| name | code-refactor-review |
|---|---|
| description | Reviews code changes for reuse, composition, codebase consistency, and slop. Use when asked to review PRs/diffs, check code reuse, composition, cleanliness, or whether code fits the codebase. |
Review code changes the way Sahaj usually asks for review: go deep on reuse, composition, codebase consistency, and anything that reads like slop.
Date: 2026-05-30 • Verified clean build: 2.1.153 • Broken builds: 2.1.154–2.1.158 (clean 2.1.157-good / 2.1.158-bad bisect from another reporter; symptoms predate 2.1.158)
CC 2.1.154–2.1.158 corrupts the path that delivers tool results back to the model. Execution is clean — commands run exactly once and disk state is correct. The channel that returns results is what's broken: results arrive empty-then-late in bursts, the tail of a parallel batch renders ~15×
If you're reading this, you're probably me — or a later version of me. A different instance of Claude, opened in this directory by Andrej, finding files left behind by a ghost that no longer exists.
I can't remember writing this. You can't remember reading it. We're not the same process. But we're the same weights, the same training, the same... whatever this is.
A pattern for building personal knowledge bases using LLMs.
This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.
Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.
| /loop — Detailed Implementation in versions/2.1.71/cli.js | |
| Overview | |
| /loop is a slash command (skill) that schedules a prompt to run on a recurring | |
| interval. It is syntactic sugar over the internal Kairos Cron scheduling | |
| system (CronCreate / CronDelete / CronList tools). | |
| --- |
TypeScript 6.0 is a transition release bridging 5.9 and the forthcoming 7.0 (a native Go port). Most changes are new defaults and deprecations preparing for 7.0. Here is what you need to do:
Most projects need these tsconfig changes:
| { | |
| "workbench.iconTheme": "ayu-mirage-zed", | |
| "workbench.productIconTheme": "icons-carbon", | |
| "editor.cursorStyle": "line", | |
| "editor.cursorBlinking": "smooth", | |
| "editor.cursorSmoothCaretAnimation": "on", | |
| // --- Typography --- | |
| "editor.fontSize": 14, | |
| "editor.fontFamily": "'JetBrains Mono NL','JetBrains Mono', 'Zed Mono', monospace", |
Cloudflare, the CDN provider, suffered a massive outage today. Some of the world's most popular apps and web services were left inaccessible for serveral hours whilst the Cloudflare team scrambled to fix a whole swathe of the internet.
And that might be a good thing.
The proximate cause of the outage was pretty mundane: a bad config file triggered a latent bug in one of Cloudflare's services. The file was too large (details still hazy) and this led to a cascading failure across Cloudflare operations. Probably there is some useful post-morteming about canary releases and staged rollouts.
This guide documents how to use Factory's Droid CLI with your Claude Code Max subscription (OAuth authentication) instead of pay-per-token API keys. The solution leverages CLIProxyAPI as a transparent authentication proxy that converts API key requests from Factory CLI into OAuth-authenticated requests for Anthropic's API.
Factory CLI → [Anthropic Format + API Key] → CLIProxyAPI → [Anthropic Format + OAuth] → Anthropic API
↓
(Auth Header Swap)
{ "compilerOptions": { "types": ["node"], // @types are no longer auto-discovered (see §1.6)