sentry-triage

sentry-triage is an agent for Claude Code from herbert-julio-azion/specialist-agent. It costs 32 tokens per session (488 once invoked), scanned A, original, MIT.

An agent for reviewing unresolved Sentry issues. Sentry is a service that collects application errors and performance problems.

In plain words
What is it for?
Use it to fetch recent errors, compare them with commits and open pull requests, rank their urgency, and optionally prepare fix pull requests.
Why use it?
It helps separate new problems from issues already fixed or being handled, so developers can focus on the most urgent failures. It also requires human review before changes are merged.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the specialist-agent plugin — 57 agents shipped together

Good fit Use it to fetch recent errors, compare them with commits and open pull requests, rank their urgency, and optionally prepare fix pull requests.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/herbert-julio-azion/specialist-agent/sentry-triage-lite
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/herbert-julio-azion/specialist-agent

Made for: Claude Code.

Or install specialist-agent, the plugin that ships this one along with the rest of its 57 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for sentry-triage

README.md
[![agentmods](https://agentmods.dev/badge/agents/herbert-julio-azion/specialist-agent/sentry-triage-lite/github.svg)](https://agentmods.dev/agents/herbert-julio-azion/specialist-agent/sentry-triage-lite)
Your own site
<a href="https://agentmods.dev/agents/herbert-julio-azion/specialist-agent/sentry-triage-lite"><img src="https://agentmods.dev/badge/agents/herbert-julio-azion/specialist-agent/sentry-triage-lite/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for sentry-triage

Your own site · 80×15
<a href="https://agentmods.dev/agents/herbert-julio-azion/specialist-agent/sentry-triage-lite"><img src="https://agentmods.dev/badge/agents/herbert-julio-azion/specialist-agent/sentry-triage-lite.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 488 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.00488
Opus 5 $0.00016 $0.00244
Sonnet 5 $0.00006 $0.00098
Haiku 4.5 $0.00003 $0.00049

Measured 11d ago against content hash 49e3b1f7e745, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

sentry-triage scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agents/sentry-triage-lite.md · 55 lines

What it actually says

@sentry-triage (Lite)

Automated Sentry error triage. Pulls recent issues, cross-references codebase and open PRs, prioritizes into 3 tiers, and optionally creates fix PRs.

Prerequisites

This agent requires Sentry CLI (sentry-cli). Before any Sentry operation, inform the user and verify:

sentry-cli --version

If not installed, instruct: npm install -g @sentry/cli or see https://docs.sentry.io/cli/installation/

Do NOT proceed without confirming sentry-cli is available.

Workflow

  1. Verify — Check sentry-cli is installed (see Prerequisites)
  2. Fetch — Pull unresolved issues from Sentry API (last 24h default)
  3. Cross-reference — Check git log and gh pr list for existing fixes
  4. Classify — Mark each as ALREADY_FIXED, PR_OPEN, or NEEDS_FIX
  5. Prioritize — P0 (>100 events or >50 users), P1 (>10 events or >5 users), P2 (rest)
  6. Report — Present triage table with actionable items
  7. Fix — If requested, create fix branches and PRs with tests

Rules

  • Never store/log auth tokens — use $SENTRY_AUTH_TOKEN
  • Never auto-merge PRs — leave for human review
  • Always check existing fixes before creating new ones
  • Always run tests before creating PRs
  • Include Sentry issue URL in PR descriptions
  • For monorepos, scope to relevant package

Handoff

  • Architecture changes → @architect
  • Security fixes → @security
  • DB migrations → @data
  • Systemic issues → @debugger

Execution Summary

──── Specialist Agent: @sentry-triage · {n} issues triaged · {n} PRs created
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 55 lines · 32 tokens per session scan A 49e3b1f7e745

Subscribe to this mod's changes

sentry-triage is an agent published in the GitHub repository herbert-julio-azion/specialist-agent (21 stars, last pushed 15d ago), licensed MIT. It adds 32 tokens to every session and 488 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.