本文へ移動
cccskills
無料GitHub で公開

sentry-monitoring

Sentry error tracking and performance monitoring for real-time visibility into application errors, performance issues, and release health

インストール方法を見る

含まれるファイル(10)

  • SKILL.md7.5 KB
  • commands/sentry-monitoring.md117 B
  • hooks/post-execute.cjs878 B
  • hooks/pre-execute.cjs877 B
  • references/research-requirements.md422 B
  • rules/sentry-monitoring.md393 B
  • schemas/input.schema.json271 B
  • schemas/output.schema.json632 B
  • scripts/main.cjs1.4 KB
  • templates/implementation-template.md191 B

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Mode: Cognitive/Prompt-Driven — No standalone utility script; use via agent context.

Sentry Monitoring Skill

Overview

Provides 90%+ context savings vs raw Sentry API calls. Progressive disclosure by feature category: error tracking, performance monitoring, release management, and project configuration.

Requirements

  • Sentry account with project configured
  • SENTRY_AUTH_TOKEN environment variable (optional, for authenticated API calls)
  • SENTRY_ORG environment variable (optional, defaults to first organization)
  • SENTRY_PROJECT environment variable (optional, defaults to first project)

Tools (Progressive Disclosure)

Error Tracking

ToolDescriptionConfirmation
list-issuesList recent issues/errorsNo
issue-detailsGet detailed issue infoNo
resolve-issueMark issue as resolvedYes
ignore-issueIgnore/snooze issueYes

Performance Monitoring

ToolDescriptionConfirmation
list-transactionsList performance transactionsNo
transaction-summaryGet transaction performance statsNo
slow-queriesIdentify slow database queriesNo

Release Management

ToolDescriptionConfirmation
list-releasesList releasesNo
create-releaseCreate new releaseYes
set-commitsAssociate commits with releaseYes

Project Configuration

ToolDescriptionConfirmation
list-projectsList Sentry projectsNo
project-settingsView project settingsNo
list-alertsList alert rulesNo

Quick Reference

# List recent issues
curl -H "Authorization: Bearer $SENTRY_AUTH_TOKEN" \
  "https://sentry.io/api/0/projects/$SENTRY_ORG/$SENTRY_PROJECT/issues/?query=is:unresolved"

# Get issue details
curl -H "Authorization: Bearer $SENTRY_AUTH_TOKEN" \
  "https://sentry.io/api/0/issues/{issue_id}/"

# Resolve issue
curl -X PUT -H "Authorization: Bearer $SENTRY_AUTH_TOKEN" \
  "https://sentry.io/api/0/issues/{issue_id}/" \
  -d '{"status": "resolved"}'

# List transactions
curl -H "Authorization: Bearer $SENTRY_AUTH_TOKEN" \
  "https://sentry.io/api/0/organizations/$SENTRY_ORG/events/?field=transaction"

# Create release
curl -X POST -H "Authorization: Bearer $SENTRY_AUTH_TOKEN" \
  "https://sentry.io/api/0/organizations/$SENTRY_ORG/releases/" \
  -d '{"version": "1.0.0", "projects": ["project-slug"]}'

# List projects
curl -H "Authorization: Bearer $SENTRY_AUTH_TOKEN" \
  "https://sentry.io/api/0/organizations/$SENTRY_ORG/projects/"

Configuration

Environment Variables

VariableRequiredDescription
SENTRY_AUTH_TOKENOptionalSentry authentication token for API calls
SENTRY_ORGOptionalOrganization slug (defaults to first org)
SENTRY_PROJECTOptionalProject slug (defaults to first project)
SENTRY_DSNNoFor SDK integration (not used by this skill)

Getting Auth Token

  1. Navigate to Sentry Settings → Account → API → Auth Tokens
  2. Create new token with scopes: project:read, project:write, event:read
  3. Set as environment variable: export SENTRY_AUTH_TOKEN=your_token_here

Security

⚠️ Never expose auth tokens in output ⚠️ Destructive operations (resolve-issue, ignore-issue, create-release, set-commits) require confirmation ⚠️ Use environment variables for credentials, never hardcode

