Back to directory

Synaptic Lens

A skill that adds a stronger, specialized reasoning model as an architecture and security advisor for AI coding agents, examining a codebase's structure before code is generated.

Synaptic Lens

Synaptic Lens is an advisor-strategy skill that deploys a separate, stronger reasoning model to review architecture, security, debugging, and performance decisions for an AI coding agent, rather than generating code itself. It ingests a project's structure and dependency graph, breaks a task into atomic steps with explicit acceptance criteria and failure conditions, and then directs the coding agent through those steps instead of producing raw code output.

It is described as working across major AI coding environments, including Claude Code, without modification, translating its advisory logic into each environment's native prompting format.

It is distributed as a skill plugin for AI coding agents.

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.