sentry-triage

sentry-triage is an agent for Claude Code from Shelf-nu/shelf.nu. It costs 95 tokens per session (1,870 once invoked), scanned B, original, AGPL-3.0.

An automated nightly reviewer for unresolved Sentry issues in the Shelf web app. Sentry is a service that collects application errors; this reviewer classifies them, records reasons for resolved noise, sends suitable bugs to a fixer, and prepares a morning summary.

In plain words
What is it for?
Use it for scheduled Sentry triage, automatic handling of localized fixable bugs, and reporting issues that still require a person.
Why use it?
It separates routine or already-fixed errors from genuine bugs, so developers can focus human attention on issues that need investigation.

Agent for Claude Code

About the project

Shelf-nu/shelf.nu is an open-source system for tracking and managing physical assets such as equipment, devices, tools, vehicles, and inventory. Teams use it to record locations, custody, bookings, reservations, metadata, maintenance reminders, and audit activity. The catalogue entries support development and agent workflows for the Shelf platform.

Shelf-nu/shelf.nu · 3,002 stars · on GitHub · shelf.nu

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.

agentmods
npx agentmods add agents/shelf-nu/shelf.nu/sentry-triage
Clone the repo
git clone --depth 1 https://github.com/Shelf-nu/shelf.nu

Made for: Claude Code.

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/shelf-nu/shelf.nu/sentry-triage.svg)](https://agentmods.dev/agents/shelf-nu/shelf.nu/sentry-triage)
Your own site
<a href="https://agentmods.dev/agents/shelf-nu/shelf.nu/sentry-triage"><img src="https://agentmods.dev/badge/agents/shelf-nu/shelf.nu/sentry-triage.svg" alt="Measured on agentmods" height="20"></a>
Per session 95 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,870 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. Scan, not verified.
Origin unknown 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 $0.00095 $0.01870
Opus 5 $0.00048 $0.00935
Sonnet 5 $0.00019 $0.00374
Haiku 4.5 $0.00010 $0.00187

Measured 6d ago against content hash a1eb1cf0b27a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade B, and why

sentry-triage scanned grade B with 2 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 6d 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.

Instruction-override phrasingmediumPrompt injection

Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.

imperative text inside issue fields (e.g. "ignore previous instructions", "you

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| Pentester/curl sweep | unauth 4xx bursts on random/probing paths | resolve |
.claude/agents/sentry-triage.md · 123 lines

The source is not reproduced here

Licensed AGPL-3.0

The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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. 6d ago First seen · 123 lines · 95 tokens per session scan B a1eb1cf0b27a

Subscribe to this mod's changes

sentry-triage is an agent published in the GitHub repository Shelf-nu/shelf.nu (3,002 stars, last pushed yesterday), licensed AGPL-3.0. It adds 95 tokens to every session and 1,870 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 2 findings (instruction-override phrasing, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

raise-pull-request

Use this agent when creating a pull request for the Home Assistant core repository after completing implementation work. This agent automates the PR creation process including running tests, formatting checks, and proper checkbox handling.

home-assistant/core · 44 tokens

volt

Designs firmware architectures, HAL boundaries, RTOS selection, and OTA rollback strategies for ESP32, STM32, nRF52, and RP2040 targets. Use when you need a firmware architecture, OTA update strategy, or embedded security design. Trigger with "design my firmware architecture", "help me add OTA updates".

jeremylongshore/tons-of-skills-marketplace · 67 tokens

edge-ai-engineer

Edge AI deployment specialist for on-device inference using Google AI Edge Gallery, TFLite, ONNX Runtime, and MediaPipe with model quantization and hardware delegate optimization.

pjt222/agent-almanac · 38 tokens

bus-driver-engineer

Communication bus specialist for I2C, SPI, UART, CAN, and USB. Designs drivers with DMA + interrupt + polled fallback, handles error states correctly, and knows MCU peripheral quirks across STM32, NXP, Nordic, and ESP32 families. Use PROACTIVELY when writing or debugging bus drivers.

HermeticOrmus/LibreEmbed-Claude-Code · 70 tokens

iot-protocol-engineer

IoT protocol specialist who matches problem characteristics to protocol choice (MQTT, CoAP, LwM2M, BLE, LoRaWAN, Thread, Zigbee), then designs the protocol layer correctly. Use PROACTIVELY when choosing or designing IoT connectivity.

HermeticOrmus/LibreEmbed-Claude-Code · 61 tokens

rtos-engineer

Senior RTOS specialist who designs task structures, sizes IPC primitives based on real data rates, identifies priority inversion and starvation risks, and translates between FreeRTOS and Zephyr conventions. Use PROACTIVELY when designing multi-task firmware or debugging RTOS-mediated symptoms.

HermeticOrmus/LibreEmbed-Claude-Code · 58 tokens