openai-sentry — Claude Code skill: what it does, how to install
The openai-sentry Claude Code skill reads Sentry issues and events through the API and summarizes production errors in a compact report.
Apache-2.0 ★ 540 updated 2026-07-14
/plugin marketplace add trailofbits/skills-curated
/plugin install openai-sentry@skills-curatedWhat openai-sentry does
The skill calls Sentry through scripts/sentry_api.py. It can list issues, fetch issue details, and retrieve related events, with filters for time range, environment, and search query. Issue results include fields such as status, first and last seen times, and event count. Personal information is redacted.
Set SENTRY_AUTH_TOKEN locally before running it, using a token with read access. The defaults are a 24h time range, the prod environment, and a limit of 20 results; the maximum is 50. The script paginates through results and retries once after a transient error. Without the token, it cannot query Sentry; it also avoids printing raw stack traces or authentication tokens.
What it helps with
- find open Sentry issues from a chosen period
- inspect events linked to an issue
- summarize recent production errors
- check basic Sentry project health
Example prompts for the agent
- List open Sentry issues for
your-organdyour-projectfrom the last24h. - Fetch events for issue
ABC-123and summarize their environment and timestamps. - Summarize the latest production errors in my Sentry project.
How to install openai-sentry
1Plugin marketplace
/plugin marketplace add trailofbits/skills-curated/plugin install openai-sentry@skills-curatedThis installs the whole openai-sentry plugin with all its skills
2Skills CLI (Vercel)
npx skills add trailofbits/skills-curated --skill openai-sentry -a claude-code3Manually: put the files in place
~/.claude/skills/openai-sentry/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/openai-sentry/
1Skills CLI (Vercel)
npx skills add trailofbits/skills-curated --skill openai-sentry -a codex2Manually: put the files in place
.agents/skills/openai-sentry/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add trailofbits/skills-curated --skill openai-sentry -a cursor2Manually: put the files in place
.cursor/skills/openai-sentry/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install trailofbits/skills-curated plugins/openai-sentry/skills/openai-sentry2Manually: put the files in place
.github/skills/openai-sentry/SKILL.md1Skills CLI (Vercel)
npx skills add trailofbits/skills-curated --skill openai-sentry -a gemini-cli2Platform CLI
gemini skills install https://github.com/trailofbits/skills-curated --path plugins/openai-sentry/skills/openai-sentryManually: put the files in place
.devin/skills/openai-sentry/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about openai-sentry
How do I install openai-sentry in Claude Code?
Run these commands in order: /plugin marketplace add trailofbits/skills-curated, then /plugin install openai-sentry@skills-curated.
What does openai-sentry do?
It queries Sentry issues and events through the API and presents a summary of errors and project data. Its requests are read-only.
What token does openai-sentry need?
Set SENTRY_AUTH_TOKEN locally with read scopes such as project:read and event:read. The skill does not print the token or ask you to paste it into chat.
Source text
SKILL.md · Apache-2.0
---
name: openai-sentry
description: Use when the user asks to inspect Sentry issues or events, summarize recent production errors,
or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script
and require `SENTRY_AUTH_TOKEN`. Originally from OpenAI's curated skills catalog.
allowed-tools:
- Bash
- Read
- Grep
- Glob
- Write
- Edit
---
# Sentry (Read-only Observability)
## Quick start
- If not already authenticated, ask the user to provide a valid `SENTRY_AUTH_TOKEN` (read-only scopes such as `project:read`, `event:read`) or to log in and create one before running commands.
- Set `SENTRY_AUTH_TOKEN` as an env var.
- Optional defaults: `SENTRY_ORG`, `SENTRY_PROJECT`, `SENTRY_BASE_URL`.
- Defaults: org/project `{your-org}`/`{your-project}`, time range `24h`, environment `prod`, limit 20 (max 50).
- Always call the Sentry API (no heuristics, no caching).
If the token is missing, give the user these steps:
1. Create a Sentry auth token: https://sentry.io/settings/account/api/auth-tokens/
2. Create a token with read-only scopes such as `project:read`, `event:read`, and `org:read`.
3. Set `SENTRY_AUTH_TOKEN` as an environment variable in their system.
4. Offer to guide them through setting the environment variable for their OS/shell if needed.
- Never ask the user to paste the full token in chat. Ask them to set it locally and confirm when ready.
## Core tasks (use bundled script)
Use `scripts/sentry_api.py` for deterministic API calls. It handles pagination and retries once on transient errors.
Scripts and references are located under `{baseDir}/`.
## API requirements
Always use these endpoints (GET only):
- List issues: `/api/0/projects/{org_slug}/{project_slug}/issues/`
- Issue detail: `/api/0/issues/{issue_id}/`
- Events for issue: `/api/0/issues/{issue_id}/events/`
- Event detail: `/api/0/projects/{org_slug}/{project_slug}/events/{event_id}/`
## Inputs and defaults
- `org_slug`, `project_slug`: default to `{your-org}`/`{your-project}` (avoid non-prod orgs).
- `time_range`: default `24h` (pass as `statsPeriod`).
- `environment`: default `prod`.
- `limit`: default 20, max 50 (paginate until limit reached).
- `search_query`: optional `query` parameter.
- `issue_short_id`: resolve via list-issues query first.
## Output formatting rules
- Issue list: show title, short_id, status, first_seen, last_seen, count, environments, top_tags; order by most recent.
- Event detail: include culprit, timestamp, environment, release, url.
- If no results, state explicitly.
- Redact PII in output (emails, IPs). Do not print raw stack traces.
- Never echo auth tokens.
## Golden test inputs
- Org: `{your-org}`
- Project: `{your-project}`
- Issue short ID: `{ABC-123}`
Example prompt: “List the top 10 open issues for prod in the last 24h.”
Expected: ordered list with titles, short IDs, counts, last seen.
## When to Use
<!-- TODO: review -->
## When NOT to Use
<!-- TODO: review -->
© OpenAI · Apache-2.0 · trailofbits/skills-curated