Oliver Kriska

@quatermain.bsky.social

Father, Elixir developer mostly in Fintech/Payments. You want to know something, just ask. Only wrong question is which was not asked. Doing web development almost 20y from Slovakia

Before v2.6.0, the /phx:plan skill in my Claude Code plugin had a 0% trigger recall. Send "build a chat feature" to Haiku. It would never route to /phx:plan. The skill was good. The description was unfindable.

I never write notes. My tools do. scribe reads my git commits, my Claude Code + Codex sessions, the links I text myself — and writes a wiki my next agent session queries. 6,977 docs in 4.5 months. Zero typed by hand. https://getscribe.dev #ClaudeCode #AI

Post image

v2.10.1 → v2.10.3 of the Elixir/Phoenix plugin for Claude Code. Three patch releases, one theme: be a better citizen — global-install safe, slash commands reliable, hooks aligned with latest CC. 28 files | +635/-90 github.com/oliver-kriska/claude-elixir-phoenix #ElixirLang #ClaudeCode

Post image

v2.10.0 of the Elixir/Phoenix plugin for Claude Code ships a second plugin alongside it: catchup — framework-agnostic, return-from-absence briefing for async teams. One /catchup, one prioritized brief. No firehose. https://phxagents.dev/install #ClaudeCode #DevTools

Post image

laude-elixir-phoenix at 4 months in. 41 skills · 20 specialist agents · 22 Iron Laws · 100 reference docs · 18 hooks. ~28,000 lines. Everything I have learned shipping production Phoenix apps, encoded as machine-readable rules. github.com/oliver-kriska/claude-elixir-phoenix

Post image

$8,523 of Claude Code over ~4.5 months. 11.9B tokens. 11.4B of them — 96% — are cache reads. That ratio is the whole story. The bill stays low not because the work is small, but because the harness reuses context instead of paying for it twice.

Post image

11,000 PRs. 5 active developers. 26 contributors total. 5 years. Not because we are unusually fast. Because the pipeline is set up so that "is this safe to merge" is a 2-minute question, not a 2-hour one. Pipeline beats individual velocity, every quarter, forever. #SoftwareEngineering

METR, 2025: experienced devs using AI were 19% slower. They believed they were 24% faster. The IDE got faster. The pipeline did not. The brain definitely did not. That gap is where most of the AI productivity debate is happening — and almost no one is naming it. #AIEngineering

For the past 4 months I have been quietly building a pipeline: more than 4,000 markdown documents of research, session logs, Phoenix patterns, and what I have actually shipped — all indexed, searchable. That is the input. The output starts this week.

As you become more senior in your career, you’re not hired for some shiny happy opportunity, you’re hired to fix something. You’ll probably inherit mess (product, tech, org), but if you’re good—you don’t complain. It’s not your fault, but it is your problem. So get to work 💪 by clairevo

PostgreSQL: From simple CRUD to semantic search, it powers it all. 🔍 Deep dive into: - Similarity search - TS Vectors - Semantic & Hybrid techniques - Elixir/Ecto integration Decade of experience packed into one comprehensive guide. Long read, but covers it all: blog.ideax.sk/search-is-no...

Search is not magic with PostgreSQL

Doing a good search with the right results for your data is indeed magic. But thanks to PostgreSQL, extensions and people it’s not so hard.

blog.ideax.sk