{
  "markdown": "# Sentry for AI\n\n> [!IMPORTANT]\n> **This is a skill *source* repository — not something you install directly.** The\n> skills here are built from this source into a portable\n> [Agent Plugin](https://github.com/getsentry/agent-plugin) and installable\n> client-specific plugins for [Claude Code](https://github.com/getsentry/plugin-claude),\n> [Cursor](https://github.com/getsentry/plugin-cursor),\n> [Codex](https://github.com/getsentry/plugin-codex), and\n> [Grok](https://github.com/getsentry/plugin-grok) — install one of those, not this\n> repo. They’re also served over HTTP at [skills.sentry.dev](https://skills.sentry.dev)\n> for agents to fetch directly.\n> In the future we may also publish the skills as a generic, standalone skills\n> repository.\n\nYour AI coding assistant already knows how to write code.\nThis plugin teaches it Sentry — how to set it up, how to find and fix production issues,\nand how to get the most out of every feature.\n\nWhether you’re adding Sentry to a new project, debugging a spike in errors, or\nconfiguring alerts, just ask.\nThe plugin gives your assistant the context it needs to do it right.\n\nSupports the [**Agent Plugins standard**](https://agent-plugins.org/),\n[**Claude Code**](https://github.com/getsentry/plugin-claude),\n[**Cursor**](https://github.com/getsentry/plugin-cursor),\n[**Codex**](https://github.com/getsentry/plugin-codex), and\n[**Grok**](https://github.com/getsentry/plugin-grok).\n\n## What You Can Do\n\n**Set up Sentry in any project** — SDK setup wizards that detect your stack, recommend\nthe right features, and walk through the full installation.\nNo copy-pasting from docs.\n\n```\nAdd Sentry to my Next.js app\nSet up Sentry in my Rails project\nAdd error monitoring to my iOS app\n```\n\n**Find and fix production issues** — Query your Sentry environment, triage errors, and\nfix them in place.\n\n```\nWhat are the top errors in the last 24 hours?\nWhich issues are affecting the most users?\nFix the recent Sentry errors\n```\n\n**Review code with Sentry context** — Automatically resolve bugs that Sentry or Seer\nflag in pull request comments.\n\n```\nReview PR #118 and fix the Sentry comments\n```\n\n**Configure monitoring** — Set up alerts, instrument AI/LLM calls, connect OpenTelemetry\npipelines.\n\n```\nCreate a Slack alert for new high-priority issues\nMonitor my OpenAI calls with Sentry\nSet up OTel Collector with Sentry exporter\n```\n\n## Distribution\n\nThis repository is the single source of truth for all skills, but it is not itself an\ninstallable plugin.\nEach assistant needs the plugin in a slightly different shape, so the\nper-agent plugins are **built** from it by the build scripts under\n`src/plugins/<agent>/build.sh`. CI runs these on every push and deploys each result to\nits own **distribution repository**, whose root is exactly that agent’s plugin:\n\n| Agent | Distribution repository |\n| --- | --- |\n| Agent Plugins 1.0.0 | [`getsentry/agent-plugin`](https://github.com/getsentry/agent-plugin) |\n| Claude Code | [`getsentry/plugin-claude`](https://github.com/getsentry/plugin-claude) |\n| Cursor | [`getsentry/plugin-cursor`](https://github.com/getsentry/plugin-cursor) |\n| Codex | [`getsentry/plugin-codex`](https://github.com/getsentry/plugin-codex) |\n| Grok | [`getsentry/plugin-grok`](https://github.com/getsentry/plugin-grok) |\n\nThese repositories are generated; do not edit them.\nEach one’s README has the install instructions for that agent.\n\nThe skill library is also browsable at [skills.sentry.dev](https://skills.sentry.dev)\nand available through the [`skills.sh`](https://www.skills.sh/getsentry/sentry-for-ai)\ninstaller.\n\n### Build it yourself\n\nEach `src/plugins/<agent>/build.sh` takes an output directory and writes that agent’s\nplugin into it (the Codex build moves the plugin under `plugins/sentry/` and swaps the\nskill tree’s `disable-model-invocation` flags for Codex’s `agents/openai.yaml` policy):\n\n```bash\ngit clone https://github.com/getsentry/sentry-for-ai.git\ncd sentry-for-ai\nsrc/plugins/agent-plugin/build.sh /tmp/sentry-agent-plugin\n```\n\nTo build any target locally, run `src/plugins/<agent>/build.sh <output-dir>`\n(`agent-plugin`, `claude`, `cursor`, `codex`, or `grok`).\n\n## Skills\n\n### Core\n\n| Skill | What it does |\n| --- | --- |\n| `sentry-get-started` | Guided entry point — orients to your current Sentry setup and routes to the right skill |\n| `sentry-instrument` | Add Sentry to a project, or wire up any signal — error monitoring, tracing, logging, metrics, profiling, session replay, user feedback, cron check-ins, and AI/LLM monitoring. Detects your platform and pulls the code from the reference library. |\n| `sentry-debug-issue` | Find a Sentry issue, pull full context, optionally run Seer root-cause / autofix, apply the fix, and resolve it |\n\n### Feature Setup\n\n| Skill | What it does |\n| --- | --- |\n| `sentry-otel-exporter-setup` | Configure OTel Collector with the Sentry exporter for multi-project routing |\n| `sentry-create-alert` | Create alerts via the Sentry workflow engine API |\n| `sentry-snapshots-cocoa` | Set up Sentry Snapshots for Apple/Cocoa projects |\n\n### Reference Library\n\n`sentry-instrument` doesn’t hard-code platform steps — it pulls them from a shared\nlibrary that the build hydrates into the skill:\n\n- **`src/references/sdks/<platform>/`** — per-platform install and per-signal code, one\n  directory per supported platform.\n- **`src/references/concepts/`** — per-signal strategy: errors, tracing, logging,\n  metrics, profiling, session replay, user feedback, crons, releases, data scrubbing,\n  and choosing-a-signal.\n\n> Superseded per-SDK “wizard” skills are frozen under `skills-legacy/`, excluded from\n> the plugin build.\n\n## Prerequisites\n\nThe plugin configures the [Sentry MCP server](https://mcp.sentry.dev) automatically on\ninstall. No extra setup needed.\n\nSome skills require the [GitHub CLI](https://cli.github.com/):\n\n```bash\nbrew install gh    # macOS\ngh auth login\n```\n\n## Contributing\n\nSkills follow the [Agent Skills specification](https://agentskills.io).\nEach skill is a directory with a `SKILL.md` file containing YAML frontmatter and\nmarkdown instructions.\nA skill can declare the shared references it needs in a `references.yml` manifest; the\nbuild hydrates the matching files from the shared library at `references/` into the\nskill so the shipped copy is self-contained.\n\n## License\n\nMIT\n",
  "bytes": 6327,
  "sha": "fd36d08516ea95124519119e2194177777ee204624014737cf43e21ef0aad1df",
  "repo_slug": "getsentry/sentry-for-ai",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/skl_getsentry_sentry_for_ai_sentry_cloudflar_74ed7dfd/readme"
}