Loading
Also from Kynth Studios
Also from Kynth Studios
Also from Kynth Studios
1# Claude Code System Prompts23## What this repository is45System prompts extracted via script from the Claude Code npm package's compiled JavaScript source. Maintained by [Piebald AI](https://piebald.ai/), not by Anthropic.67See the [Extraction section in README.md](./README.md#extraction) for details on the extraction method.89## What Claude Code is1011Claude Code is Anthropic's CLI tool for agentic coding. It is distributed as a compiled npm package (`@anthropic-ai/claude-code`). Source code is not publicly available. The [anthropics/claude-code](https://github.com/anthropics/claude-code) GitHub repository contains issues and releases only.1213## How to use these files1415- **Reference:** Understand what prompts Claude Code uses and how they change across versions16- **Local patching:** Use [tweakcc](https://github.com/Piebald-AI/tweakcc) to customize individual prompt pieces in your local Claude Code installation17- **Feature requests:** For changes to Claude Code's prompts, file issues at [anthropics/claude-code/issues](https://github.com/anthropics/claude-code/issues)1819## For AI agents working with this repository2021- These files are **extracted reference material**, not modifiable source code22- Editing files here does not change Claude Code's behavior23- The `system-prompts/` directory contains markdown files with YAML frontmatter noting the Claude Code version and template variables24- Template variables like `${BASH_TOOL_NAME}` are interpolated at runtime by Claude Code — they appear as literal strings in these files25- The [CHANGELOG.md](./CHANGELOG.md) tracks prompt changes across Claude Code versions26
Same format, overlapping stack, ranked by quality.
| Repository | Format | Stack | Covers | Score | Changed |
|---|---|---|---|---|---|
| bagisto/bagistoCLAUDE.md · 28k | CLAUDE.md | setupbuildteststyle+5 | 100/100 | 7 days ago | |
| Adit-Jain-srm/NightmareNetCLAUDE.md · 46 | CLAUDE.md | buildtestlint-formatstyle+6 | 100/100 | 14 days ago | |
| nimbalyst/nimbalystpackages/android/CLAUDE.md · 1.5k | CLAUDE.md | setupbuildstylearch+2 | 100/100 | 14 days ago | |
| microsoft/playwrightCLAUDE.md · 95k | CLAUDE.md | buildtestlint-formatstyle+7 | 100/100 | 7 days ago | |
| tphakala/birdnet-goCLAUDE.md · 1.6k | CLAUDE.md | buildtestlint-formatstyle+8 | 100/100 | today | |
| dotCMS/corecore-web/CLAUDE.md · 949 | CLAUDE.md | teststylearchtesting-strategy+3 | 100/100 | 14 days ago | |
| tyrchen/geektime-bootcamp-aiw7/genslides/backend/CLAUDE.md · 230 | CLAUDE.md | testlint-formatstylearch+6 | 100/100 | 9 days ago | |
| livewire/livewireCLAUDE.md · 24k | CLAUDE.md | setupbuildteststyle+4 | 100/100 | 14 days ago |
A badge carrying the measured quality of the strongest agent config file in this repository, out of 100. It reads from this index every time somebody loads your page, so it changes when the measurement changes and there is nothing to keep up to date. Free, no account, and the value is not something you or we can set by hand.
[](https://rulestack.kynth.studio/configs/piebald-ai-claude-code-system-prompts-claude)Would rather not hotlink us? Every badge is also served in shields.io’s endpoint schema, so shields renders the image and your readers never talk to our domain:
Published by Toolproof, the masthead over this index and eight others. The method behind the number is at toolproof.kynth.studio/methodology, and the whole thing is readable as JSON with no key at /api.