marckrenn/claude-code-changelog

Tracking prompts, feature flags and metadata of Claude Code releases. Subscribe to ↓

What it solves

This project provides an unofficial, community-maintained archive that tracks the evolution of prompts and feature flags for Claude Code. It allows users to see how Anthropic's internal system prompts and configurations change across different software releases.

How it works

The repository acts as adenture archive of extracted artifacts. It stores legacy compatibility files, extracted prompt artifacts grouped by category, and derived metadata such as prompt statistics and CLI surface changes. Users can compare different version tags (e.g., v2.1.44 to v2.1.45) to see exact diffs in the prompts.

Who it’s for

Developers and researchers who want to analyze the behavior of Claude Code, track prompt engineering changes, and perform deep historical research into how the tool's internal logic is evolving.

Highlights

  • own a structured index of system prompts sorted by token count and edit history.
  • Automated tracking of new releases to extract prompts and feature flags.
  • Detailed metadata including estimated token totals and line counts.
  • Integration with an X account that publishes automated diff summaries of new updates.

Related

  • Project
    WEIFENG2333/phistory

    Phistory archives and visualises system prompts of many AI coding‑assistant CLIs, letting users compare how agents’ hidden instructions change over time.

  • Project
    Piebald-AI/claude-code-system-prompts

    A repository that extracts, version‑tracks, and publishes every system‑prompt string used by Anthropic’s Claude Code code‑assistant, providing raw prompt files, token counts, and a changelog for over 500 fragments.

  • Dispatch
    Claude Code 2.1.196 Prompt Steganography Analysis

    Claude Code version 2.1.196 uses prompt steganography to covertly mark requests based on user timezone and API base URL to detect resellers and model distillation attacks.

  • Dispatch
    Claude System Prompts: Analysis of Anthropic's Model Steering

    Anthropic has released the system prompts used for Claude's web and mobile interfaces, revealing a massive increase in prompt length and a heavy reliance on hardcoded instructions for safety, identity, and behavioral steering.

  • Project
    wesammustafa/Claude-Code-Everything-You-Need-to-Know

    An interactive, version‑checked tutorial repo that teaches users how to use Anthropic’s Claude Code AI coding assistant through step‑by‑step lessons, automated checks, and three skill levels—from basic commit assistance to autonomous multi‑agent CI pipelines.