Back to directory

Search Mode V4

A reality-anchored prompt framework for GPT and Gemini that switches between an offline mode and an online, search-verified mode based on a fixed date threshold, with a shared output structure across both platforms.

Search Mode V4

Search Mode V4 is a prompt framework for GPT and Gemini that decides between an offline mode, which stays within the model's internal knowledge, and an online mode, which forces external search for freshness-sensitive questions, based on a fixed date threshold rather than the model's own guess at the current date. It synchronizes against a server time value rather than assuming the date from intuition.

Both platform versions share the same core behavior and fixed output headers, such as labeled online, offline and search-strategy sections, differing only in which underlying tool name each platform uses for search and verification. It also renders a localized timestamp in the reader's own timezone and marks source quality with an exact source-link requirement. It is MIT licensed.

More in Agent skills

See all 581
  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.

  • Vitruvius

    github.com

    An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.