Back to directory

Sentry for AI

A source repository of skills that teach an AI coding assistant how to set up Sentry error monitoring in a project, triage and fix production issues, and configure alerts, distributed as plugins for Claude Code, Cursor, Codex and Grok rather than installed directly.

Sentry for AI

Sentry for AI is built, not installed, from this repository: per-agent build scripts produce a generic Agent Plugin and separate client-specific plugins for Claude Code, Cursor, Codex and Grok, each deployed by continuous integration to its own distribution repository, and the same skills are also served directly over HTTP for an agent to fetch.

Once a built plugin is installed in a supported assistant, a developer can ask it to add Sentry to a new project, such as a Next.js or Rails app, with a setup wizard that detects the stack and walks through the full installation instead of copying from documentation by hand; query recent errors and see which issues affect the most users; automatically resolve bugs that Sentry or its Seer feature flagged in a pull request's comments; and configure monitoring, such as a Slack alert for high-priority issues or an OpenTelemetry collector pointed at Sentry.

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.