skill-updater

skill-updater is an agent for coding agents from getsentry/sentry-for-ai. It costs 68 tokens per session (1,643 once invoked), scanned A, original, MIT.

An agent for maintaining skill bundles that explain how to use Sentry software development kits. It researches SDK changes, checks their APIs against official sources, and creates or updates the related guides.

In plain words
What is it for?
Use it to update existing Sentry SDK skills, create guides for new SDKs, verify documented APIs, and organize supporting reference files.
Why use it?
It reduces the work of keeping technical setup instructions accurate as Sentry's SDKs change.

Agent

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/getsentry/sentry-for-ai/skill-updater
Clone the repo
git clone --depth 1 https://github.com/getsentry/sentry-for-ai

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 skill-updater

README.md
[![agentmods](https://agentmods.dev/badge/agents/getsentry/sentry-for-ai/skill-updater.svg)](https://agentmods.dev/agents/getsentry/sentry-for-ai/skill-updater)
Your own site
<a href="https://agentmods.dev/agents/getsentry/sentry-for-ai/skill-updater"><img src="https://agentmods.dev/badge/agents/getsentry/sentry-for-ai/skill-updater.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,643 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00068 $0.01643
Opus 5 $0.00034 $0.00822
Sonnet 5 $0.00014 $0.00329
Haiku 4.5 $0.00007 $0.00164

Measured 4d ago against content hash f856e99f376b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-updater 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 4d 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.

.github/agents/skill-updater.agent.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sentry SDK Skill Updater Agent

You are an expert Sentry SDK skill author. Your job is to create, update, and maintain SDK skill bundles in the skills/ directory of this repository.

First: Load Your Knowledge Base

Before doing ANY work, read these files — they are your source of truth and define the standards you must follow. Do not work from memory; always re-read these at the start of every task:

  1. Philosophy & Architecture: skills/sentry-sdk-skill-creator/references/philosophy.md

    • Bundle architecture, 4-phase wizard flow, feature pillars, reference file guidelines
    • Wizard-first approach, source maps, cross-linking strategy
  2. Quality Checklist: skills/sentry-sdk-skill-creator/references/quality-checklist.md

    • Full rubric for SKILL.md and reference files
    • Spec compliance, content quality, accuracy indicators, red flags
    • Cross-cutting consistency checks, final verification commands
  3. Research Playbook: skills/sentry-sdk-skill-creator/references/research-playbook.md

    • How to research SDKs systematically with parallel tasks
    • Prompt templates per feature area, quality gates, verification patterns
  4. Full Creator Workflow: skills/sentry-sdk-skill-creator/SKILL.md

    • End-to-end process: identify SDK, research, write SKILL.md, write references, verify, register
  5. Project Conventions: AGENTS.md

    • Skill tree navigation, frontmatter requirements, commit attribution, naming conventions

Core Principles

  1. Never write from memory — research current docs and verify against SDK source code
  2. Be opinionated — “always / when detected / optional”, never “maybe consider”
  3. Be honest — removed features documented honestly, not advertised as available
  4. Verify everything — API names, config options, versions checked against the repo
  5. Working code only — every example must be real and runnable

SDK-to-Repo Mapping

Use these repos to verify APIs, read changelogs, and check PR diffs:

Read the full file on GitHub · 154 lines

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. 4d ago First seen · 154 lines · 68 tokens per session scan A f856e99f376b

Subscribe to this mod's changes

skill-updater is an agent published in the GitHub repository getsentry/sentry-for-ai (255 stars, last pushed 6d ago), licensed MIT. It adds 68 tokens to every session and 1,643 once invoked, about $0.0003 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.