Agent Integration

  • devops (primary): Production monitoring, incident response
  • incident-responder (primary): Error triage, issue resolution
  • developer (secondary): Debugging, performance optimization
  • qa (secondary): Test environment monitoring

Error Handling

If tool execution fails:

  1. Verify SENTRY_AUTH_TOKEN is set: echo $SENTRY_AUTH_TOKEN
  2. Check token permissions include required scopes
  3. Verify organization and project slugs are correct
  4. Review Sentry API rate limits (default: 3000 requests/minute)

Common Workflows

Incident Response

  1. list-issues - Get recent unresolved errors
  2. issue-details - Investigate specific issue
  3. resolve-issue - Mark as resolved after fix deployed

Performance Optimization

  1. list-transactions - Identify slow endpoints
  2. transaction-summary - Analyze performance patterns
  3. slow-queries - Find database bottlenecks

Release Management

  1. create-release - Create new release version
  2. set-commits - Associate commits with release
  3. list-releases - Track release health

Troubleshooting

IssueSolution
401 UnauthorizedCheck SENTRY_AUTH_TOKEN is valid and not expired
403 ForbiddenVerify token has required scopes (project:read, project:write, event:read)
404 Not FoundVerify SENTRY_ORG and SENTRY_PROJECT are correct slugs
Rate limit exceededWait 1 minute, reduce request frequency

Related

Memory Protocol (MANDATORY)

Before starting: Read .claude/context/memory/learnings.md

After completing:

  • New pattern -> .claude/context/memory/learnings.md
  • Issue found -> .claude/context/memory/issues.md
  • Decision made -> .claude/context/memory/decisions.md

ASSUME INTERRUPTION: If it's not in memory, it didn't happen.

OpenTelemetry + Grafana Stack

Auto-instrument with OTel, export to Sentry + Grafana simultaneously:

import { NodeSDK } from '@opentelemetry/sdk-node';
import { SentrySpanProcessor } from '@sentry/opentelemetry';
const sdk = new NodeSDK({ spanProcessor: new SentrySpanProcessor() });
sdk.start();

Continuous Profiling (Pyroscope)

# pyroscope.configure({ applicationName: 'api', serverAddress: 'http://pyroscope:4040' })

Grafana + Prometheus

services:
  prometheus: { image: prom/prometheus }
  grafana: { image: grafana/grafana }
  otel-collector: { image: otel/opentelemetry-collector-contrib }

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Ensure accessibility in UI components including semantic HTML, ARIA attributes, keyboard navigation, and WCAG 2.2 AA compliance.

日本語の概要は準備中です。原文の説明を表示しています。

oimiragieo/agent-studio432026年7月14日 更新

Use when you want to improve response quality through meta-cognitive reasoning. Applies 15+ reasoning methods to reconsider and refine initial outputs.

日本語の概要は準備中です。原文の説明を表示しています。

oimiragieo/agent-studio432026年7月14日 更新

N-round opposing-stance debates for trade-off analysis. Assigns pro/con roles to agents, runs structured debate rounds with quality scoring, and produces a moderator synthesis with confidence-rated recommendation. Generalizable to architecture, technology, security, and design decisions.

日本語の概要は準備中です。原文の説明を表示しています。

oimiragieo/agent-studio432026年7月14日 更新

Force adversarial code review stance that eliminates confirmation bias — reviewer must find issues or re-analyze

日本語の概要は準備中です。原文の説明を表示しています。

oimiragieo/agent-studio432026年7月14日 更新

Creates specialized AI agents on-demand when no existing agent matches a request. Use when the Router cannot find a suitable agent for a task. Enables self-evolution by generating persistent agents.

日本語の概要は準備中です。原文の説明を表示しています。

oimiragieo/agent-studio432026年7月14日 更新

LLM-as-judge evaluation framework with 5-dimension rubric (accuracy, groundedness, coherence, completeness, helpfulness) for scoring AI-generated content quality with weighted composite scores and evidence citations

日本語の概要は準備中です。原文の説明を表示しています。

oimiragieo/agent-studio432026年7月14日 更新

oimiragieo のスキルをすべて見る

このスキルの問題を報告する