflow
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.
Reach for it 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.
Frameworks -
What Claude Code Can Do That You Haven’t Tried
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.
Reach for it when you have used Claude Code for months and suspect you are still driving it the way it worked a year ago.
Claude Code
Caught up?
A free account opens 10 articles a month. A digest, when we send one, goes to account holders.
The ladder is free. The Toolkit opens the rest.
$59.99 once for 12 months: every guide in English and Polish, the eight books and the Setup Pack. A first purchase is refundable for 30 days.
$59.99 once for 12 months of access. Nothing renews on its own. 30-day refund on a first purchase.