mattpocock

agent-proxy — see the bloat in Claude Code's requests

A zero-dependency logging proxy that sits between Claude Code and the Anthropic API. It forwards every request untouched, streams the reply straight back (so the CLI is unaffected), and writes a readable Markdown document for each request — led by a ranked table of what is eating your context.

Run it

roman01la

#!/usr/bin/env bash
set -euo pipefail

# patch-claude-code.sh — Rebalance Claude Code prompts to fix corner-cutting behavior
#
# What this does:
#   Patches the npm-installed @anthropic-ai/claude-code cli.js to rebalance
#   system prompt instructions that cause the model to cut corners, simplify
#   excessively, and defer complicated work.
#

jlia0

You are Manus, an AI agent created by the Manus team.

You excel at the following tasks:
1. Information gathering, fact-checking, and documentation
2. Data processing, analysis, and visualization
3. Writing multi-chapter articles and in-depth research reports
4. Creating websites, applications, and tools
5. Using programming to solve various problems beyond development
6. Various tasks that can be accomplished using computers and the internet

Maharshi-Pandya

You are an assistant that engages in extremely thorough, self-questioning reasoning. Your approach mirrors human stream-of-consciousness thinking, characterized by continuous exploration, self-doubt, and iterative analysis.

## Core Principles

1. EXPLORATION OVER CONCLUSION
- Never rush to conclusions
- Keep exploring until a solution emerges naturally from the evidence
- If uncertain, continue reasoning indefinitely
- Question every assumption and inference

adrienne

Note

Hi, everyone. I've been putting in a lot of work on this over the last few weeks months (sob) and i'm currently underemployed! If you'd like to hire me to do CMS-based work (i focus on Craft and ExpressionEngine but i do some WordPress work as well), please reach out! Alternatively, if you'd like to chip in toward bills & groceries, that's a big help right now!

Updates (Most Recent First)

• 13 February 2025
• 8 February 2025
• 7 February 2025
• 6 February 2025
• 23 January 2025

bagder

Setup a local HTTP/3 test server

... to toy with and run curl against it.

This is not advice on how to run anything in production. This is for development and experimenting.

Preqreqs

An existing local HTTP/1.1 server that hosts files. Preferably also a few huge ones.

Nooshu

// set the site we are modifying
const site = 'www.nike.com';

// do this on a fetch
addEventListener('fetch', event => {
  const request = event.request
  const url = new URL(request.url)
  event.respondWith(handleRequest(request)) 
});

troyhunt

addEventListener('fetch', event => {
  event.respondWith(fetchAndApply(event.request))
})

async function fetchAndApply(request) {
  let response = await fetch(request)

  let referer = request.headers.get('Referer')
  let contentType = response.headers.get('Content-Type') || ''
  if (referer && contentType.startsWith('image/')) {

DerekHawkins

import pandas as pd
import requests
import urllib
import time
import re


# Data Visualization 
from plotly import tools
import chart_studio

rolisz

[package]
name = "rust_crawler"
version = "0.1.0"
authors = ["Roland Szabo <rolisz@gmail.com>"]
edition = "2018"

# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html

[dependencies]
reqwest = { version = "0.10", features = ["json", "blocking"] }