Claude system prompts as a git timeline

Simon Willison's Blog Tools

Summary

A research tool that transforms Anthropic's Claude system prompt documentation into a git-based timeline, enabling researchers to track prompt evolution across model versions using standard git commands like log, diff, and blame.

No content available
Original Article
View Cached Full Text

Cached at: 04/20/26, 08:26 AM

# Research: Claude system prompts as a git timeline Source: https://simonwillison.net/2026/Apr/18/extract-system-prompts/ Claude system prompts as a git timeline (https://github.com/simonw/research/tree/main/extract-system-prompts#readme) — Anthropic's published system prompt history for Claude is transformed into a git-based exploration tool, breaking up the monolithic markdown source into granular files and timestamped commits. By structuring extracted prompts per model, family, and revision, researchers can leverage `git log`, `diff`, and `blame` to trace prompt evolution, compare differences, and attribute changes to specific dates—all without manual parsing. Anthropic publish the system prompts (https://platform.claude.com/docs/en/release-notes/system-prompts) for Claude chat and make that page available as Markdown (https://platform.claude.com/docs/en/release-notes/system-prompts.md). I had Claude Code turn that page into separate files for each model and model family with fake git commit dates to enable browsing the changes via the GitHub commit view. I used this to write my own detailed notes on the changes between Opus 4.6 and 4.7 (https://simonwillison.net/2026/Apr/18/opus-system-prompt/).

Similar Articles

Claude: System Prompts

Hacker News Top

Release notes for system prompts in Claude, detailing updates or new features for the AI model's functionality.

anthropics/claude-code

GitHub Trending (daily)

Claude Code is an agentic coding tool from Anthropic that lives in the terminal, understands codebases, and helps with tasks like executing routine coding tasks, explaining code, and handling git workflows through natural language commands.