upgrade-setup

upgrade-setup is a skill for Claude Code from a2ngerer/claude_onboarding_agent. It costs 80 tokens per session (5,084 once invoked), scanned B, original, MIT.

A guided updater for an existing Claude Code setup. It compares the setup with newer recommended templates, shows each proposed change, and can back up files before applying approved updates.

In plain words
What is it for?
Use it to review and selectively refresh an onboarding-agent setup, either normally or with a dry run.
Why use it?
It keeps setup guidance current while giving you control over changes and protecting existing customizations.

Skill for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

Part of the claude-onboarding-agent plugin — 16 skills, 4 agents, 1 hook shipped together

Good fit Use it to review and selectively refresh an onboarding-agent setup, either normally or with a dry run.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/a2ngerer/claude_onboarding_agent/upgrade-setup
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.

Any agent
npx skills add a2ngerer/claude_onboarding_agent --skill upgrade-setup
Clone the repo
git clone --depth 1 https://github.com/a2ngerer/claude_onboarding_agent

Made for: Claude Code.

Or install claude-onboarding-agent, the plugin that ships this one along with the rest of its 16 skills, 4 agents, 1 hook.

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 upgrade-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/a2ngerer/claude_onboarding_agent/upgrade-setup/github.svg)](https://agentmods.dev/skills/a2ngerer/claude_onboarding_agent/upgrade-setup)
Your own site
<a href="https://agentmods.dev/skills/a2ngerer/claude_onboarding_agent/upgrade-setup"><img src="https://agentmods.dev/badge/skills/a2ngerer/claude_onboarding_agent/upgrade-setup/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 upgrade-setup

Your own site · 80×15
<a href="https://agentmods.dev/skills/a2ngerer/claude_onboarding_agent/upgrade-setup"><img src="https://agentmods.dev/badge/skills/a2ngerer/claude_onboarding_agent/upgrade-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,084 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00080 $0.05084
Opus 5 $0.00040 $0.02542
Sonnet 5 $0.00016 $0.01017
Haiku 4.5 $0.00008 $0.00508

Measured 9d ago against content hash 81a756f4660b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

upgrade-setup scanned grade B with 1 finding 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 9d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- `./.claude/settings.json` (if the skill generates one)
skills/upgrade-setup/SKILL.md · 404 lines

How it starts

The opening of the file, as written. The whole thing — 404 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Upgrade Setup — Selective Best-Practice Refresh

Power-user / internal tool. Normal users run /checkup, which decides whether /upgrade-setup is the right action and invokes it automatically. Running /upgrade-setup directly still works — use it when you already know you want to re-apply current best practices.

Use this skill to bring an existing setup up to the current plugin's defaults without destroying user customizations. It is the non-audit counterpart to /audit-setup:

Skill Read-only Applies changes Per-change confirmation Backup
/audit-setup yes no n/a n/a
/upgrade-setup no yes yes (y/n/all/skip-rest) yes

This skill is a protocol. Run every pass in order. Do not skip passes, and do not apply changes before Pass 3 confirms each one.

Language

Detect language from the user's first message in this invocation and respond in it throughout. All file content written to disk stays in English (see the repo language rule in CLAUDE.md).

Argument parsing

The invocation may contain --dry-run anywhere in the argument string (as a flag, not a value).

  • If present: set dry_run: true. Pass 4 prints every diff but writes no files.
  • Otherwise: set dry_run: false. Pass 4 runs normally.

If any other argument is passed, ignore it silently (forward compatibility — do not error).


Pass 1 — Detect the existing setup

Step 1.1 — Read the meta file

Read ./.claude/onboarding-meta.json if it exists. Expected shape:

{
  "setup_type": "coding",
  "skills_used": ["coding-setup"],
  "plugin_version": "0.9.0",
  "installed_at": "2026-04-01T12:00:00Z",
  "upgraded_at": null
}

If the file parses and setup_type is a recognized slug (one of: coding, data-science, design, knowledge-base, devops, content-voice, office, research, academic-writing, web-development), set:

Read the full file on GitHub · 404 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. 9d ago First seen · 404 lines · 80 tokens per session scan B 81a756f4660b

Subscribe to this mod's changes

upgrade-setup is a skill published in the GitHub repository a2ngerer/claude_onboarding_agent (5 stars, last pushed today), licensed MIT. It adds 80 tokens to every session and 5,084 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens