Sentry issues and events
Reads Sentry issues and events through the sentry CLI without changing anything: recent production errors, issue and event details, AI root-cause summaries, with PII redacted. Use when you ask what is failing in production according to Sentry.
sentry- Author
- OpenAI
- Source
- openai/skills/skills/.curated/sentry @ 49f948f
- License
- Apache-2.0
About this skill
What it does
The skill reads production errors from Sentry through the sentry command-line tool and changes nothing there. It lists issues, opens one by its short ID (ABC-123), pulls the issue's events and single-event details, and can run the CLI's AI root-cause analysis (sentry issue explain) and fix plan (sentry issue plan). Anything without a dedicated command goes through sentry api ... --method GET, with sentry schema to find the endpoint.
The CLI detects the organization and project from DSNs in .env files, source code, config defaults and directory names; <org>/<project> is passed only when it guesses wrong. Defaults are the last 24 hours, the production environment and 20 results, with --json --fields to keep output small. An issue list shows title, short ID, status, first and last seen, count, environments and top tags, newest first; an event shows culprit, timestamp, environment, release and URL. Emails and IPs are redacted, raw stack traces are not printed, tokens are never echoed, and the agent never asks you to paste a token into the chat.
There are no scripts: the folder holds SKILL.md, agents/openai.yaml, icons and the licence.
When to use it, and when not
Use it to answer "what broke in production since yesterday", or to study an issue and its releases before fixing it.
It does not resolve, assign or comment on issues, and it does not touch your code. Without access to a Sentry organization it has nothing to read.
How to run it
The install command below puts the folder in place. Then install the CLI with curl https://cli.sentry.dev/install -fsS | bash and log in with sentry auth login, or set SENTRY_AUTH_TOKEN; sentry auth status confirms it works. The agent picks the skill up by its description; to call it yourself:
- Claude Code:
/sentry, or ask for the skill by name. - Codex:
$sentry. - Cursor: type
/in the Agent chat and picksentry.
Example: /sentry List the ten newest unresolved production issues from the last 24 hours.
OpenAI has marked openai/skills deprecated; our copy is pinned to a commit there. The sentry skill in openai/plugins is an older version that queries the API through a bundled script instead of the Sentry CLI.
How it differs from similar skills
Log triage works on raw logs and finds the first failure by request ID and timestamp; this skill starts from errors Sentry has already grouped into issues. Observability and instrumentation decides before a release what gets logged and alerted on. The Sentry pack in this catalog comes from Sentry's own repository and covers code review, security and commits; none of its skills reads Sentry data. Once the cause is clear, Root-cause debugging takes the fix.
Install
Run one command — it saves SKILL.md and the files it uses into your agent's skills folder. Claude Code and Codex pick up a new skill without a restart; if it does not show up, restart the agent.
curl -fsSL --create-dirs -o ~/.claude/skills/sentry/SKILL.md https://anymodel.org/en/skills/openai/sentry/SKILL.md -o ~/.claude/skills/sentry/LICENSE.txt https://anymodel.org/en/skills/openai/sentry/LICENSE.txt -o ~/.claude/skills/sentry/agents/openai.yaml https://anymodel.org/en/skills/openai/sentry/agents/openai.yaml -o ~/.claude/skills/sentry/assets/sentry-small.svg https://anymodel.org/en/skills/openai/sentry/assets/sentry-small.svg -o ~/.claude/skills/sentry/assets/sentry.png https://anymodel.org/en/skills/openai/sentry/assets/sentry.png
curl -fsSL --create-dirs -o ~/.agents/skills/sentry/SKILL.md https://anymodel.org/en/skills/openai/sentry/SKILL.md -o ~/.agents/skills/sentry/LICENSE.txt https://anymodel.org/en/skills/openai/sentry/LICENSE.txt -o ~/.agents/skills/sentry/agents/openai.yaml https://anymodel.org/en/skills/openai/sentry/agents/openai.yaml -o ~/.agents/skills/sentry/assets/sentry-small.svg https://anymodel.org/en/skills/openai/sentry/assets/sentry-small.svg -o ~/.agents/skills/sentry/assets/sentry.png https://anymodel.org/en/skills/openai/sentry/assets/sentry.png
foreach ($f in 'SKILL.md','LICENSE.txt','agents/openai.yaml','assets/sentry-small.svg','assets/sentry.png') { $p = Join-Path "$HOME\.claude\skills\sentry" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/openai/sentry/$f" -UseBasicParsing -OutFile $p }foreach ($f in 'SKILL.md','LICENSE.txt','agents/openai.yaml','assets/sentry-small.svg','assets/sentry.png') { $p = Join-Path "$HOME\.agents\skills\sentry" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/openai/sentry/$f" -UseBasicParsing -OutFile $p }Any other agent: save the file into its skills folder, or give it the link to the file: https://anymodel.org/en/skills/openai/sentry/SKILL.md
SKILL.md
Sentry (Read-only Observability)
Quick start
- If not already authenticated, ask the user to run
sentry auth loginor setSENTRY_AUTH_TOKENas an env var. - The CLI auto-detects org/project from DSNs in
.envfiles, source code, config defaults, and directory names. Only specify<org>/<project>if auto-detection fails or picks the wrong target. - Defaults: time range
24h, environmentproduction, limit 20. - Always use
--jsonwhen processing output programmatically. Use--json --fieldsto select specific fields and reduce output size. - Use
sentry schema <resource>to discover API endpoints quickly.
If the CLI is not installed, give the user these steps:
- Install the Sentry CLI:
curl https://cli.sentry.dev/install -fsS | bash - Authenticate:
sentry auth login - Confirm authentication:
sentry auth status
- Never ask the user to paste the full token in chat. Ask them to set it locally and confirm when ready.
Core tasks (use Sentry CLI)
Use the sentry CLI for all queries. It handles authentication, org/project detection, pagination, and retries automatically. Use --json for machine-readable output.
1) List issues (ordered by most recent)
sentry issue list \
--query "is:unresolved environment:production" \
--period 24h \
--limit 20 \
--json --fields shortId,title,priority,level,status
If auto-detection doesn't resolve org/project, pass them explicitly:
sentry issue list {your-org}/{your-project} \
--query "is:unresolved environment:production" \
--period 24h \
--limit 20 \
--json
2) Resolve an issue short ID to issue detail
sentry issue view {ABC-123} --json
Use the short ID format (e.g., ABC-123), not the numeric ID.
3) Issue detail
sentry issue view {ABC-123}
4) Issue events
sentry issue events {ABC-123} --limit 20 --json
5) Event detail
sentry event view {your-org}/{your-project}/{event_id} --json
6) AI-powered root cause analysis
sentry issue explain {ABC-123}
7) AI-powered fix plan
sentry issue plan {ABC-123}
Fallback: arbitrary API access
For endpoints not covered by dedicated CLI commands, use sentry api:
sentry api /api/0/organizations/{your-org}/ --method GET
Use sentry schema to discover available API endpoints:
sentry schema issues
Inputs and defaults
org_slug,project_slug: auto-detected by the CLI from DSNs, env vars, and directory names. Override with positional{your-org}/{your-project}if auto-detection fails.time_range: default24h(pass as--period 24h).environment: defaultprod(pass as part of--query, e.g.,environment:production).limit: default 20 (pass as--limit).search_query: optional--queryparameter, uses Sentry search syntax (e.g.,is:unresolved,assigned:me).issue_short_id: use directly withsentry issue view.
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.
Connect through AnyModel API
This skill runs on whatever model your agent uses. Point Claude Code, Codex or Cursor at AnyModel to run it on Claude, GPT, Gemini and more with one key — pay per token, no subscription.
AnyModel