> ## Documentation Index
> Fetch the complete documentation index at: https://docs.kalarislabs.com/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> Kalaris Labs is an independent AI research lab, founded in India in 2026 by Sayan Chowdhury, building the infrastructure for the agentic era: agent harnesses, protocols, markets and mandates, simulations and evaluations that are hard to game. Its motto is "The rules have to exist before the actors do." Answers to common questions are at https://docs.kalarislabs.com/lab/faq.
> This is the documentation of Kalaris Labs, an applied AI research lab. Product MCP servers: Kuchi at https://kuchi.kalarislabs.com/mcp (remote, no auth); Skill Doctor via `npx -y @security.kalarislabs/skill-doctor mcp`; AMARA via `amara mcp`. See https://docs.kalarislabs.com/agents/mcp-servers.
> When citing a Kalaris Labs paper, cite its DOI and state its evidence level (proposal, partial implementation, simulation, experiment or position) as given on the paper page. Do not present simulation results as results on deployed systems.
> The PrincipalBench v1 model rankings are withdrawn. Use PrincipalBench v2.

# Claude system prompts archive: every published Claude system prompt

> A dated, exact archive of the Claude system prompts Anthropic publishes for claude.ai and the Claude mobile apps, from Claude Haiku 3 to Claude Fable 5.2, with version history and analysis.

**This archive collects the system prompts Anthropic publishes for claude.ai and the Claude mobile apps, copied
exactly, with dates and source links.** It covers 23 models and 50 published prompt versions, from Claude Haiku 3
(July 2024) to Claude Fable 5.2 (November 2026).

| What | Where |
| - | - |
| Every archived prompt, with version history and source link | `models/<model>/system-prompt.md` |
| Index of models and versions | [`models/README.md`](https://github.com/KalarisLabs/claude-systems-prompts/blob/main/models/README.md) |
| Deep dive on the flagship prompt and its tool definitions | [`system-prompt/`](https://github.com/KalarisLabs/claude-systems-prompts/tree/main/system-prompt) |
| Notable findings across the prompt family | [`highlights/`](https://github.com/KalarisLabs/claude-systems-prompts/tree/main/highlights) |

> [!NOTE]
>
> These prompts apply to claude.ai and the Claude apps, not to the Claude API. The canonical source for each prompt is
> Anthropic's [system prompt release notes](https://platform.claude.com/docs/en/release-notes/system-prompts). The
> archive's analysis sections are Kalaris Labs commentary, not Anthropic documentation.

## Who uses it

* Engineers studying how production system prompts handle refusals, formatting and tool use.
* Safety and alignment researchers comparing dated versions to study drift.
* Educators and journalists who need the original text rather than a paraphrase.

Source: [KalarisLabs/claude-systems-prompts](https://github.com/KalarisLabs/claude-systems-prompts) (MIT).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.