You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Instantly share code, notes, and snippets.
🏠
Working from home
Omer Faruk Oruc
OmerFarukOruc
🏠
Working from home
Embedded Software Engineer | Founder @ninetech | C/C++, STM32, ESP32, FreeRTOS, TypeScript | Safety-critical systems & AI tooling
Runtime-only scripts for experimenting with hidden Codex Desktop UI feature flags. They launch Codex with a local Chrome DevTools Protocol port and inject renderer feature overrides. They do not modify Codex.app.
Run
First quit Codex Desktop. Only one desktop instance can run at a time, and the launcher needs to reopen it with the override hook.
Option A: ask the codex CLI to run it for you. Paste this into Terminal:
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.
The core idea
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.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Enterprise Slack-native governance substrate for humans, Claude Code, and peer agents — declarative policy + Ed25519-signed audit + crash-safe loss-proof replies (single/chunked/streaming/file) + five-layer prompt-injection defense. v0.12.0.
Enterprise Slack-native governance substrate for humans, Claude Code, and peer agents in shared channels. Declarative policy + signed audit + crash-safe loss-proof replies + five-layer prompt-injection defense.
claude-code-slack-channel v0.12.0
Enterprise Slack-native governance substrate where humans, Claude Code sessions, and peer agents converse safely in shared channels. Every tool call passes through a declarative policy engine; every gate decision lands in a hash-chained, Ed25519-signed audit journal — per-thread session isolation, identity-aware permission gates, five-layer prompt-injection defense, and (new in v0.12.0) crash-safe sessions with loss-proof reply delivery.
A claude/channel implementation for Slack. Socket Mode (outbound WebSocket, no public URL) bridges Slack into a running Claude Code session via MCP stdio. Permission relay with Block Kit buttons, per-thread session isolation, hash-chained Ed25519-signed audit journal, declarative tier-aware policy engine, multi-agent coordin
Codex CLI exec mode experiments: 81 flag/feature tests with raw outputs
Codex CLI Exec Mode Experiments
Date: 2026-03-13
CLI Version: 0.114.0
Total Experiments: 81
Raw experiment outputs from testing various codex exec flag combinations.
Note: Some experiment outputs include MCP (Model Context Protocol) server startup messages (e.g., mcp: flywheel starting, mcp: exa ready). These are from the author's local Codex configuration and do not affect experiment results. Your output may differ depending on your configured MCP servers.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
opencode titlecase crash fix: TypeError when task() called without subagent_type in TypeScript project directories
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
When using [opencode](https://github.com/anomalyco/opencode) (v1.2.6) with the [oh-my-opencode](https://github.com/code-yeongyu/oh-my-opencode) plugin in **TypeScript project directories**, the process crashes with:
```
TypeError: undefined is not an object (evaluating 'str3.replace')
AIO SCRIPT TO SETUP WSL+OMZ+LAZYVIM+ZSH+MISE+OPENCODE+OH+MY+OPENCODE
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters