Back to directory

Agent

A personal collection of Agent Skills for coding assistants such as Codex, including a pre-launch and pre-commit audit skill and a reliability overlay for safer, more focused coding work.

Agent

Agent is a personal collection of Agent Skills maintained by the author, distributed as portable folders under a skills directory. Each skill folder contains a SKILL.md entry point that an AI coding agent reads, plus agent-specific metadata where needed.

Two skills are included: wtf runs pre-launch and pre-commit audits focused on repository hygiene, secrets, environment variables, database readiness, deployment risks, dead code, and common mistakes in AI-built applications. better-codex is a reliability overlay for Codex coding work, covering scope control, stale-edit prevention, dependency judgment, root-cause debugging, and concise updates.

Skills are installed by copying or symlinking their folders into the agent's own skills directory.

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.