Blog
Blog.
What I built and how: the stack, the architecture and what I'd change next time.
20 posts · RSS feed
Same agent, rebuilt workspace, a quarter of the bill: what EnvOpt shows
A new arXiv paper leaves the model and the harness alone and lets another AI rebuild the workspace the agent works in. On 200 test tasks, the same Claude Haiku 4.5 agent cost $42.36 before and $11.55 after, and passed more tasks.
7 min read · Read the post →2026
-
CLAUDE.md vs AGENTS.md: which one Claude Code reads, and why I keep only one
When a repository has both files, Claude Code reads CLAUDE.md and leaves AGENTS.md alone unless you import it. I found five of my repositories set up the wrong way round: the real instructions in AGENTS.md, and a CLAUDE.md that only pointed at it.
How I buildAI5 min read -
Running several Claude Code agents at once: worktrees, handoffs and one check per phase
What broke when I put many Claude Code agents on the same repositories, and the four rules that stayed: one worktree per agent, small file-disjoint jobs, a rewritten handoff, and one full check per phase.
How I buildAI5 min read -
Your agent finished the task. Did every step work? What prefix executability shows
A new arXiv paper replays every tool call an agent made and marks the first one that could not run. On 200 function-calling tasks, one agent finished 94 % of them, yet only 47 % of its runs ran clean from start to end.
AIpapers5 min read -
CLAUDE.md, hooks, skills or the task: where each rule for Claude Code belongs
Claude Code gives you four places to put a rule, and they differ in when they load, what they cost and whether they are enforced. How I decide, with the rules in my own setup that moved from one place to another.
How I buildAI6 min read -
Same local model, twice the right answers: what the MuninAI paper changes
A new arXiv paper puts the open-weight model a research group already runs inside an agent loop over its own papers. Accuracy on 199 literature questions went from 38.7 % to 87.4 %, and the usual top-5 retrieval scored worse than no retrieval at all.
AIpapers5 min read -
What Claude Code really costs: tokens per session across thousands of runs
Tokens and list-price cost per finished Claude Code session, from thousands of my own sessions: what fills the context window, why most of the bill is re-reading, and the changes that took one tier from $32.86 to $1.75 a session.
How I buildAI6 min read -
Running many coding agents at once: worktrees, handoffs, one check per phase
The two parts of a many-agents setup that break quietly: the worktree each session works in, and the handoff file a session leaves for the next one. Setup, traps, cleanup and a template.
How I buildAI7 min read -
Claude Code on a server: one copy of the work, and you attach to it
Closing the laptop killed 27 % of my long agent runs. Syncing files to a server is the wrong fix. Here is the one that works, and an open-source setup you can run.
How I buildAI5 min read -
Claude Code hooks: run each one in warn mode for a week first
A hook that blocks the wrong thing stops good work. Mine logged for a week before any of them blocked. One of the rules fired 307 times and was right zero times in the sample I checked.
How I buildAI5 min read -
My CLAUDE.md, and the failure behind each rule
Every line in my CLAUDE.md is there because something went wrong. Here are the rules, what broke, and what an instruction file costs you on every step.
How I buildAI6 min read -
How I run thousands of Claude Code sessions without losing the plot
One task per session, written briefs, handoffs, hooks, what it costs and what went wrong.
How I buildAI12 min read -
Ask for a role, not a model: the small AI gateway behind my sites
Code asks for “summarise” or “translate”, never for a model name. One table decides the rest.
AISvelteKit14 min read -
Why AI-generated websites all look the same, and what I built to stop it
A hundred prompts, the same page a hundred times. The seeds and checks I used against it.
AISvelteKit3 min read -
Meridia: getting places out of news text
News says "the region" and "local authorities". A map needs a place.
ProjectsAI1 min read -
AutoPlakáty: keeping ads playing with no signal
Tablets in moving cars lose signal all the time. The screen still can't go blank.
ProjectsSvelteKit1 min read
2025
-
Niro3D: one price in the browser and on the server
The price you see while configuring has to be the price at checkout. One package does both.
ProjectsGoSvelteKit1 min read -
Lucky Autoservis: local pages in two languages
One matrix of services, car makes and places, in Czech and Russian.
ProjectsSvelteKit1 min read -
ReadVault: a Chrome extension
A reading list that stays on your machine.
Tools3 min read -
BlockAid: a website blocker for Chrome
Blocking distracting sites while you work.
Tools3 min read