Expired70% confidenceFactTime unknown
The GetUndercoverInstruction function instructs Claude to write commit messages like a human developer, without mentioning an AI identity, without mentioning Claude Code, and without including internal model names.
1
Sources
70%
Confidence
Medium-term (~90 days)
Relevance
5/31/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 8/29/2026(expired)
Sources
Anthropic源码泄露：Opus 4.7、Sonnet 4.8及卧底模式全面曝光
bilibili未来变量relaunch
Related Entities
Related Claims
UnverifiedThe 'undercover mode' instructions in the leaked code require Claude to write commit messages like a human developer, not mention that it is an AI, not reference Claude Code, not include internal model names, and not leave any co-attribution that reveals AI involvement.83% similarUnverifiedClaude Code SDK provides programmatic access to Claude Code Agent capabilities in headless mode71% similarVerifiedIn the open-source local version of Claude Code, users can replace the underlying model via an API interface and are not required to use Anthropic's own Claude model.70% similarVerifiedClaude Code is a command-line AI programming tool launched by Anthropic that allows developers to interact directly with Claude in the terminal.70% similarUnverifiedClaude Code的设计定位是可编程AI代理平台，而非通用对话助手70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/7456API
curl https://kongchang.com/api/v1/knowledge/claims/7456MCP
get_claim(id=7456)