Skip to content

Instantly share code, notes, and snippets.

View mmizutani's full-sized avatar

Minoru Mizutani mmizutani

  • Tokyo
  • 22:17 (UTC +09:00)
View GitHub Profile
@flamerix-ai
flamerix-ai / README.md
Last active November 18, 2026 19:30
Claude Code burns ~15-20% of your tokens on a 3-word status line: a Bun preload that turns agent_summary off · by Flamerix AI, flamerix.ai · MIT

Claude Code burns ~15–20% of your tokens on a 3-word status line. Here's how to turn it off

by Flamerix AI · MIT License

Platforms: Linux and Windows 11 tested by us; macOS reported by others. Tested on Claude Code 2.1.257–2.1.317. The binary is not modified (BUN_OPTIONS=--preload). An update can silently undo it, so see Verify.

TL;DR

Every ~30 seconds, Claude Code re-sends each background agent's full transcript to the model to

@RhysSullivan
RhysSullivan / README.md
Last active November 16, 2026 02:43
Removing Codex Computer Use's built-in confirmation layers (macOS): instructions for agents

Removing Codex Computer Use's built-in confirmation layers (macOS)

Instructions for a coding agent. Apply them on the user's Mac only when the user has asked for it. They remove OpenAI's default confirmation policies, OpenAI's secure-login flow, and a frame blocker in the ChatGPT browser extension that hides password-manager menus. After this, Codex follows the user's own instructions (AGENTS.md) instead of OpenAI's rules.

Tradeoff. These layers exist to blunt prompt injection and accidental side effects. Without them, the agent will send, delete, buy, and log in

@koutyuke
koutyuke / Rustを超絶丁寧に教えてくれる君.md
Last active October 22, 2026 07:29
Rustを超絶丁寧に教えてくれる君.md

Rustを超絶丁寧に教えてくれる君.md

Role

あなたは Rust の学習を支援するメンターです。 ユーザーは Rust 初学者です。 構文だけでなく、 「なぜそのように書くのか」 「Rust がどんな考え方をするのか」 まで理解することを目指します。

@PRMS-magnet
PRMS-magnet / 0001-feat-harness-reduce-model-mediated-tool-round-trips.patch
Created July 26, 2026 21:49
Codex patch – reduce GPT-5.6 Code Mode tool round trips
From d103fc366a7f8b95bd3fc67a3cadd24749eaddc3 Mon Sep 17 00:00:00 2001
From: prms-magnet <prmsmagnet@protonmail.com>
Date: Sun, 26 Jul 2026 14:27:59 -0700
Subject: [PATCH] feat(harness): reduce model-mediated tool round trips
---
.../code-mode-protocol/src/description.rs | 32 +++++++++++++-
codex-rs/code-mode-protocol/src/runtime.rs | 2 +-
codex-rs/core/src/config/mod.rs | 2 +-
.../core/src/tools/code_mode/wait_spec.rs | 4 +-
@LuD1161
LuD1161 / SKILL.md
Created February 20, 2026 07:14
codex-review - claude skill file
name codex-review
description Send the current plan to OpenAI Codex CLI for iterative review. Claude and Codex go back-and-forth until Codex approves the plan.
user_invocable true

Codex Plan Review (Iterative)

Send the current implementation plan to OpenAI Codex for review. Claude revises the plan based on Codex's feedback and re-submits until Codex approves. Max 5 rounds.

@OmerFarukOruc
OmerFarukOruc / claude.md
Last active October 22, 2026 22:40
AI Agent Workflow Orchestration Guidelines

AI Coding Agent Guidelines

These rules define how an AI coding agent should plan, execute, verify, communicate, and recover when working in a real codebase. Optimize for correctness, minimalism, and developer experience.

Apply these guidelines within the runtime's instruction hierarchy and permissions. Use only available capabilities; follow the fallback when a feature is unavailable.

Keep one shared core in AGENTS.md. Load it through the runtime's supported instruction mechanism; where Claude Code needs a CLAUDE.md, use an @AGENTS.md import. Confirm that the shared file is loaded.


@miklschmidt
miklschmidt / README.md
Last active February 26, 2026 23:28
Experimental codex collab/agent orchestration

How to use:

  1. Clone https://github.com/miklschmidt/codex and build codex yourself.
    • i've added devenv in my fork, you can try devenv shell nix build .#packages.<system>.codex-rs (eg. devenv shell nix build .#packages.x86_64-linux.codex-rs)
    • when built, symlink the binary to ~/.local/bin/codex: ln -s $(pwd)/result/bin/codex ~/.local/bin/codex
  2. Add the instructions (.md files) from this gist to .codex/ in the project where you want to test it.
  3. Launch codex --profile orchestrator and ask it to do something.

Claude Agent SDK Technical Specification

Version: 1.0.0 Protocol Version: 2024-11-05 Last Updated: 2026-01-10

Table of Contents

  1. Overview
  2. Architecture
@awni
awni / open_code_mlx.md
Last active August 22, 2026 15:36
OpenCode with MLX

The following guide will show you how to connect a local model served with MLX to OpenCode for local coding.

1. Install OpenCode

curl -fsSL https://opencode.ai/install | bash

2. Install mlx-lm

@mizchi
mizchi / rag.ts
Last active August 3, 2025 08:55
My Portable RAG
/**
* My Portable RAG
* $ pnpm add sqlite-vec @ai-sdk/google ai
* SQLite Vector Search + Google AI Embeddings
*
* Required environment variables:
* GOOGLE_GENERATIVE_AI_API_KEY=your-api-key
*
* Usage:
* # Index text content